Yang Li

Youwei Liang, Junfeng He, Gang Li et al.

Recent Text-to-Image (T2I) generation models such as Stable Diffusion and Imagen have made significant progress in generating high-resolution images based on text descriptions. However, many generated images still suffer from issues such as artifacts/implausibility, misalignment with text descriptions, and low aesthetic quality. Inspired by the success of Reinforcement Learning with Human Feedback (RLHF) for large language models, prior works collected human-provided scores as feedback on generated images and trained a reward model to improve the T2I generation. In this paper, we enrich the feedback signal by (i) marking image regions that are implausible or misaligned with the text, and (ii) annotating which words in the text prompt are misrepresented or missing on the image. We collect such rich human feedback on 18K generated images (RichHF-18K) and train a multimodal transformer to predict the rich feedback automatically. We show that the predicted rich human feedback can be leveraged to improve image generation, for example, by selecting high-quality training data to finetune and improve the generative models, or by creating masks with predicted heatmaps to inpaint the problematic regions. Notably, the improvements generalize to models (Muse) beyond those used to generate the images on which human feedback data were collected (Stable Diffusion variants). The RichHF-18K data set will be released in our GitHub repository: https://github.com/google-research/google-research/tree/master/richhf_18k.

Yifang Xu, Benxiang Zhai, Yunzhuo Sun et al.

Recent advancements in diffusion-based technologies have made significant strides, particularly in identity-preserved portrait generation (IPG). However, when using multiple reference images from the same ID, existing methods typically produce lower-fidelity portraits and struggle to customize face attributes precisely. To address these issues, this paper presents HiFi-Portrait, a high-fidelity method for zero-shot portrait generation. Specifically, we first introduce the face refiner and landmark generator to obtain fine-grained multi-face features and 3D-aware face landmarks. The landmarks include the reference ID and the target attributes. Then, we design HiFi-Net to fuse multi-face features and align them with landmarks, which improves ID fidelity and face control. In addition, we devise an automated pipeline to construct an ID-based dataset for training HiFi-Portrait. Extensive experimental results demonstrate that our method surpasses the SOTA approaches in face similarity and controllability. Furthermore, our method is also compatible with previous SDXL-based works.

Dong Wang, Yang Li, Ansong Ni et al.

Synthetic data has become increasingly important for training large language models, especially when real data is scarce, expensive, or privacy-sensitive. Many such generation tasks require coordinated multi-agent workflows, where specialized agents collaborate to produce data that is higher quality, more diverse, and structurally richer. However, existing frameworks for multi-agent synthesis often depend on a centralized orchestrator, creating scalability bottlenecks, or are hardcoded for specific domains, limiting flexibility. We present \textbf{Matrix}, a decentralized framework that represents both control and data flow as serialized messages passed through distributed queues. This peer-to-peer design eliminates the central orchestrator. Each task progresses independently through lightweight agents, while compute-intensive operations, such as LLM inference or containerized environments, are handled by distributed services. Built on Ray, Matrix scales to tens of thousands of concurrent agentic workflows and provides a modular, configurable design that enables easy adaptation to a wide range of data generation workflows. We evaluate Matrix across diverse synthesis scenarios, such as multi-agent collaborative dialogue, web-based reasoning data extraction, and tool-use trajectory generation in customer service environments. In all cases, Matrix achieves $2$--$15\times$ higher data generation throughput under identical hardware resources, without compromising output quality.

Dongchi Huang, Jiaqi Wang, Yang Li et al.

Partial observability presents a significant challenge for Safe Reinforcement Learning (Safe RL), as it impedes the identification of potential risks and rewards. Leveraging specific types of privileged information during training to mitigate the effects of partial observability has yielded notable empirical successes. In this paper, we propose Asymmetric Constrained Partially Observable Markov Decision Processes (ACPOMDPs) to theoretically examine the advantages of incorporating privileged information in Safe RL. Building upon ACPOMDPs, we propose the Privileged Information Guided Dreamer (PIGDreamer), a model-based RL approach that leverages privileged information to enhance the agent's safety and performance through privileged representation alignment and an asymmetric actor-critic structure. Our empirical results demonstrate that PIGDreamer significantly outperforms existing Safe RL methods. Furthermore, compared to alternative privileged RL methods, our approach exhibits enhanced performance, robustness, and efficiency. Codes are available at: https://github.com/hggforget/PIGDreamer.

