Qiming Zhang

Yufei Xu, Jing Zhang, Qiming Zhang et al.

Although no specific domain knowledge is considered in the design, plain vision transformers have shown excellent performance in visual recognition tasks. However, little effort has been made to reveal the potential of such simple structures for pose estimation tasks. In this paper, we show the surprisingly good capabilities of plain vision transformers for pose estimation from various aspects, namely simplicity in model structure, scalability in model size, flexibility in training paradigm, and transferability of knowledge between models, through a simple baseline model called ViTPose. Specifically, ViTPose employs plain and non-hierarchical vision transformers as backbones to extract features for a given person instance and a lightweight decoder for pose estimation. It can be scaled up from 100M to 1B parameters by taking the advantages of the scalable model capacity and high parallelism of transformers, setting a new Pareto front between throughput and performance. Besides, ViTPose is very flexible regarding the attention type, input resolution, pre-training and finetuning strategy, as well as dealing with multiple pose tasks. We also empirically demonstrate that the knowledge of large ViTPose models can be easily transferred to small ones via a simple knowledge token. Experimental results show that our basic ViTPose model outperforms representative methods on the challenging MS COCO Keypoint Detection benchmark, while the largest model sets a new state-of-the-art. The code and models are available at https://github.com/ViTAE-Transformer/ViTPose.

Qiming Zhang, Yufei Xu, Jing Zhang et al.

Attention within windows has been widely explored in vision transformers to balance the performance, computation complexity, and memory footprint. However, current models adopt a hand-crafted fixed-size window design, which restricts their capacity of modeling long-term dependencies and adapting to objects of different sizes. To address this drawback, we propose \textbf{V}aried-\textbf{S}ize Window \textbf{A}ttention (VSA) to learn adaptive window configurations from data. Specifically, based on the tokens within each default window, VSA employs a window regression module to predict the size and location of the target window, i.e., the attention area where the key and value tokens are sampled. By adopting VSA independently for each attention head, it can model long-term dependencies, capture rich context from diverse windows, and promote information exchange among overlapped windows. VSA is an easy-to-implement module that can replace the window attention in state-of-the-art representative models with minor modifications and negligible extra computational cost while improving their performance by a large margin, e.g., 1.1\% for Swin-T on ImageNet classification. In addition, the performance gain increases when using larger images for training and test. Experimental results on more downstream tasks, including object detection, instance segmentation, and semantic segmentation, further demonstrate the superiority of VSA over the vanilla window attention in dealing with objects of different sizes. The code will be released https://github.com/ViTAE-Transformer/ViTAE-VSA.

Qiming Zhang, Jing Zhang, Yufei Xu et al.

Window-based attention has become a popular choice in vision transformers due to its superior performance, lower computational complexity, and less memory footprint. However, the design of hand-crafted windows, which is data-agnostic, constrains the flexibility of transformers to adapt to objects of varying sizes, shapes, and orientations. To address this issue, we propose a novel quadrangle attention (QA) method that extends the window-based attention to a general quadrangle formulation. Our method employs an end-to-end learnable quadrangle regression module that predicts a transformation matrix to transform default windows into target quadrangles for token sampling and attention calculation, enabling the network to model various targets with different shapes and orientations and capture rich context information. We integrate QA into plain and hierarchical vision transformers to create a new architecture named QFormer, which offers minor code modifications and negligible extra computational cost. Extensive experiments on public benchmarks demonstrate that QFormer outperforms existing representative vision transformers on various vision tasks, including classification, object detection, semantic segmentation, and pose estimation. The code will be made publicly available at \href{https://github.com/ViTAE-Transformer/QFormer}{QFormer}.

Wei Li, Qiming Zhang, Jing Zhang et al.

