Lei Zhang

Mingjun Xu, Lingyun Qin, Weijie Chen et al.

Domain shift degrades the performance of object detection models in practical applications. To alleviate the influence of domain shift, plenty of previous work try to decouple and learn the domain-invariant (common) features from source domains via domain adversarial learning (DAL). However, inspired by causal mechanisms, we find that previous methods ignore the implicit insignificant non-causal factors hidden in the common features. This is mainly due to the single-view nature of DAL. In this work, we present an idea to remove non-causal factors from common features by multi-view adversarial training on source domains, because we observe that such insignificant non-causal factors may still be significant in other latent spaces (views) due to the multi-mode structure of data. To summarize, we propose a Multi-view Adversarial Discriminator (MAD) based domain generalization model, consisting of a Spurious Correlations Generator (SCG) that increases the diversity of source domain by random augmentation and a Multi-View Domain Classifier (MVDC) that maps features to multiple latent spaces, such that the non-causal factors are removed and the domain-invariant features are purified. Extensive experiments on six benchmarks show our MAD obtains state-of-the-art performance.

Bojia Zi, Xianbiao Qi, Lingzhi Wang et al.

In this paper, we present Delta-LoRA, which is a novel parameter-efficient approach to fine-tune large language models (LLMs). In contrast to LoRA and other low-rank adaptation methods such as AdaLoRA, Delta-LoRA not only updates the low-rank matrices $\bA$ and $\bB$, but also propagate the learning to the pre-trained weights $\bW$ via updates utilizing the delta of the product of two low-rank matrices ($\bA^{(t+1)}\bB^{(t+1)} - \bA^{(t)}\bB^{(t)}$). Such a strategy effectively addresses the limitation that the incremental update of low-rank matrices is inadequate for learning representations capable for downstream tasks. Moreover, as the update of $\bW$ does not need to compute the gradients of $\bW$ and store their momentums, Delta-LoRA shares comparable memory requirements and computational costs with LoRA. Extensive experiments show that Delta-LoRA significantly outperforms existing low-rank adaptation methods. We further support these results with comprehensive analyses that underscore the effectiveness of Delta-LoRA.

Minghan Li, Lei Zhang

It is expensive and labour-extensive to label the pixel-wise object masks in a video. As a result, the amount of pixel-wise annotations in existing video instance segmentation (VIS) datasets is small, limiting the generalization capability of trained VIS models. An alternative but much cheaper solution is to use bounding boxes to label instances in videos. Inspired by the recent success of box-supervised image instance segmentation, we adapt the state-of-the-art pixel-supervised VIS models to a box-supervised VIS (BoxVIS) baseline, and observe slight performance degradation. We consequently propose to improve the BoxVIS performance from two aspects. First, we propose a box-center guided spatial-temporal pairwise affinity (STPA) loss to predict instance masks for better spatial and temporal consistency. Second, we collect a larger scale box-annotated VIS dataset (BVISD) by consolidating the videos from current VIS benchmarks and converting images from the COCO dataset to short pseudo video clips. With the proposed BVISD and the STPA loss, our trained BoxVIS model achieves 43.2\% and 29.0\% mask AP on the YouTube-VIS 2021 and OVIS valid sets, respectively. It exhibits comparable instance mask prediction performance and better generalization ability than state-of-the-art pixel-supervised VIS models by using only 16\% of their annotation time and cost. Codes and data can be found at \url{https://github.com/MinghanLi/BoxVIS}.

Qing Jiang, Feng Li, Tianhe Ren et al.

We introduce T-Rex, an interactive object counting model designed to first detect and then count any objects. We formulate object counting as an open-set object detection task with the integration of visual prompts. Users can specify the objects of interest by marking points or boxes on a reference image, and T-Rex then detects all objects with a similar pattern. Guided by the visual feedback from T-Rex, users can also interactively refine the counting results by prompting on missing or falsely-detected objects. T-Rex has achieved state-of-the-art performance on several class-agnostic counting benchmarks. To further exploit its potential, we established a new counting benchmark encompassing diverse scenarios and challenges. Both quantitative and qualitative results show that T-Rex possesses exceptional zero-shot counting capabilities. We also present various practical application scenarios for T-Rex, illustrating its potential in the realm of visual prompting.

Peggy Tang, Kun Hu, Rui Yan et al.

Extractive text summarisation aims to select salient sentences from a document to form a short yet informative summary. While learning-based methods have achieved promising results, they have several limitations, such as dependence on expensive training and lack of interpretability. Therefore, in this paper, we propose a novel non-learning-based method by for the first time formulating text summarisation as an Optimal Transport (OT) problem, namely Optimal Transport Extractive Summariser (OTExtSum). Optimal sentence extraction is conceptualised as obtaining an optimal summary that minimises the transportation cost to a given document regarding their semantic distributions. Such a cost is defined by the Wasserstein distance and used to measure the summary's semantic coverage of the original document. Comprehensive experiments on four challenging and widely used datasets - MultiNews, PubMed, BillSum, and CNN/DM demonstrate that our proposed method outperforms the state-of-the-art non-learning-based methods and several recent learning-based methods in terms of the ROUGE metric.

Yingjian Chen, Lei Zhang, Yakun Niu

The rise of generative models has raised concerns about image authenticity online, highlighting the urgent need for a detector that is (1) highly generalizable, capable of handling unseen forgery techniques, and (2) data-efficient, achieving optimal performance with minimal training data, enabling it to counter newly emerging forgery techniques effectively. To achieve this, we propose ForgeLens, a data-efficient, feature-guided framework that incorporates two lightweight designs to enable a frozen network to focus on forgery-specific features. First, we introduce the Weight-Shared Guidance Module (WSGM), which guides the extraction of forgery-specific features during training. Second, a forgery-aware feature integrator, FAFormer, is used to effectively integrate forgery information across multi-stage features. ForgeLens addresses a key limitation of previous frozen network-based methods, where general-purpose features extracted from large datasets often contain excessive forgery-irrelevant information. As a result, it achieves strong generalization and reaches optimal performance with minimal training data. Experimental results on 19 generative models, including both GANs and diffusion models, demonstrate improvements of 13.61% in Avg.Acc and 8.69% in Avg.AP over the base model. Notably, ForgeLens outperforms existing forgery detection methods, achieving state-of-the-art performance with just 1% of the training data. Our code is available at https://github.com/Yingjian-Chen/ForgeLens.

Qing Jiang, Feng Li, Zhaoyang Zeng et al.

We present T-Rex2, a highly practical model for open-set object detection. Previous open-set object detection methods relying on text prompts effectively encapsulate the abstract concept of common objects, but struggle with rare or complex object representation due to data scarcity and descriptive limitations. Conversely, visual prompts excel in depicting novel objects through concrete visual examples, but fall short in conveying the abstract concept of objects as effectively as text prompts. Recognizing the complementary strengths and weaknesses of both text and visual prompts, we introduce T-Rex2 that synergizes both prompts within a single model through contrastive learning. T-Rex2 accepts inputs in diverse formats, including text prompts, visual prompts, and the combination of both, so that it can handle different scenarios by switching between the two prompt modalities. Comprehensive experiments demonstrate that T-Rex2 exhibits remarkable zero-shot object detection capabilities across a wide spectrum of scenarios. We show that text prompts and visual prompts can benefit from each other within the synergy, which is essential to cover massive and complicated real-world scenarios and pave the way towards generic object detection. Model API is now available at \url{https://github.com/IDEA-Research/T-Rex}.

Lei Zhang, Diwen Zheng, Kaixin Bai et al.