Jingyun Yang, Guoqing Zhang, Jingge Wang et al.

Recent advances in foundation models have brought promising results in computer vision, including medical image segmentation. Fine-tuning foundation models on specific low-resource medical tasks has become a standard practice. However, ensuring reliable and robust model adaptation when the target task has a large domain gap and few annotated samples remains a challenge. Previous few-shot domain adaptation (FSDA) methods seek to bridge the distribution gap between source and target domains by utilizing auxiliary data. The selection and scheduling of auxiliaries are often based on heuristics, which can easily cause negative transfer. In this work, we propose an Active and Sequential domain AdaPtation (ASAP) framework for dynamic auxiliary dataset selection in FSDA. We formulate FSDA as a multi-armed bandit problem and derive an efficient reward function to prioritize training on auxiliary datasets that align closely with the target task, through a single-round fine-tuning. Empirical validation on diverse medical segmentation datasets demonstrates that our method achieves favorable segmentation performance, significantly outperforming the state-of-the-art FSDA methods, achieving an average gain of 27.75% on MRI and 7.52% on CT datasets in Dice score. Code is available at the git repository: https://github.com/techicoco/ASAP.

Wenhao Zhang, Shao Zhang, Xihuai Wang et al.

In-Context Reinforcement Learning (ICRL) has emerged as a promising paradigm for developing agents that can rapidly adapt to new tasks by leveraging past experiences as context, without updating their parameters. Recent approaches train large sequence models on monotonic policy improvement data from online RL, aiming to a continue improved testing time performance. However, our experimental analysis reveals a critical flaw: these models cannot show a continue improvement like the training data during testing time. Theoretically, we identify this phenomenon as Contextual Ambiguity, where the model's own stochastic actions can generate an interaction history that misleadingly resembles that of a sub-optimal policy from the training data, initiating a vicious cycle of poor action selection. To resolve the Contextual Ambiguity, we introduce Context Value into training phase and propose Context Value Informed ICRL (CV-ICRL). CV-ICRL use Context Value as an explicit signal representing the ideal performance theoretically achievable by a policy given the current context. As the context expands, Context Value could include more task-relevant information, and therefore the ideal performance should be non-decreasing. We prove that the Context Value tightens the lower bound on the performance gap relative to an ideal, monotonically improving policy. We fruther propose two methods for estimating Context Value at both training and testing time. Experiments conducted on the Dark Room and Minigrid testbeds demonstrate that CV-ICRL effectively mitigates performance degradation and improves overall ICRL abilities across various tasks and environments. The source code and data of this paper are available at https://github.com/Bluixe/towards_monotonic_improvement .

Yang Li, Tingfa Xu, Shuyan Bai et al.

Camouflaged Object Detection (COD) aims to identify objects that blend seamlessly into natural scenes. Although RGB-based methods have advanced, their performance remains limited under challenging conditions. Multispectral imagery, providing rich spectral information, offers a promising alternative for enhanced foreground-background discrimination. However, existing COD benchmark datasets are exclusively RGB-based, lacking essential support for multispectral approaches, which has impeded progress in this area. To address this gap, we introduce MCOD, the first challenging benchmark dataset specifically designed for multispectral camouflaged object detection. MCOD features three key advantages: (i) Comprehensive challenge attributes: It captures real-world difficulties such as small object sizes and extreme lighting conditions commonly encountered in COD tasks. (ii) Diverse real-world scenarios: The dataset spans a wide range of natural environments to better reflect practical applications. (iii) High-quality pixel-level annotations: Each image is manually annotated with precise object masks and corresponding challenge attribute labels. We benchmark eleven representative COD methods on MCOD, observing a consistent performance drop due to increased task difficulty. Notably, integrating multispectral modalities substantially alleviates this degradation, highlighting the value of spectral information in enhancing detection robustness. We anticipate MCOD will provide a strong foundation for future research in multispectral camouflaged object detection. The dataset is publicly accessible at https://github.com/yl2900260-bit/MCOD.