Single image deraining (SID) in real scenarios attracts increasing attention in recent years. Due to the difficulty in obtaining real-world rainy/clean image pairs, previous real datasets suffer from low-resolution images, homogeneous rain streaks, limited background variation, and even misalignment of image pairs, resulting in incomprehensive evaluation of SID methods. To address these issues, we establish a new high-quality dataset named RealRain-1k, consisting of $1,120$ high-resolution paired clean and rainy images with low- and high-density rain streaks, respectively. Images in RealRain-1k are automatically generated from a large number of real-world rainy video clips through a simple yet effective rain density-controllable filtering method, and have good properties of high image resolution, background diversity, rain streaks variety, and strict spatial alignment. RealRain-1k also provides abundant rain streak layers as a byproduct, enabling us to build a large-scale synthetic dataset named SynRain-13k by pasting the rain streak layers on abundant natural images. Based on them and existing datasets, we benchmark more than 10 representative SID methods on three tracks: (1) fully supervised learning on RealRain-1k, (2) domain generalization to real datasets, and (3) syn-to-real transfer learning. The experimental results (1) show the difference of representative methods in image restoration performance and model complexity, (2) validate the significance of the proposed datasets for model generalization, and (3) provide useful insights on the superiority of learning from diverse domains and shed lights on the future research on real-world SID. The datasets will be released at https://github.com/hiker-lw/RealRain-1k

Haimei Zhao, Qiming Zhang, Shanshan Zhao et al.

Multi-view camera-based 3D object detection has become popular due to its low cost, but accurately inferring 3D geometry solely from camera data remains challenging and may lead to inferior performance. Although distilling precise 3D geometry knowledge from LiDAR data could help tackle this challenge, the benefits of LiDAR information could be greatly hindered by the significant modality gap between different sensory modalities. To address this issue, we propose a Simulated multi-modal Distillation (SimDistill) method by carefully crafting the model architecture and distillation strategy. Specifically, we devise multi-modal architectures for both teacher and student models, including a LiDAR-camera fusion-based teacher and a simulated fusion-based student. Owing to the ``identical'' architecture design, the student can mimic the teacher to generate multi-modal features with merely multi-view images as input, where a geometry compensation module is introduced to bridge the modality gap. Furthermore, we propose a comprehensive multi-modal distillation scheme that supports intra-modal, cross-modal, and multi-modal fusion distillation simultaneously in the Bird's-eye-view space. Incorporating them together, our SimDistill can learn better feature representations for 3D object detection while maintaining a cost-effective camera-only deployment. Extensive experiments validate the effectiveness and superiority of SimDistill over state-of-the-art methods, achieving an improvement of 4.8\% mAP and 4.1\% NDS over the baseline detector. The source code will be released at https://github.com/ViTAE-Transformer/SimDistill.

Di Wang, Qiming Zhang, Yufei Xu et al.

Large-scale vision foundation models have made significant progress in visual tasks on natural images, with vision transformers being the primary choice due to their good scalability and representation ability. However, large-scale models in remote sensing (RS) have not yet been sufficiently explored. In this paper, we resort to plain vision transformers with about 100 million parameters and make the first attempt to propose large vision models tailored to RS tasks and investigate how such large models perform. To handle the large sizes and objects of arbitrary orientations in RS images, we propose a new rotated varied-size window attention to replace the original full attention in transformers, which can significantly reduce the computational cost and memory footprint while learning better object representation by extracting rich context from the generated diverse windows. Experiments on detection tasks show the superiority of our model over all state-of-the-art models, achieving 81.24% mAP on the DOTA-V1.0 dataset. The results of our models on downstream classification and segmentation tasks also show competitive performance compared to existing advanced methods. Further experiments show the advantages of our models in terms of computational complexity and data efficiency in transferring.

Mingjin Zhang, Chi Zhang, Qiming Zhang et al.

Recent advancements in deep learning have greatly advanced the field of infrared small object detection (IRSTD). Despite their remarkable success, a notable gap persists between these IRSTD methods and generic segmentation approaches in natural image domains. This gap primarily arises from the significant modality differences and the limited availability of infrared data. In this study, we aim to bridge this divergence by investigating the adaptation of generic segmentation models, such as the Segment Anything Model (SAM), to IRSTD tasks. Our investigation reveals that many generic segmentation models can achieve comparable performance to state-of-the-art IRSTD methods. However, their full potential in IRSTD remains untapped. To address this, we propose a simple, lightweight, yet effective baseline model for segmenting small infrared objects. Through appropriate distillation strategies, we empower smaller student models to outperform state-of-the-art methods, even surpassing fine-tuned teacher results. Furthermore, we enhance the model's performance by introducing a novel query design comprising dense and sparse queries to effectively encode multi-scale features. Through extensive experimentation across four popular IRSTD datasets, our model demonstrates significantly improved performance in both accuracy and throughput compared to existing approaches, surpassing SAM and Semantic-SAM by over 14 IoU on NUDT and 4 IoU on IRSTD1k. The source code and models will be released at https://github.com/O937-blip/SimIR.