Dexterous grasp generation aims to produce grasp poses that align with task requirements and human interpretable grasp semantics. However, achieving semantically controllable dexterous grasp synthesis remains highly challenging due to the lack of unified modeling of multiple semantic dimensions, including grasp taxonomy, contact semantics, and functional affordance. To address these limitations, we present OmniDexVLG, a multimodal, semantics aware grasp generation framework capable of producing structurally diverse and semantically coherent dexterous grasps under joint language and visual guidance. Our approach begins with OmniDexDataGen, a semantic rich dexterous grasp dataset generation pipeline that integrates grasp taxonomy guided configuration sampling, functional affordance contact point sampling, taxonomy aware differential force closure grasp sampling, and physics based optimization and validation, enabling systematic coverage of diverse grasp types. We further introduce OmniDexReasoner, a multimodal grasp type semantic reasoning module that leverages multi agent collaboration, retrieval augmented generation, and chain of thought reasoning to infer grasp related semantics and generate high quality annotations that align language instructions with task specific grasp intent. Building upon these components, we develop a unified Vision Language Grasping generation model that explicitly incorporates grasp taxonomy, contact structure, and functional affordance semantics, enabling fine grained control over grasp synthesis from natural language instructions. Extensive experiments in simulation and real world object grasping and ablation studies demonstrate that our method substantially outperforms state of the art approaches in terms of grasp diversity, contact semantic diversity, functional affordance diversity, and semantic consistency.

Luojun Lin, Zhifeng Shen, Zhishu Sun et al.

Agnostic domain shift is the main reason of model degradation on the unknown target domains, which brings an urgent need to develop Domain Generalization (DG). Recent advances at DG use dynamic networks to achieve training-free adaptation on the unknown target domains, termed Dynamic Domain Generalization (DDG), which compensates for the lack of self-adaptability in static models with fixed weights. The parameters of dynamic networks can be decoupled into a static and a dynamic component, which are designed to learn domain-invariant and domain-specific features, respectively. Based on the existing arts, in this work, we try to push the limits of DDG by disentangling the static and dynamic components more thoroughly from an optimization perspective. Our main consideration is that we can enable the static component to learn domain-invariant features more comprehensively by augmenting the domain-specific information. As a result, the more comprehensive domain-invariant features learned by the static component can then enforce the dynamic component to focus more on learning adaptive domain-specific features. To this end, we propose a simple yet effective Parameter Exchange (PE) method to perturb the combination between the static and dynamic components. We optimize the model using the gradients from both the perturbed and non-perturbed feed-forward jointly to implicitly achieve the aforementioned disentanglement. In this way, the two components can be optimized in a mutually-beneficial manner, which can resist the agnostic domain shifts and improve the self-adaptability on the unknown target domain. Extensive experiments show that PE can be easily plugged into existing dynamic networks to improve their generalization ability without bells and whistles.

Lei Zhang, Hao Chen, Shu Hu et al.

Generative adversarial networks (GANs) have remarkably advanced in diverse domains, especially image generation and editing. However, the misuse of GANs for generating deceptive images, such as face replacement, raises significant security concerns, which have gained widespread attention. Therefore, it is urgent to develop effective detection methods to distinguish between real and fake images. Current research centers around the application of transfer learning. Nevertheless, it encounters challenges such as knowledge forgetting from the original dataset and inadequate performance when dealing with imbalanced data during training. To alleviate this issue, this paper introduces a novel GAN-generated image detection algorithm called X-Transfer, which enhances transfer learning by utilizing two neural networks that employ interleaved parallel gradient transmission. In addition, we combine AUC loss and cross-entropy loss to improve the model's performance. We carry out comprehensive experiments on multiple facial image datasets. The results show that our model outperforms the general transferring approach, and the best metric achieves 99.04%, which is increased by approximately 10%. Furthermore, we demonstrate excellent performance on non-face datasets, validating its generality and broader application prospects.

Fuxiang Huang, Suqi Song, Lei Zhang

Unsupervised domain adaptation (UDA) intends to transfer knowledge from a labeled source domain to an unlabeled target domain. Many current methods focus on learning feature representations that are both discriminative for classification and invariant across domains by simultaneously optimizing domain alignment and classification tasks. However, these methods often overlook a crucial challenge: the inherent conflict between these two tasks during gradient-based optimization. In this paper, we delve into this issue and introduce two effective solutions known as Gradient Harmonization, including GH and GH++, to mitigate the conflict between domain alignment and classification tasks. GH operates by altering the gradient angle between different tasks from an obtuse angle to an acute angle, thus resolving the conflict and trade-offing the two tasks in a coordinated manner. Yet, this would cause both tasks to deviate from their original optimization directions. We thus further propose an improved version, GH++, which adjusts the gradient angle between tasks from an obtuse angle to a vertical angle. This not only eliminates the conflict but also minimizes deviation from the original gradient directions. Finally, for optimization convenience and efficiency, we evolve the gradient harmonization strategies into a dynamically weighted loss function using an integral operator on the harmonized gradient. Notably, GH/GH++ are orthogonal to UDA and can be seamlessly integrated into most existing UDA models. Theoretical insights and experimental analyses demonstrate that the proposed approaches not only enhance popular UDA baselines but also improve recent state-of-the-art models.

Nan Chen, Mengqi Huang, Zhuowei Chen et al.

Subject-driven text-to-image (T2I) customization has drawn significant interest in academia and industry. This task enables pre-trained models to generate novel images based on unique subjects. Existing studies adopt a self-reconstructive perspective, focusing on capturing all details of a single image, which will misconstrue the specific image's irrelevant attributes (e.g., view, pose, and background) as the subject intrinsic attributes. This misconstruction leads to both overfitting or underfitting of irrelevant and intrinsic attributes of the subject, i.e., these attributes are over-represented or under-represented simultaneously, causing a trade-off between similarity and controllability. In this study, we argue an ideal subject representation can be achieved by a cross-differential perspective, i.e., decoupling subject intrinsic attributes from irrelevant attributes via contrastive learning, which allows the model to focus more on intrinsic attributes through intra-consistency (features of the same subject are spatially closer) and inter-distinctiveness (features of different subjects have distinguished differences). Specifically, we propose CustomContrast, a novel framework, which includes a Multilevel Contrastive Learning (MCL) paradigm and a Multimodal Feature Injection (MFI) Encoder. The MCL paradigm is used to extract intrinsic features of subjects from high-level semantics to low-level appearance through crossmodal semantic contrastive learning and multiscale appearance contrastive learning. To facilitate contrastive learning, we introduce the MFI encoder to capture cross-modal representations. Extensive experiments show the effectiveness of CustomContrast in subject similarity and text controllability.

Fuxiang Huang, Lei Zhang

Interactive Image Retrieval (IIR) aims to retrieve images that are generally similar to the reference image but under the requested text modification. The existing methods usually concatenate or sum the features of image and text simply and roughly, which, however, is difficult to precisely change the local semantics of the image that the text intends to modify. To solve this problem, we propose a Language Guided Local Infiltration (LGLI) system, which fully utilizes the text information and penetrates text features into image features as much as possible. Specifically, we first propose a Language Prompt Visual Localization (LPVL) module to generate a localization mask which explicitly locates the region (semantics) intended to be modified. Then we introduce a Text Infiltration with Local Awareness (TILA) module, which is deployed in the network to precisely modify the reference image and generate image-text infiltrated representation. Extensive experiments on various benchmark databases validate that our method outperforms most state-of-the-art IIR approaches.