Yao Chen, Jiabao Wang, Peichao Wang et al.

Low-resolution fine-grained image classification has recently made significant progress, largely thanks to the super-resolution techniques and knowledge distillation methods. However, these approaches lead to an exponential increase in the number of parameters and computational complexity of models. In order to solve this problem, in this letter, we propose a Vision Mamba Distillation (ViMD) approach to enhance the effectiveness and efficiency of low-resolution fine-grained image classification. Concretely, a lightweight super-resolution vision Mamba classification network (SRVM-Net) is proposed to improve its capability for extracting visual features by redesigning the classification sub-network with Mamba modeling. Moreover, we design a novel multi-level Mamba knowledge distillation loss boosting the performance, which can transfer prior knowledge obtained from a High-resolution Vision Mamba classification Network (HRVM-Net) as a teacher into the proposed SRVM-Net as a student. Extensive experiments on seven public fine-grained classification datasets related to benchmarks confirm our ViMD achieves a new state-of-the-art performance. While having higher accuracy, ViMD outperforms similar methods with fewer parameters and FLOPs, which is more suitable for embedded device applications. Code is available at https://github.com/boa2004plaust/ViMD.

Yang Li, Shoaib Akbar, Junier B. Oliva

Understanding the dependencies among features of a dataset is at the core of most unsupervised learning tasks. However, a majority of generative modeling approaches are focused solely on the joint distribution $p(x)$ and utilize models where it is intractable to obtain the conditional distribution of some arbitrary subset of features $x_u$ given the rest of the observed covariates $x_o$: $p(x_u \mid x_o)$. Traditional conditional approaches provide a model for a fixed set of covariates conditioned on another fixed set of observed covariates. Instead, in this work we develop a model that is capable of yielding all conditional distributions $p(x_u \mid x_o)$ (for arbitrary $x_u$) via tractable conditional likelihoods. We propose a novel extension of (change of variables based) flow generative models, arbitrary conditioning flow models (AC-Flow), that can be conditioned on arbitrary subsets of observed covariates, which was previously infeasible. We apply AC-Flow to the imputation of features, and also develop a unified platform for both multiple and single imputation by introducing an auxiliary objective that provides a principled single "best guess" for flow models. Extensive empirical evaluations show that our models achieve state-of-the-art performance in both single and multiple imputation across image inpainting and feature imputation in synthetic and real-world datasets. Code is available at https://github.com/lupalab/ACFlow.

Yang Li

The rapid advancement in large language models (LLMs) has brought forth a diverse range of models with varying capabilities that excel in different tasks and domains. However, selecting the optimal LLM for user queries often involves a challenging trade-off between accuracy and cost, a problem exacerbated by the diverse demands of individual queries. In this work, we present a novel framework that formulates the LLM selection process as a multi-armed bandit problem, enabling dynamic and intelligent routing of queries to the most appropriate model. Our approach incorporates a preference-conditioned dynamic routing mechanism, allowing users to specify their preferences at inference time, thereby offering a customizable balance between performance and cost. Additionally, our selection policy is designed to generalize to unseen LLMs, ensuring adaptability to new models as they emerge. Experimental results demonstrate that our method achieves significant improvements in both accuracy and cost-effectiveness across various LLM platforms, showcasing the potential of our framework to adaptively optimize LLM selection in real-world scenarios.

Yiming Sun, Fan Yu, Shaoxiang Chen et al.

Visual object tracking aims to locate a targeted object in a video sequence based on an initial bounding box. Recently, Vision-Language~(VL) trackers have proposed to utilize additional natural language descriptions to enhance versatility in various applications. However, VL trackers are still inferior to State-of-The-Art (SoTA) visual trackers in terms of tracking performance. We found that this inferiority primarily results from their heavy reliance on manual textual annotations, which include the frequent provision of ambiguous language descriptions. In this paper, we propose ChatTracker to leverage the wealth of world knowledge in the Multimodal Large Language Model (MLLM) to generate high-quality language descriptions and enhance tracking performance. To this end, we propose a novel reflection-based prompt optimization module to iteratively refine the ambiguous and inaccurate descriptions of the target with tracking feedback. To further utilize semantic information produced by MLLM, a simple yet effective VL tracking framework is proposed and can be easily integrated as a plug-and-play module to boost the performance of both VL and visual trackers. Experimental results show that our proposed ChatTracker achieves a performance comparable to existing methods.

Libing Yang, Yang Li, Long Chen

Vision-based robotic cloth unfolding has made great progress recently. However, prior works predominantly rely on value learning and have not fully explored policy-based techniques. Recently, the success of reinforcement learning on the large language model has shown that the policy gradient algorithm can enhance policy with huge action space. In this paper, we introduce ClothPPO, a framework that employs a policy gradient algorithm based on actor-critic architecture to enhance a pre-trained model with huge 10^6 action spaces aligned with observation in the task of unfolding clothes. To this end, we redefine the cloth manipulation problem as a partially observable Markov decision process. A supervised pre-training stage is employed to train a baseline model of our policy. In the second stage, the Proximal Policy Optimization (PPO) is utilized to guide the supervised model within the observation-aligned action space. By optimizing and updating the strategy, our proposed method increases the garment's surface area for cloth unfolding under the soft-body manipulation task. Experimental results show that our proposed framework can further improve the unfolding performance of other state-of-the-art methods.

Shanshan Zhang, Mingqian Ji, Yang Li et al.

Pedestrian detection has significantly progressed in recent years, thanks to the development of DNNs. However, detection performance at occluded scenes is still far from satisfactory, as occlusion increases the intra-class variance of pedestrians, hindering the model from finding an accurate classification boundary between pedestrians and background clutters. From the perspective of reducing intra-class variance, we propose to complete features for occluded regions so as to align the features of pedestrians across different occlusion patterns. An important premise for feature completion is to locate occluded regions. From our analysis, channel features of different pedestrian proposals only show high correlation values at visible parts and thus feature correlations can be used to model occlusion patterns. In order to narrow down the gap between completed features and real fully visible ones, we propose an adversarial learning method, which completes occluded features with a generator such that they can hardly be distinguished by the discriminator from real fully visible features. We report experimental results on the CityPersons, Caltech and CrowdHuman datasets. On CityPersons, we show significant improvements over five different baseline detectors, especially on the heavy occlusion subset. Furthermore, we show that our proposed method FeatComp++ achieves state-of-the-art results on all the above three datasets without relying on extra cues.

Yang Li, Zhi Chen, Steve Yang

High-frequency trading (HFT) is an investing strategy that continuously monitors market states and places bid and ask orders at millisecond speeds. Traditional HFT approaches fit models with historical data and assume that future market states follow similar patterns. This limits the effectiveness of any single model to the specific conditions it was trained for. Additionally, these models achieve optimal solutions only under specific market conditions, such as assumptions about stock price's stochastic process, stable order flow, and the absence of sudden volatility. Real-world markets, however, are dynamic, diverse, and frequently volatile. To address these challenges, we propose the FlowHFT, a novel imitation learning framework based on flow matching policy. FlowHFT simultaneously learns strategies from numerous expert models, each proficient in particular market scenarios. As a result, our framework can adaptively adjust investment decisions according to the prevailing market state. Furthermore, FlowHFT incorporates a grid-search fine-tuning mechanism. This allows it to refine strategies and achieve superior performance even in complex or extreme market scenarios where expert strategies may be suboptimal. We test FlowHFT in multiple market environments. We first show that flow matching policy is applicable in stochastic market environments, thus enabling FlowHFT to learn trading strategies under different market conditions. Notably, our single framework consistently achieves performance superior to the best expert for each market condition.