Lingchen Sun, Rongyuan Wu, Zhiyuan Ma et al.

Diffusion prior-based methods have shown impressive results in real-world image super-resolution (SR). However, most existing methods entangle pixel-level and semantic-level SR objectives in the training process, struggling to balance pixel-wise fidelity and perceptual quality. Meanwhile, users have varying preferences on SR results, thus it is demanded to develop an adjustable SR model that can be tailored to different fidelity-perception preferences during inference without re-training. We present Pixel-level and Semantic-level Adjustable SR (PiSA-SR), which learns two LoRA modules upon the pre-trained stable-diffusion (SD) model to achieve improved and adjustable SR results. We first formulate the SD-based SR problem as learning the residual between the low-quality input and the high-quality output, then show that the learning objective can be decoupled into two distinct LoRA weight spaces: one is characterized by the $\ell_2$-loss for pixel-level regression, and another is characterized by the LPIPS and classifier score distillation losses to extract semantic information from pre-trained classification and SD models. In its default setting, PiSA-SR can be performed in a single diffusion step, achieving leading real-world SR results in both quality and efficiency. By introducing two adjustable guidance scales on the two LoRA modules to control the strengths of pixel-wise fidelity and semantic-level details during inference, PiSASR can offer flexible SR results according to user preference without re-training. Codes and models can be found at https://github.com/csslc/PiSA-SR.

Xianbiao Qi, Jianan Wang, Lei Zhang

This article provides a comprehensive understanding of optimization in deep learning, with a primary focus on the challenges of gradient vanishing and gradient exploding, which normally lead to diminished model representational ability and training instability, respectively. We analyze these two challenges through several strategic measures, including the improvement of gradient flow and the imposition of constraints on a network's Lipschitz constant. To help understand the current optimization methodologies, we categorize them into two classes: explicit optimization and implicit optimization. Explicit optimization methods involve direct manipulation of optimizer parameters, including weight, gradient, learning rate, and weight decay. Implicit optimization methods, by contrast, focus on improving the overall landscape of a network by enhancing its modules, such as residual shortcuts, normalization methods, attention mechanisms, and activations. In this article, we provide an in-depth analysis of these two optimization classes and undertake a thorough examination of the Jacobian matrices and the Lipschitz constants of many widely used deep learning modules, highlighting existing issues as well as potential improvements. Moreover, we also conduct a series of analytical experiments to substantiate our theoretical discussions. This article does not aim to propose a new optimizer or network. Rather, our intention is to present a comprehensive understanding of optimization in deep learning. We hope that this article will assist readers in gaining a deeper insight in this field and encourages the development of more robust, efficient, and high-performing models.

Qing Jiang, Gen Luo, Yuqin Yang et al.

Perception and understanding are two pillars of computer vision. While multimodal large language models (MLLM) have demonstrated remarkable visual understanding capabilities, they arguably lack accurate perception abilities, e.g. the stage-of-the-art model Qwen2-VL only achieves a 43.9 recall rate on the COCO dataset, limiting many tasks requiring the combination of perception and understanding. In this work, we aim to bridge this perception gap from both model designing and data development perspectives. We first introduce ChatRex, an MLLM with a decoupled perception design. Instead of having the LLM directly predict box coordinates, we feed the output boxes from a universal proposal network into the LLM, allowing it to output the corresponding box indices to represent its detection results, turning the regression task into a retrieval-based task that LLM handles more proficiently. From the data perspective, we build a fully automated data engine and construct the Rexverse-2M dataset which possesses multiple granularities to support the joint training of perception and understanding. After a three-stage training approach, ChatRex demonstrates strong perception and understanding performance, and the combination of these two capabilities also unlocks many attractive applications, demonstrating their complementary roles in MLLM. Code is available at https://github.com/IDEA-Research/ChatRex.

Wenqiao Zhang, Tianwei Lin, Jiang Liu et al.

Recent advancements indicate that scaling up Multimodal Large Language Models (MLLMs) effectively enhances performance on downstream multimodal tasks. The prevailing MLLM paradigm, \emph{e.g.}, LLaVA, transforms visual features into text-like tokens using a \emph{static} vision-language mapper, thereby enabling \emph{static} LLMs to develop the capability to comprehend visual information through visual instruction tuning. Although promising, the \emph{static} tuning strategy~\footnote{The static tuning refers to the trained model with static parameters.} that shares the same parameters may constrain performance across different downstream multimodal tasks. In light of this, we introduce HyperLLaVA, which involves adaptive tuning of the projector and LLM parameters, in conjunction with a dynamic visual expert and language expert, respectively. These experts are derived from HyperNetworks, which generates adaptive parameter shifts through visual and language guidance, enabling dynamic projector and LLM modeling in two-stage training. Our experiments demonstrate that our solution significantly surpasses LLaVA on existing MLLM benchmarks, including MME, MMBench, SEED-Bench, and LLaVA-Bench. ~\footnote{Our project is available on the link https://github.com/DCDmllm/HyperLLaVA}.

Qing Jiang, Lin Wu, Zhaoyang Zeng et al.

Humans are undoubtedly the most important participants in computer vision, and the ability to detect any individual given a natural language description, a task we define as referring to any person, holds substantial practical value. However, we find that existing models generally fail to achieve real-world usability, and current benchmarks are limited by their focus on one-to-one referring, that hinder progress in this area. In this work, we revisit this task from three critical perspectives: task definition, dataset design, and model architecture. We first identify five aspects of referable entities and three distinctive characteristics of this task. Next, we introduce HumanRef, a novel dataset designed to tackle these challenges and better reflect real-world applications. From a model design perspective, we integrate a multimodal large language model with an object detection framework, constructing a robust referring model named RexSeek. Experimental results reveal that state-of-the-art models, which perform well on commonly used benchmarks like RefCOCO/+/g, struggle with HumanRef due to their inability to detect multiple individuals. In contrast, RexSeek not only excels in human referring but also generalizes effectively to common object referring, making it broadly applicable across various perception tasks. Code is available at https://github.com/IDEA-Research/RexSeek

Jiazhou Zhou, Qing Jiang, Kanghao Chen et al.

Object detection methods have evolved from closed-set to open-set paradigms over the years. Current open-set object detectors, however, remain constrained by their exclusive reliance on positive indicators based on given prompts like text descriptions or visual exemplars. This positive-only paradigm experiences consistent vulnerability to visually similar but semantically different distractors. We propose T-Rex-Omni, a novel framework that addresses this limitation by incorporating negative visual prompts to negate hard negative distractors. Specifically, we first introduce a unified visual prompt encoder that jointly processes positive and negative visual prompts. Next, a training-free Negating Negative Computing (NNC) module is proposed to dynamically suppress negative responses during the probability computing stage. To further boost performance through fine-tuning, our Negating Negative Hinge (NNH) loss enforces discriminative margins between positive and negative embeddings. T-Rex-Omni supports flexible deployment in both positive-only and joint positive-negative inference modes, accommodating either user-specified or automatically generated negative examples. Extensive experiments demonstrate remarkable zero-shot detection performance, significantly narrowing the performance gap between visual-prompted and text-prompted methods while showing particular strength in long-tailed scenarios (51.2 AP_r on LVIS-minival). This work establishes negative prompts as a crucial new dimension for advancing open-set visual recognition systems.

Fuxiang Huang, Xiaowei Fu, Shiyu Ye et al.

Unsupervised domain adaptation (UDA) aims to transfer knowledge from a label-rich source domain to an unlabeled target domain by addressing domain shifts. Most UDA approaches emphasize transfer ability, but often overlook robustness against adversarial attacks. Although vanilla adversarial training (VAT) improves the robustness of deep neural networks, it has little effect on UDA. This paper focuses on answering three key questions: 1) Why does VAT, known for its defensive effectiveness, fail in the UDA paradigm? 2) What is the generalization bound theory under attacks and how does it evolve from classical UDA theory? 3) How can we implement a robustification training procedure without complex modifications? Specifically, we explore and reveal the inherent entanglement challenge in general UDA+VAT paradigm, and propose an unsupervised robust domain adaptation (URDA) paradigm. We further derive the generalization bound theory of the URDA paradigm so that it can resist adversarial noise and domain shift. To the best of our knowledge, this is the first time to establish the URDA paradigm and theory. We further introduce a simple, novel yet effective URDA algorithm called Disentangled Adversarial Robustness Training (DART), a two-step training procedure that ensures both transferability and robustness. DART first pre-trains an arbitrary UDA model, and then applies an instantaneous robustification post-training step via disentangled distillation.Experiments on four benchmark datasets with/without attacks show that DART effectively enhances robustness while maintaining domain adaptability, and validate the URDA paradigm and theory.

Jianfeng Wang, Xi Yin, Lijuan Wang et al.

In this paper, we propose an algorithm, named hashing-based non-maximum suppression (HNMS) to efficiently suppress the non-maximum boxes for object detection. Non-maximum suppression (NMS) is an essential component to suppress the boxes at closely located locations with similar shapes. The time cost tends to be huge when the number of boxes becomes large, especially for crowded scenes. The basic idea of HNMS is to firstly map each box to a discrete code (hash cell) and then remove the boxes with lower confidences if they are in the same cell. Considering the intersection-over-union (IoU) as the metric, we propose a simple yet effective hashing algorithm, named IoUHash, which guarantees that the boxes within the same cell are close enough by a lower IoU bound. For two-stage detectors, we replace NMS in region proposal network with HNMS, and observe significant speed-up with comparable accuracy. For one-stage detectors, HNMS is used as a pre-filter to speed up the suppression with a large margin. Extensive experiments are conducted on CARPK, SKU-110K, CrowdHuman datasets to demonstrate the efficiency and effectiveness of HNMS. Code is released at \url{https://github.com/microsoft/hnms.git}.

Fuxiang Huang, Lei Zhang, Yang Yang et al.

Domain adaptive image retrieval includes single-domain retrieval and cross-domain retrieval. Most of the existing image retrieval methods only focus on single-domain retrieval, which assumes that the distributions of retrieval databases and queries are similar. However, in practical application, the discrepancies between retrieval databases often taken in ideal illumination/pose/background/camera conditions and queries usually obtained in uncontrolled conditions are very large. In this paper, considering the practical application, we focus on challenging cross-domain retrieval. To address the problem, we propose an effective method named Probability Weighted Compact Feature Learning (PWCF), which provides inter-domain correlation guidance to promote cross-domain retrieval accuracy and learns a series of compact binary codes to improve the retrieval speed. First, we derive our loss function through the Maximum A Posteriori Estimation (MAP): Bayesian Perspective (BP) induced focal-triplet loss, BP induced quantization loss and BP induced classification loss. Second, we propose a common manifold structure between domains to explore the potential correlation across domains. Considering the original feature representation is biased due to the inter-domain discrepancy, the manifold structure is difficult to be constructed. Therefore, we propose a new feature named Histogram Feature of Neighbors (HFON) from the sample statistics perspective. Extensive experiments on various benchmark databases validate that our method outperforms many state-of-the-art image retrieval methods for domain adaptive image retrieval. The source code is available at https://github.com/fuxianghuang1/PWCF

Hui Zeng, Lida Li, Zisheng Cao et al.

Image cropping aims to improve the composition as well as aesthetic quality of an image by removing extraneous content from it. Existing image cropping databases provide only one or several human-annotated bounding boxes as the groundtruth, which cannot reflect the non-uniqueness and flexibility of image cropping in practice. The employed evaluation metrics such as intersection-over-union cannot reliably reflect the real performance of cropping models, either. This work revisits the problem of image cropping, and presents a grid anchor based formulation by considering the special properties and requirements (e.g., local redundancy, content preservation, aspect ratio) of image cropping. Our formulation reduces the searching space of candidate crops from millions to less than one hundred. Consequently, a grid anchor based cropping benchmark is constructed, where all crops of each image are annotated and more reliable evaluation metrics are defined. We also design an effective and lightweight network module, which simultaneously considers the region of interest and region of discard for more accurate image cropping. Our model can stably output visually pleasing crops for images of different scenes and run at a speed of 125 FPS. Code and dataset are available at: https://github.com/HuiZeng/Grid-Anchor-based-Image-Cropping.

Lei Zhang, Shanshan Wang, Guang-Bin Huang et al.

In many practical transfer learning scenarios, the feature distribution is different across the source and target domains (i.e. non-i.i.d.). Maximum mean discrepancy (MMD), as a domain discrepancy metric, has achieved promising performance in unsupervised domain adaptation (DA). We argue that MMD-based DA methods ignore the data locality structure, which, to some extent, would cause the negative transfer effect. The locality plays an important role in minimizing the nonlinear local domain discrepancy underlying the marginal distributions. For better exploiting the domain locality, a novel local generative discrepancy metric (LGDM) based intermediate domain generation learning called Manifold Criterion guided Transfer Learning (MCTL) is proposed in this paper. The merits of the proposed MCTL are four-fold: 1) the concept of manifold criterion (MC) is first proposed as a measure validating the distribution matching across domains, and domain adaptation is achieved if the MC is satisfied; 2) the proposed MC can well guide the generation of the intermediate domain sharing similar distribution with the target domain, by minimizing the local domain discrepancy; 3) a global generative discrepancy metric (GGDM) is presented, such that both the global and local discrepancy can be effectively and positively reduced; 4) a simplified version of MCTL called MCTL-S is presented under a perfect domain generation assumption for more generic learning scenario. Experiments on a number of benchmark visual transfer tasks demonstrate the superiority of the proposed manifold criterion guided generative transfer method, by comparing with other state-of-the-art methods. The source code is available in https://github.com/wangshanshanCQU/MCTL.

Ji Liu, Lei Zhang

Recently, learning to hash has been widely studied for image retrieval thanks to the computation and storage efficiency of binary codes. For most existing learning to hash methods, sufficient training images are required and used to learn precise hashing codes. However, in some real-world applications, there are not always sufficient training images in the domain of interest. In addition, some existing supervised approaches need a amount of labeled data, which is an expensive process in term of time, label and human expertise. To handle such problems, inspired by transfer learning, we propose a simple yet effective unsupervised hashing method named Optimal Projection Guided Transfer Hashing (GTH) where we borrow the images of other different but related domain i.e., source domain to help learn precise hashing codes for the domain of interest i.e., target domain. Besides, we propose to seek for the maximum likelihood estimation (MLE) solution of the hashing functions of target and source domains due to the domain gap. Furthermore,an alternating optimization method is adopted to obtain the two projections of target and source domains such that the domain hashing disparity is reduced gradually. Extensive experiments on various benchmark databases verify that our method outperforms many state-of-the-art learning to hash methods. The implementation details are available at https://github.com/liuji93/GTH.