Guanzi Chen, Jiying Zhang, Yang Li

Cross-graph node classification, utilizing the abundant labeled nodes from one graph to help classify unlabeled nodes in another graph, can be viewed as a domain generalization problem of graph neural networks (GNNs) due to the structure shift commonly appearing among various graphs. Nevertheless, current endeavors for cross-graph node classification mainly focus on model training. Data augmentation approaches, a simple and easy-to-implement domain generalization technique, remain under-explored. In this paper, we develop a new graph structure augmentation for the crossgraph domain generalization problem. Specifically, low-weight edgedropping is applied to remove potential noise edges that may hinder the generalization ability of GNNs, stimulating the GNNs to capture the essential invariant information underlying different structures. Meanwhile, clustering-based edge-adding is proposed to generate invariant structures based on the node features from the same distribution. Consequently, with these augmentation techniques, the GNNs can maintain the domain invariant structure information that can improve the generalization ability. The experiments on out-ofdistribution citation network datasets verify our method achieves state-of-the-art performance among conventional augmentations.

Yang Li, Zhichen Dong, Yuhan Sun et al.

The reasoning pattern of Large language models (LLMs) remains opaque, and Reinforcement learning (RL) typically applies uniform credit across an entire generation, blurring the distinction between pivotal and routine steps. This work positions attention as a privileged substrate that renders the internal logic of LLMs legible, not merely as a byproduct of computation, but as a mechanistic blueprint of reasoning itself. We first distinguish attention heads between locally and globally focused information processing and reveal that locally focused heads produce a sawtooth pattern near the diagonal indicating phrasal chunks, while globally focused heads expose tokens that exert broad downstream influence over future tokens. We formalize these with two metrics: 1) Windowed Average Attention Distance, which measures the extent of backward attention within a clipped window; 2) Future Attention Influence, which quantifies a token's global importance as the average attention it receives from subsequent tokens. Taken together, these signals reveal a recurring preplan-and-anchor mechanism, where the model first performs a long-range contextual reference to generate an introductory token, which is immediately followed by or coincides with a semantic anchor token that organizes subsequent reasoning. Leveraging these insights, we introduce three novel RL strategies that dynamically perform targeted credit assignment to critical nodes (preplan tokens, anchor tokens, and their temporal coupling) and show consistent performance gains across various reasoning tasks. By aligning optimization with the model's intrinsic reasoning rhythm, we aim to transform opaque optimization into an actionable structure-aware process, hoping to offer a potential step toward more transparent and effective optimization of LLM reasoning.

Shreyas Bhat Brahmavar, Yang Li, Junier Oliva

Real-world data often appears in diverse, disjoint forms -- with varying schemas, inconsistent semantics, and no fixed feature ordering -- making it challenging to build general-purpose models that can leverage information across datasets. We introduce ASPIRE, Arbitrary Set-based Permutation-Invariant Reasoning Engine, a Universal Neural Inference model for semantic reasoning and prediction over heterogeneous structured data. ASPIRE combines a permutation-invariant, set-based Transformer with a semantic grounding module that incorporates natural language descriptions, dataset metadata, and in-context examples to learn cross-dataset feature dependencies. This architecture allows ASPIRE to ingest arbitrary sets of feature--value pairs and support examples, align semantics across disjoint tables, and make predictions for any specified target. Once trained, ASPIRE generalizes to new inference tasks without additional tuning. In addition to delivering strong results across diverse benchmarks, ASPIRE naturally supports cost-aware active feature acquisition in an open-world setting, selecting informative features under test-time budget constraints for an arbitrary unseen dataset. These capabilities position ASPIRE as a step toward truly universal, semantics-aware inference over structured data.

Dongwei Pan, Yang Li, Hongsheng Li et al.