Lei Zhang, David Zhang

Image/video data is usually represented with multiple visual features. Fusion of multi-source information for establishing the attributes has been widely recognized. Multi-feature visual recognition has recently received much attention in multimedia applications. This paper studies visual understanding via a newly proposed l_2-norm based multi-feature shared learning framework, which can simultaneously learn a global label matrix and multiple sub-classifiers with the labeled multi-feature data. Additionally, a group graph manifold regularizer composed of the Laplacian and Hessian graph is proposed for better preserving the manifold structure of each feature, such that the label prediction power is much improved through the semi-supervised learning with global label consistency. For convenience, we call the proposed approach Global-Label-Consistent Classifier (GLCC). The merits of the proposed method include: 1) the manifold structure information of each feature is exploited in learning, resulting in a more faithful classification owing to the global label consistency; 2) a group graph manifold regularizer based on the Laplacian and Hessian regularization is constructed; 3) an efficient alternative optimization method is introduced as a fast solver owing to the convex sub-problems. Experiments on several benchmark visual datasets for multimedia understanding, such as the 17-category Oxford Flower dataset, the challenging 101-category Caltech dataset, the YouTube & Consumer Videos dataset and the large-scale NUS-WIDE dataset, demonstrate that the proposed approach compares favorably with the state-of-the-art algorithms. An extensive experiment on the deep convolutional activation features also show the effectiveness of the proposed approach. The code is available on http://www.escience.cn/people/lei/index.html

Tianhe Ren, Yihao Chen, Qing Jiang et al.

In this paper, we introduce DINO-X, which is a unified object-centric vision model developed by IDEA Research with the best open-world object detection performance to date. DINO-X employs the same Transformer-based encoder-decoder architecture as Grounding DINO 1.5 to pursue an object-level representation for open-world object understanding. To make long-tailed object detection easy, DINO-X extends its input options to support text prompt, visual prompt, and customized prompt. With such flexible prompt options, we develop a universal object prompt to support prompt-free open-world detection, making it possible to detect anything in an image without requiring users to provide any prompt. To enhance the model's core grounding capability, we have constructed a large-scale dataset with over 100 million high-quality grounding samples, referred to as Grounding-100M, for advancing the model's open-vocabulary detection performance. Pre-training on such a large-scale grounding dataset leads to a foundational object-level representation, which enables DINO-X to integrate multiple perception heads to simultaneously support multiple object perception and understanding tasks, including detection, segmentation, pose estimation, object captioning, object-based QA, etc. Experimental results demonstrate the superior performance of DINO-X. Specifically, the DINO-X Pro model achieves 56.0 AP, 59.8 AP, and 52.4 AP on the COCO, LVIS-minival, and LVIS-val zero-shot object detection benchmarks, respectively. Notably, it scores 63.3 AP and 56.5 AP on the rare classes of LVIS-minival and LVIS-val benchmarks, improving the previous SOTA performance by 5.8 AP and 5.0 AP. Such a result underscores its significantly improved capacity for recognizing long-tailed objects.

Yunshui Li, Binyuan Hui, Xiaobo Xia et al. · tsinghua

Contemporary practices in instruction tuning often hinge on enlarging data scaling without a clear strategy for ensuring data quality, inadvertently introducing noise that may compromise model performance. To address this challenge, we introduce \textsc{Nuggets}, a novel and efficient methodology that leverages one-shot learning to discern and select high-quality instruction data from extensive datasets. \textsc{Nuggets} assesses the potential of individual instruction examples to act as effective one-shot learning instances, thereby identifying those that can significantly improve performance across diverse tasks. \textsc{Nuggets} utilizes a scoring system based on the impact of candidate examples on the perplexity of a diverse anchor set, facilitating the selection of the most advantageous data for instruction tuning. Through comprehensive evaluations on two benchmarks, including MT-Bench and Alpaca-Eval, we show that instruction tuning with the top 1\% of examples curated by \textsc{Nuggets} substantially outperforms conventional methods employing the entire dataset.

Mingfu Liang, Xi Liu, Rong Jin et al.

Ads recommendation is a prominent service of online advertising systems and has been actively studied. Recent studies indicate that scaling-up and advanced design of the recommendation model can bring significant performance improvement. However, with a larger model scale, such prior studies have a significantly increasing gap from industry as they often neglect two fundamental challenges in industrial-scale applications. First, training and inference budgets are restricted for the model to be served, exceeding which may incur latency and impair user experience. Second, large-volume data arrive in a streaming mode with data distributions dynamically shifting, as new users/ads join and existing users/ads leave the system. We propose the External Large Foundation Model (ExFM) framework to address the overlooked challenges. Specifically, we develop external distillation and a data augmentation system (DAS) to control the computational cost of training/inference while maintaining high performance. We design the teacher in a way like a foundation model (FM) that can serve multiple students as vertical models (VMs) to amortize its building cost. We propose Auxiliary Head and Student Adapter to mitigate the data distribution gap between FM and VMs caused by the streaming data issue. Comprehensive experiments on internal industrial-scale applications and public datasets demonstrate significant performance gain by ExFM.

Lei Zhang, Yuhang Zhou, Yi Yang et al.

Despite providing high-performance solutions for computer vision tasks, the deep neural network (DNN) model has been proved to be extremely vulnerable to adversarial attacks. Current defense mainly focuses on the known attacks, but the adversarial robustness to the unknown attacks is seriously overlooked. Besides, commonly used adaptive learning and fine-tuning technique is unsuitable for adversarial defense since it is essentially a zero-shot problem when deployed. Thus, to tackle this challenge, we propose an attack-agnostic defense method named Meta Invariance Defense (MID). Specifically, various combinations of adversarial attacks are randomly sampled from a manually constructed Attacker Pool to constitute different defense tasks against unknown attacks, in which a student encoder is supervised by multi-consistency distillation to learn the attack-invariant features via a meta principle. The proposed MID has two merits: 1) Full distillation from pixel-, feature- and prediction-level between benign and adversarial samples facilitates the discovery of attack-invariance. 2) The model simultaneously achieves robustness to the imperceptible adversarial perturbations in high-level image classification and attack-suppression in low-level robust image regeneration. Theoretical and empirical studies on numerous benchmarks such as ImageNet verify the generalizable robustness and superiority of MID under various attacks.

Qing Jiang, Xingyu Chen, Zhaoyang Zeng et al.

Object referring aims to detect all objects in an image that match a given natural language description. We argue that a robust object referring model should be grounded, meaning its predictions should be both explainable and faithful to the visual content. Specifically, it should satisfy two key properties: 1) Verifiable, by producing interpretable reasoning that justifies its predictions and clearly links them to visual evidence; and 2) Trustworthy, by learning to abstain when no object in the image satisfies the given expression. However, most methods treat referring as a direct bounding box prediction task, offering limited interpretability and struggling to reject expressions with no matching object. In this work, we propose Rex-Thinker, a model that formulates object referring as an explicit CoT reasoning task. Given a referring expression, we first identify all candidate object instances corresponding to the referred object category. Rex-Thinker then performs step-by-step reasoning over each candidate to assess whether it matches the given expression, before making a final prediction. To support this paradigm, we construct a large-scale CoT-style referring dataset named HumanRef-CoT by prompting GPT-4o on the HumanRef dataset. Each reasoning trace follows a structured planning, action, and summarization format, enabling the model to learn decomposed, interpretable reasoning over object candidates. We then train Rex-Thinker in two stages: a cold-start supervised fine-tuning phase to teach the model how to perform structured reasoning, followed by GRPO-based RL learning to improve accuracy and generalization. Experiments show that our approach outperforms standard baselines in both precision and interpretability on in-domain evaluation, while also demonstrating improved ability to reject hallucinated outputs and strong generalization in out-of-domain settings.

Lei Zhang, Xiaowei Fu, Fuxiang Huang et al.

Person re-identification (ReID) has made great strides thanks to the data-driven deep learning techniques. However, the existing benchmark datasets lack diversity, and models trained on these data cannot generalize well to dynamic wild scenarios. To meet the goal of improving the explicit generalization of ReID models, we develop a new Open-World, Diverse, Cross-Spatial-Temporal dataset named OWD with several distinct features. 1) Diverse collection scenes: multiple independent open-world and highly dynamic collecting scenes, including streets, intersections, shopping malls, etc. 2) Diverse lighting variations: long time spans from daytime to nighttime with abundant illumination changes. 3) Diverse person status: multiple camera networks in all seasons with normal/adverse weather conditions and diverse pedestrian appearances (e.g., clothes, personal belongings, poses, etc.). 4) Protected privacy: invisible faces for privacy critical applications. To improve the implicit generalization of ReID, we further propose a Latent Domain Expansion (LDE) method to develop the potential of source data, which decouples discriminative identity-relevant and trustworthy domain-relevant features and implicitly enforces domain-randomized identity feature space expansion with richer domain diversity to facilitate domain invariant representations. Our comprehensive evaluations with most benchmark datasets in the community are crucial for progress, although this work is far from the grand goal toward open-world and dynamic wild applications.

Junhao Liu, Siwei Xu, Lei Zhang et al.

Over the past decade, the revolution in single-cell sequencing has enabled the simultaneous molecular profiling of various modalities across thousands of individual cells, allowing scientists to investigate the diverse functions of complex tissues and uncover underlying disease mechanisms. Among all the analytical steps, assigning individual cells to specific types is fundamental for understanding cellular heterogeneity. However, this process is usually labor-intensive and requires extensive expert knowledge. Recent advances in large language models (LLMs) have demonstrated their ability to efficiently process and synthesize vast corpora of text to automatically extract essential biological knowledge, such as marker genes, potentially promoting more efficient and automated cell type annotations. To thoroughly evaluate the capability of modern instruction-tuned LLMs in automating the cell type identification process, we introduce SOAR, a comprehensive benchmarking study of LLMs for cell type annotation tasks in single-cell genomics. Specifically, we assess the performance of 8 instruction-tuned LLMs across 11 datasets, spanning multiple cell types and species. Our study explores the potential of LLMs to accurately classify and annotate cell types in single-cell RNA sequencing (scRNA-seq) data, while extending their application to multiomics data through cross-modality translation. Additionally, we evaluate the effectiveness of chain-of-thought (CoT) prompting techniques in generating detailed biological insights during the annotation process. The results demonstrate that LLMs can provide robust interpretations of single-cell data without requiring additional fine-tuning, advancing the automation of cell type annotation in genomics research.

Hao Li, Mengqi Huang, Lei Zhang et al.

GAN-based image attribute editing firstly leverages GAN Inversion to project real images into the latent space of GAN and then manipulates corresponding latent codes. Recent inversion methods mainly utilize additional high-bit features to improve image details preservation, as low-bit codes cannot faithfully reconstruct source images, leading to the loss of details. However, during editing, existing works fail to accurately complement the lost details and suffer from poor editability. The main reason is they inject all the lost details indiscriminately at one time, which inherently induces the position and quantity of details to overfit source images, resulting in inconsistent content and artifacts in edited images. This work argues that details should be gradually injected into both the reconstruction and editing process in a multi-stage coarse-to-fine manner for better detail preservation and high editability. Therefore, a novel dual-stream framework is proposed to accurately complement details at each stage. The Reconstruction Stream is employed to embed coarse-to-fine lost details into residual features and then adaptively add them to the GAN generator. In the Editing Stream, residual features are accurately aligned by our Selective Attention mechanism and then injected into the editing process in a multi-stage manner. Extensive experiments have shown the superiority of our framework in both reconstruction accuracy and editing quality compared with existing methods.

Chenxu Zhang, Fuxiang Huang, Lei Zhang

With climate change intensifying, urban waterlogging poses an increasingly severe threat to global public safety and infrastructure. However, existing monitoring approaches rely heavily on manual reporting and fail to provide timely and comprehensive assessments. In this study, we present Urban Waterlogging Assessment (UWAssess), a foundation model-driven framework that automatically identifies waterlogged areas in surveillance images and generates structured assessment reports. To address the scarcity of labeled data, we design a semi-supervised fine-tuning strategy and a chain-of-thought (CoT) prompting strategy to unleash the potential of the foundation model for data-scarce downstream tasks. Evaluations on challenging visual benchmarks demonstrate substantial improvements in perception performance. GPT-based evaluations confirm the ability of UWAssess to generate reliable textual reports that accurately describe waterlogging extent, depth, risk and impact. This dual capability enables a shift of waterlogging monitoring from perception to generation, while the collaborative framework of multiple foundation models lays the groundwork for intelligent and scalable systems, supporting urban management, disaster response and climate resilience.

Qing Jiang, Junan Huo, Xingyu Chen et al.

Object detection has long been dominated by traditional coordinate regression-based models, such as YOLO, DETR, and Grounding DINO. Although recent efforts have attempted to leverage MLLMs to tackle this task, they face challenges like low recall rate, duplicate predictions, coordinate misalignment, etc. In this work, we bridge this gap and propose Rex-Omni, a 3B-scale MLLM that achieves state-of-the-art object perception performance. On benchmarks like COCO and LVIS, Rex-Omni attains performance comparable to or exceeding regression-based models (e.g., DINO, Grounding DINO) in a zero-shot setting. This is enabled by three key designs: 1) Task Formulation: we use special tokens to represent quantized coordinates from 0 to 999, reducing the model's learning difficulty and improving token efficiency for coordinate prediction; 2) Data Engines: we construct multiple data engines to generate high-quality grounding, referring, and pointing data, providing semantically rich supervision for training; \3) Training Pipelines: we employ a two-stage training process, combining supervised fine-tuning on 22 million data with GRPO-based reinforcement post-training. This RL post-training leverages geometry-aware rewards to effectively bridge the discrete-to-continuous coordinate prediction gap, improve box accuracy, and mitigate undesirable behaviors like duplicate predictions that stem from the teacher-guided nature of the initial SFT stage. Beyond conventional detection, Rex-Omni's inherent language understanding enables versatile capabilities such as object referring, pointing, visual prompting, GUI grounding, spatial referring, OCR and key-pointing, all systematically evaluated on dedicated benchmarks. We believe that Rex-Omni paves the way for more versatile and language-aware visual perception systems.

Lina Ma, Xiaowei Fu, Fuxiang Huang et al.

Existing defense methods fail to defend against unknown attacks and thus raise generalization issue of adversarial robustness. To remedy this problem, we attempt to delve into some underlying common characteristics among various attacks for generality. In this work, we reveal the commonly overlooked low entropy prior (LE) implied in various adversarial samples, and shed light on the universal robustness against unseen attacks in inference phase. LE prior is elaborated as two properties across various attacks as shown in Fig. 1 and Fig. 2: 1) low entropy misclassification for adversarial samples and 2) lower entropy prediction for higher attack intensity. This phenomenon stands in stark contrast to the naturally distributed samples. The LE prior can instruct existing test-time defense methods, thus we propose a two-stage REAL approach: Rectify Adversarial sample based on LE prior for test-time adversarial rectification. Specifically, to align adversarial samples more closely with clean samples, we propose to first rectify adversarial samples misclassified with low entropy by reverse maximizing prediction entropy, thereby eliminating their adversarial nature. To ensure the rectified samples can be correctly classified with low entropy, we carry out secondary rectification by forward minimizing prediction entropy, thus creating a Max-Min entropy optimization scheme. Further, based on the second property, we propose an attack-aware weighting mechanism to adaptively adjust the strengths of Max-Min entropy objectives. Experiments on several datasets show that REAL can greatly improve the performance of existing sample rectification models.