We present TimeWalker, a novel framework that models realistic, full-scale 3D head avatars of a person on lifelong scale. Unlike current human head avatar pipelines that capture identity at the momentary level(e.g., instant photography or short videos), TimeWalker constructs a person's comprehensive identity from unstructured data collection over his/her various life stages, offering a paradigm to achieve full reconstruction and animation of that person at different moments of life. At the heart of TimeWalker's success is a novel neural parametric model that learns personalized representation with the disentanglement of shape, expression, and appearance across ages. Central to our methodology are the concepts of two aspects: (1) We track back to the principle of modeling a person's identity in an additive combination of average head representation in the canonical space, and moment-specific head attribute representations driven from a set of neural head basis. To learn the set of head basis that could represent the comprehensive head variations in a compact manner, we propose a Dynamic Neural Basis-Blending Module (Dynamo). It dynamically adjusts the number and blend weights of neural head bases, according to both shared and specific traits of the target person over ages. (2) Dynamic 2D Gaussian Splatting (DNA-2DGS), an extension of Gaussian splatting representation, to model head motion deformations like facial expressions without losing the realism of rendering and reconstruction. DNA-2DGS includes a set of controllable 2D oriented planar Gaussian disks that utilize the priors from parametric model, and move/rotate with the change of expression. Through extensive experimental evaluations, we show TimeWalker's ability to reconstruct and animate avatars across decoupled dimensions with realistic rendering effects, demonstrating a way to achieve personalized 'time traveling' in a breeze.

Yi-Kai Zhang, Shiyin Lu, Yang Li et al.

Multimodal large language models (MLLMs), initiated with a trained LLM, first align images with text and then fine-tune on multimodal mixed inputs. However, the MLLM catastrophically forgets the text-only instructions, which do not include images and can be addressed within the initial LLM. In this paper, we present Wings, a novel MLLM that excels in both text-only dialogues and multimodal comprehension. Analyzing MLLM attention in multimodal instructions reveals that text-only forgetting is related to the attention shifts from pre-image to post-image text. From that, we construct extra modules that act as the boosted learner to compensate for the attention shift. The complementary visual and textual learners, like "wings" on either side, are connected in parallel within each layer's attention block. Initially, image and text inputs are aligned with visual learners operating alongside the main attention, balancing focus on visual elements. Textual learners are later collaboratively integrated with attention-based routing to blend the outputs of the visual and textual learners. We design the Low-Rank Residual Attention (LoRRA) to guarantee high efficiency for learners. Our experimental results demonstrate that Wings outperforms equally-scaled MLLMs in both text-only and visual question-answering tasks. On a newly constructed Interleaved Image-Text (IIT) benchmark, Wings exhibits superior performance from text-only-rich to multimodal-rich question-answering tasks.

Yang Li, Hong Zhang, Yu Zhang

The ImageNet pre-training initialization is the de-facto standard for object detection. He et al. found it is possible to train detector from scratch(random initialization) while needing a longer training schedule with proper normalization technique. In this paper, we explore to directly pre-training on target dataset for object detection. Under this situation, we discover that the widely adopted large resizing strategy e.g. resize image to (1333, 800) is important for fine-tuning but it's not necessary for pre-training. Specifically, we propose a new training pipeline for object detection that follows `pre-training and fine-tuning', utilizing low resolution images within target dataset to pre-training detector then load it to fine-tuning with high resolution images. With this strategy, we can use batch normalization(BN) with large bath size during pre-training, it's also memory efficient that we can apply it on machine with very limited GPU memory(11G). We call it direct detection pre-training, and also use direct pre-training for short. Experiment results show that direct pre-training accelerates the pre-training phase by more than 11x on COCO dataset while with even +1.8mAP compared to ImageNet pre-training. Besides, we found direct pre-training is also applicable to transformer based backbones e.g. Swin Transformer. Code will be available.