Jie Zhang, Lei Zhang, Gang Li et al.

Adversarial examples are inputs for machine learning models that have been designed by attackers to cause the model to make mistakes. In this paper, we demonstrate that adversarial examples can also be utilized for good to improve the performance of imbalanced learning. We provide a new perspective on how to deal with imbalanced data: adjust the biased decision boundary by training with Guiding Adversarial Examples (GAEs). Our method can effectively increase the accuracy of minority classes while sacrificing little accuracy on majority classes. We empirically show, on several benchmark datasets, our proposed method is comparable to the state-of-the-art method. To our best knowledge, we are the first to deal with imbalanced learning with adversarial examples.

Keyang Wang, Lei Zhang

Classification and regression are two pillars of object detectors. In most CNN-based detectors, these two pillars are optimized independently. Without direct interactions between them, the classification loss and the regression loss can not be optimized synchronously toward the optimal direction in the training phase. This clearly leads to lots of inconsistent predictions with high classification score but low localization accuracy or low classification score but high localization accuracy in the inference phase, especially for the objects of irregular shape and occlusion, which severely hurts the detection performance of existing detectors after NMS. To reconcile prediction consistency for balanced object detection, we propose a Harmonic loss to harmonize the optimization of classification branch and localization branch. The Harmonic loss enables these two branches to supervise and promote each other during training, thereby producing consistent predictions with high co-occurrence of top classification and localization in the inference phase. Furthermore, in order to prevent the localization loss from being dominated by outliers during training phase, a Harmonic IoU loss is proposed to harmonize the weight of the localization loss of different IoU-level samples. Comprehensive experiments on benchmarks PASCAL VOC and MS COCO demonstrate the generality and effectiveness of our model for facilitating existing object detectors to state-of-the-art accuracy.

Liyuan Zhang, Yuhang Zhou, Lei Zhang

State-of-the-art deep neural networks (DNNs) have been proved to have excellent performance on unsupervised domain adaption (UDA). However, recent work shows that DNNs perform poorly when being attacked by adversarial samples, where these attacks are implemented by simply adding small disturbances to the original images. Although plenty of work has focused on this, as far as we know, there is no systematic research on the robustness of unsupervised domain adaption model. Hence, we discuss the robustness of unsupervised domain adaption against adversarial attacking for the first time. We benchmark various settings of adversarial attack and defense in domain adaption, and propose a cross domain attack method based on pseudo label. Most importantly, we analyze the impact of different datasets, models, attack methods and defense methods. Directly, our work proves the limited robustness of unsupervised domain adaptation model, and we hope our work may facilitate the community to pay more attention to improve the robustness of the model against attacking.

Yabin Zhang, Haojian Zhang, Bin Deng et al.

Unsupervised domain adaptation (UDA) and semi-supervised learning (SSL) are two typical strategies to reduce expensive manual annotations in machine learning. In order to learn effective models for a target task, UDA utilizes the available labeled source data, which may have different distributions from unlabeled samples in the target domain, while SSL employs few manually annotated target samples. Although UDA and SSL are seemingly very different strategies, we find that they are closely related in terms of task objectives and solutions, and SSL is a special case of UDA problems. Based on this finding, we further investigate whether SSL methods work on UDA tasks. By adapting eight representative SSL algorithms on UDA benchmarks, we show that SSL methods are strong UDA learners. Especially, state-of-the-art SSL methods significantly outperform existing UDA methods on the challenging UDA benchmark of DomainNet, and state-of-the-art UDA methods could be further enhanced with SSL techniques. We thus promote that SSL methods should be employed as baselines in future UDA studies and expect that the revealed relationship between UDA and SSL could shed light on future UDA development. Codes are available at \url{https://github.com/YBZh}.

Shilong Liu, Lei Zhang, Xiao Yang et al.

We study the problem of unsupervised discovery and segmentation of object parts, which, as an intermediate local representation, are capable of finding intrinsic object structure and providing more explainable recognition results. Recent unsupervised methods have greatly relaxed the dependency on annotated data which are costly to obtain, but still rely on additional information such as object segmentation mask or saliency map. To remove such a dependency and further improve the part segmentation performance, we develop a novel approach by disentangling the appearance and shape representations of object parts followed with reconstruction losses without using additional object mask information. To avoid degenerated solutions, a bottleneck block is designed to squeeze and expand the appearance representation, leading to a more effective disentanglement between geometry and appearance. Combined with a self-supervised part classification loss and an improved geometry concentration constraint, we can segment more consistent parts with semantic meanings. Comprehensive experiments on a wide variety of objects such as face, bird, and PASCAL VOC objects demonstrate the effectiveness of the proposed method.

Luowei Zhou, Jingjing Liu, Yu Cheng et al.

This work concerns video-language pre-training and representation learning. In this now ubiquitous training scheme, a model first performs pre-training on paired videos and text (e.g., video clips and accompanied subtitles) from a large uncurated source corpus, before transferring to specific downstream tasks. This two-stage training process inevitably raises questions about the generalization ability of the pre-trained model, which is particularly pronounced when a salient domain gap exists between source and target data (e.g., instructional cooking videos vs. movies). In this paper, we first bring to light the sensitivity of pre-training objectives (contrastive vs. reconstructive) to domain discrepancy. Then, we propose a simple yet effective framework, CUPID, to bridge this domain gap by filtering and adapting source data to the target data, followed by domain-focused pre-training. Comprehensive experiments demonstrate that pre-training on a considerably small subset of domain-focused data can effectively close the source-target domain gap and achieve significant performance gain, compared to random sampling or even exploiting the full pre-training dataset. CUPID yields new state-of-the-art performance across multiple video-language and video tasks, including text-to-video retrieval [72, 37], video question answering [36], and video captioning [72], with consistent performance lift over different pre-training methods.

Peng Wang, Kai Han, Xiu-Shen Wei et al.

Learning discriminative image representations plays a vital role in long-tailed image classification because it can ease the classifier learning in imbalanced cases. Given the promising performance contrastive learning has shown recently in representation learning, in this work, we explore effective supervised contrastive learning strategies and tailor them to learn better image representations from imbalanced data in order to boost the classification accuracy thereon. Specifically, we propose a novel hybrid network structure being composed of a supervised contrastive loss to learn image representations and a cross-entropy loss to learn classifiers, where the learning is progressively transited from feature learning to the classifier learning to embody the idea that better features make better classifiers. We explore two variants of contrastive loss for feature learning, which vary in the forms but share a common idea of pulling the samples from the same class together in the normalized embedding space and pushing the samples from different classes apart. One of them is the recently proposed supervised contrastive (SC) loss, which is designed on top of the state-of-the-art unsupervised contrastive loss by incorporating positive samples from the same class. The other is a prototypical supervised contrastive (PSC) learning strategy which addresses the intensive memory consumption in standard SC loss and thus shows more promise under limited memory budget. Extensive experiments on three long-tailed classification datasets demonstrate the advantage of the proposed contrastive learning based hybrid networks in long-tailed classification.

Dengpan Fu, Dongdong Chen, Jianmin Bao et al.

In this paper, we present a large scale unlabeled person re-identification (Re-ID) dataset "LUPerson" and make the first attempt of performing unsupervised pre-training for improving the generalization ability of the learned person Re-ID feature representation. This is to address the problem that all existing person Re-ID datasets are all of limited scale due to the costly effort required for data annotation. Previous research tries to leverage models pre-trained on ImageNet to mitigate the shortage of person Re-ID data but suffers from the large domain gap between ImageNet and person Re-ID data. LUPerson is an unlabeled dataset of 4M images of over 200K identities, which is 30X larger than the largest existing Re-ID dataset. It also covers a much diverse range of capturing environments (eg, camera settings, scenes, etc.). Based on this dataset, we systematically study the key factors for learning Re-ID features from two perspectives: data augmentation and contrastive loss. Unsupervised pre-training performed on this large-scale dataset effectively leads to a generic Re-ID feature that can benefit all existing person Re-ID methods. Using our pre-trained model in some basic frameworks, our methods achieve state-of-the-art results without bells and whistles on four widely used Re-ID datasets: CUHK03, Market1501, DukeMTMC, and MSMT17. Our results also show that the performance improvement is more significant on small-scale target datasets or under few-shot setting.

Lei Zhang, Zhenwei He, Yi Yang et al.

The traditional object retrieval task aims to learn a discriminative feature representation with intra-similarity and inter-dissimilarity, which supposes that the objects in an image are manually or automatically pre-cropped exactly. However, in many real-world searching scenarios (e.g., video surveillance), the objects (e.g., persons, vehicles, etc.) are seldom accurately detected or annotated. Therefore, object-level retrieval becomes intractable without bounding-box annotation, which leads to a new but challenging topic, i.e. image-level search. In this paper, to address the image search issue, we first introduce an end-to-end Integrated Net (I-Net), which has three merits: 1) A Siamese architecture and an on-line pairing strategy for similar and dissimilar objects in the given images are designed. 2) A novel on-line pairing (OLP) loss is introduced with a dynamic feature dictionary, which alleviates the multi-task training stagnation problem, by automatically generating a number of negative pairs to restrict the positives. 3) A hard example priority (HEP) based softmax loss is proposed to improve the robustness of classification task by selecting hard categories. With the philosophy of divide and conquer, we further propose an improved I-Net, called DC-I-Net, which makes two new contributions: 1) two modules are tailored to handle different tasks separately in the integrated framework, such that the task specification is guaranteed. 2) A class-center guided HEP loss (C2HEP) by exploiting the stored class centers is proposed, such that the intra-similarity and inter-dissimilarity can be captured for ultimate retrieval. Extensive experiments on famous image-level search oriented benchmark datasets demonstrate that the proposed DC-I-Net outperforms the state-of-the-art tasks-integrated and tasks-separated image search models.

Yingguo Xu, Lei Zhang, Qingyan Duan

Heterogeneous face recognition is a challenging task due to the large modality discrepancy and insufficient cross-modal samples. Most existing works focus on discriminative feature transformation, metric learning and cross-modal face synthesis. However, the fact that cross-modal faces are always coupled by domain (modality) and identity information has received little attention. Therefore, how to learn and utilize the domain-private feature and domain-agnostic feature for modality adaptive face recognition is the focus of this work. Specifically, this paper proposes a Feature Aggregation Network (FAN), which includes disentangled representation module (DRM), feature fusion module (FFM) and adaptive penalty metric (APM) learning session. First, in DRM, two subnetworks, i.e. domain-private network and domain-agnostic network are specially designed for learning modality features and identity features, respectively. Second, in FFM, the identity features are fused with domain features to achieve cross-modal bi-directional identity feature transformation, which, to a large extent, further disentangles the modality information and identity information. Third, considering that the distribution imbalance between easy and hard pairs exists in cross-modal datasets, which increases the risk of model bias, the identity preserving guided metric learning with adaptive hard pairs penalization is proposed in our FAN. The proposed APM also guarantees the cross-modality intra-class compactness and inter-class separation. Extensive experiments on benchmark cross-modal face datasets show that our FAN outperforms SOTA methods.

Xiaoqi Zhao, Youwei Pang, Lihe Zhang et al.

Most salient object detection approaches use U-Net or feature pyramid networks (FPN) as their basic structures. These methods ignore two key problems when the encoder exchanges information with the decoder: one is the lack of interference control between them, the other is without considering the disparity of the contributions of different encoder blocks. In this work, we propose a simple gated network (GateNet) to solve both issues at once. With the help of multilevel gate units, the valuable context information from the encoder can be optimally transmitted to the decoder. We design a novel gated dual branch structure to build the cooperation among different levels of features and improve the discriminability of the whole network. Through the dual branch design, more details of the saliency map can be further restored. In addition, we adopt the atrous spatial pyramid pooling based on the proposed "Fold" operation (Fold-ASPP) to accurately localize salient objects of various scales. Extensive experiments on five challenging datasets demonstrate that the proposed model performs favorably against most state-of-the-art methods under different evaluation metrics.

Xiaoqi Zhao, Lihe Zhang, Youwei Pang et al.

Existing RGB-D salient object detection (SOD) approaches concentrate on the cross-modal fusion between the RGB stream and the depth stream. They do not deeply explore the effect of the depth map itself. In this work, we design a single stream network to directly use the depth map to guide early fusion and middle fusion between RGB and depth, which saves the feature encoder of the depth stream and achieves a lightweight and real-time model. We tactfully utilize depth information from two perspectives: (1) Overcoming the incompatibility problem caused by the great difference between modalities, we build a single stream encoder to achieve the early fusion, which can take full advantage of ImageNet pre-trained backbone model to extract rich and discriminative features. (2) We design a novel depth-enhanced dual attention module (DEDA) to efficiently provide the fore-/back-ground branches with the spatially filtered features, which enables the decoder to optimally perform the middle fusion. Besides, we put forward a pyramidally attended feature extraction module (PAFE) to accurately localize the objects of different scales. Extensive experiments demonstrate that the proposed model performs favorably against most state-of-the-art methods under different evaluation metrics. Furthermore, this model is 55.5\% lighter than the current lightest model and runs at a real-time speed of 32 FPS when processing a $384 \times 384$ image.

Zhenwei He, Lei Zhang

Conventional object detection models inevitably encounter a performance drop as the domain disparity exists. Unsupervised domain adaptive object detection is proposed recently to reduce the disparity between domains, where the source domain is label-rich while the target domain is label-agnostic. The existing models follow a parameter shared siamese structure for adversarial domain alignment, which, however, easily leads to the collapse and out-of-control risk of the source domain and brings negative impact to feature adaption. The main reason is that the labeling unfairness (asymmetry) between source and target makes the parameter sharing mechanism unable to adapt. Therefore, in order to avoid the source domain collapse risk caused by parameter sharing, we propose an asymmetric tri-way Faster-RCNN (ATF) for domain adaptive object detection. Our ATF model has two distinct merits: 1) A ancillary net supervised by source label is deployed to learn ancillary target features and simultaneously preserve the discrimination of source domain, which enhances the structural discrimination (object classification vs. bounding box regression) of domain alignment. 2) The asymmetric structure consisting of a chief net and an independent ancillary net essentially overcomes the parameter sharing aroused source risk collapse. The adaption safety of the proposed ATF detector is guaranteed. Extensive experiments on a number of datasets, including Cityscapes, Foggy-cityscapes, KITTI, Sim10k, Pascal VOC, Clipart and Watercolor, demonstrate the SOTA performance of our method.