Yang Li, Zinc Zhang, Hutchin Huang

Hateful content detection is one of the areas where deep learning can and should make a significant difference. The Hateful Memes Challenge from Facebook helps fulfill such potential by challenging the contestants to detect hateful speech in multi-modal memes using deep learning algorithms. In this paper, we utilize multi-modal, pre-trained models VilBERT and Visual BERT. We improved models' performance by adding training datasets generated from data augmentation. Enlarging the training data set helped us get a more than 2% boost in terms of AUROC with the Visual BERT model. Our approach achieved 0.7439 AUROC along with an accuracy of 0.7037 on the challenge's test set, which revealed remarkable progress.

Jiabao Wang, Yang Li, Shanshan Jiao et al.

Convolutional neural networks have shown outstanding effectiveness in person re-identification (re-ID). However, the models always have large number of parameters and much computation for mobile application. In order to relieve this problem, we propose a novel grafted network (GraftedNet), which is designed by grafting a high-accuracy rootstock and a light-weighted scion. The rootstock is based on the former parts of ResNet-50 to provide a strong baseline, while the scion is a new designed module, composed of the latter parts of SqueezeNet, to compress the parameters. To extract more discriminative feature representation, a joint multi-level and part-based feature is proposed. In addition, to train GraftedNet efficiently, we propose an accompanying learning method, by adding an accompanying branch to train the model in training and removing it in testing for saving parameters and computation. On three public person re-ID benchmarks (Market1501, DukeMTMC-reID and CUHK03), the effectiveness of GraftedNet are evaluated and its components are analyzed. Experimental results show that the proposed GraftedNet achieves 93.02%, 85.3% and 76.2% in Rank-1 and 81.6%, 74.7% and 71.6% in mAP, with only 4.6M parameters.

Jiabao Wang, Yang Li, Yangshuo Zhang et al.

Convolutional neural networks with multiple branches have recently been proved highly effective in person re-identification (re-ID). Researchers design multi-branch networks using part models, yet they always attribute the effectiveness to multiple parts. In addition, existing multi-branch networks always have isomorphic branches, which lack structural diversity. In order to improve this problem, we propose a novel Heterogeneous Branch and Multi-level Classification Network (HBMCN), which is designed based on the pre-trained ResNet-50 model. A new heterogeneous branch, SE-Res-Branch, is proposed based on the SE-Res module, which consists of the Squeeze-and-Excitation block and the residual block. Furthermore, a new multi-level classification joint objective function is proposed for the supervised learning of HBMCN, whereby multi-level features are extracted from multiple high-level layers and concatenated to represent a person. Based on three public person re-ID benchmarks (Market1501, DukeMTMC-reID and CUHK03), experimental results show that the proposed HBMCN reaches 94.4%, 85.7% and 73.8% in Rank-1, and 85.7%, 74.6% and 69.0% in mAP, achieving a state-of-the-art performance. Further analysis demonstrates that the specially designed heterogeneous branch performs better than an isomorphic branch, and multi-level classification provides more discriminative features compared to single-level classification. As a result, HBMCN provides substantial further improvements in person re-ID tasks.

Yang Li, Guodong Long, Tao Shen et al.

Distantly supervised relation extraction intrinsically suffers from noisy labels due to the strong assumption of distant supervision. Most prior works adopt a selective attention mechanism over sentences in a bag to denoise from wrongly labeled data, which however could be incompetent when there is only one sentence in a bag. In this paper, we propose a brand-new light-weight neural framework to address the distantly supervised relation extraction problem and alleviate the defects in previous selective attention framework. Specifically, in the proposed framework, 1) we use an entity-aware word embedding method to integrate both relative position information and head/tail entity embeddings, aiming to highlight the essence of entities for this task; 2) we develop a self-attention mechanism to capture the rich contextual dependencies as a complement for local dependencies captured by piecewise CNN; and 3) instead of using selective attention, we design a pooling-equipped gate, which is based on rich contextual representations, as an aggregator to generate bag-level representation for final relation classification. Compared to selective attention, one major advantage of the proposed gating mechanism is that, it performs stably and promisingly even if only one sentence appears in a bag and thus keeps the consistency across all training examples. The experiments on NYT dataset demonstrate that our approach achieves a new state-of-the-art performance in terms of both AUC and top-n precision metrics.

Yang Li, Tianxiang Gao, Junier B. Oliva

In this work, we propose to learn a generative model using both learned features (through a latent space) and memories (through neighbors). Although human learning makes seamless use of both learned perceptual features and instance recall, current generative learning paradigms only make use of one of these two components. Take, for instance, flow models, which learn a latent space of invertible features that follow a simple distribution. Conversely, kernel density techniques use instances to shift a simple distribution into an aggregate mixture model. Here we propose multiple methods to enhance the latent space of a flow model with neighborhood information. Not only does our proposed framework represent a more human-like approach by leveraging both learned features and memories, but it may also be viewed as a step forward in non-parametric methods. The efficacy of our model is shown empirically with standard image datasets. We observe compelling results and a significant improvement over baselines.

Jiabao Wang, Yang Li, Zhuang Miao

In person re-identification (re-ID), the key task is feature representation, which is used to compute distance or similarity in prediction. Person re-ID achieves great improvement when deep learning methods are introduced to tackle this problem. The features extracted by convolutional neural networks (CNN) are more effective and discriminative than the hand-crafted features. However, deep feature extracted by a single CNN network is not robust enough in testing stage. To improve the ability of feature representation, we propose a new ensemble network (EnsembleNet) by dividing a single network into multiple end-to-end branches. The ensemble feature is obtained by concatenating each of the branch features to represent a person. EnsembleNet is designed based on ResNet-50 and its backbone shares most of the parameters for saving computation and memory cost. Experimental results show that our EnsembleNet achieves the state-of-the-art performance on the public Market1501, DukeMTMC-reID and CUHK03 person re-ID benchmarks.

Yadan Luo, Zi Huang, Yang Li et al.

Hashing techniques are in great demand for a wide range of real-world applications such as image retrieval and network compression. Nevertheless, existing approaches could hardly guarantee a satisfactory performance with the extremely low-bit (e.g., 4-bit) hash codes due to the severe information loss and the shrink of the discrete solution space. In this paper, we propose a novel \textit{Collaborative Learning} strategy that is tailored for generating high-quality low-bit hash codes. The core idea is to jointly distill bit-specific and informative representations for a group of pre-defined code lengths. The learning of short hash codes among the group can benefit from the manifold shared with other long codes, where multiple views from different hash codes provide the supplementary guidance and regularization, making the convergence faster and more stable. To achieve that, an asymmetric hashing framework with two variants of multi-head embedding structures is derived, termed as Multi-head Asymmetric Hashing (MAH), leading to great efficiency of training and querying. Extensive experiments on three benchmark datasets have been conducted to verify the superiority of the proposed MAH, and have shown that the 8-bit hash codes generated by MAH achieve $94.3\%$ of the MAP (Mean Average Precision (MAP)) score on the CIFAR-10 dataset, which significantly surpasses the performance of the 48-bit codes by the state-of-the-arts in image retrieval tasks.

Yang Li, Samy Bengio, Gilles Bailly

Predicting human performance in interaction tasks allows designers or developers to understand the expected performance of a target interface without actually testing it with real users. In this work, we present a deep neural net to model and predict human performance in performing a sequence of UI tasks. In particular, we focus on a dominant class of tasks, i.e., target selection from a vertical list or menu. We experimented with our deep neural net using a public dataset collected from a desktop laboratory environment and a dataset collected from hundreds of touchscreen smartphone users via crowdsourcing. Our model significantly outperformed previous methods on these datasets. Importantly, our method, as a deep model, can easily incorporate additional UI attributes such as visual appearance and content semantics without changing model architectures. By understanding about how a deep learning model learns from human behaviors, our approach can be seen as a vehicle to discover new patterns about human behaviors to advance analytical modeling.