Yufei Xu, Jing Zhang, Qiming Zhang et al.

Self-supervised pre-training vision transformer (ViT) via masked image modeling (MIM) has been proven very effective. However, customized algorithms should be carefully designed for the hierarchical ViTs, e.g., GreenMIM, instead of using the vanilla and simple MAE for the plain ViT. More importantly, since these hierarchical ViTs cannot reuse the off-the-shelf pre-trained weights of the plain ViTs, the requirement of pre-training them leads to a massive amount of computational cost, thereby incurring both algorithmic and computational complexity. In this paper, we address this problem by proposing a novel idea of disentangling the hierarchical architecture design from the self-supervised pre-training. We transform the plain ViT into a hierarchical one with minimal changes. Technically, we change the stride of linear embedding layer from 16 to 4 and add convolution (or simple average) pooling layers between the transformer blocks, thereby reducing the feature size from 1/4 to 1/32 sequentially. Despite its simplicity, it outperforms the plain ViT baseline in classification, detection, and segmentation tasks on ImageNet, MS COCO, Cityscapes, and ADE20K benchmarks, respectively. We hope this preliminary study could draw more attention from the community on developing effective (hierarchical) ViTs while avoiding the pre-training cost by leveraging the off-the-shelf checkpoints. The code and models will be released at https://github.com/ViTAE-Transformer/HPViT.

Yufei Xu, Jing Zhang, Qiming Zhang et al.

In this paper, we show the surprisingly good properties of plain vision transformers for body pose estimation from various aspects, namely simplicity in model structure, scalability in model size, flexibility in training paradigm, and transferability of knowledge between models, through a simple baseline model dubbed ViTPose. Specifically, ViTPose employs the plain and non-hierarchical vision transformer as an encoder to encode features and a lightweight decoder to decode body keypoints in either a top-down or a bottom-up manner. It can be scaled up from about 20M to 1B parameters by taking advantage of the scalable model capacity and high parallelism of the vision transformer, setting a new Pareto front for throughput and performance. Besides, ViTPose is very flexible regarding the attention type, input resolution, and pre-training and fine-tuning strategy. Based on the flexibility, a novel ViTPose+ model is proposed to deal with heterogeneous body keypoint categories in different types of body pose estimation tasks via knowledge factorization, i.e., adopting task-agnostic and task-specific feed-forward networks in the transformer. We also empirically demonstrate that the knowledge of large ViTPose models can be easily transferred to small ones via a simple knowledge token. Experimental results show that our ViTPose model outperforms representative methods on the challenging MS COCO Human Keypoint Detection benchmark at both top-down and bottom-up settings. Furthermore, our ViTPose+ model achieves state-of-the-art performance simultaneously on a series of body pose estimation tasks, including MS COCO, AI Challenger, OCHuman, MPII for human keypoint detection, COCO-Wholebody for whole-body keypoint detection, as well as AP-10K and APT-36K for animal keypoint detection, without sacrificing inference speed.

Benjamin Kiefer, Matej Kristan, Janez Perš et al.

The 1$^{\text{st}}$ Workshop on Maritime Computer Vision (MaCVi) 2023 focused on maritime computer vision for Unmanned Aerial Vehicles (UAV) and Unmanned Surface Vehicle (USV), and organized several subchallenges in this domain: (i) UAV-based Maritime Object Detection, (ii) UAV-based Maritime Object Tracking, (iii) USV-based Maritime Obstacle Segmentation and (iv) USV-based Maritime Obstacle Detection. The subchallenges were based on the SeaDronesSee and MODS benchmarks. This report summarizes the main findings of the individual subchallenges and introduces a new benchmark, called SeaDronesSee Object Detection v2, which extends the previous benchmark by including more classes and footage. We provide statistical and qualitative analyses, and assess trends in the best-performing methodologies of over 130 submissions. The methods are summarized in the appendix. The datasets, evaluation code and the leaderboard are publicly available at https://seadronessee.cs.uni-tuebingen.de/macvi.

Jiawei Zhou, Chi Zhang, Xiang Feng et al.

We present Omni-I2C, a comprehensive benchmark designed to evaluate the capability of Large Multimodal Models (LMMs) in converting complex, structured digital graphics into executable code. We argue that this task represents a non-trivial challenge for the current generation of LMMs: it demands an unprecedented synergy between high-fidelity visual perception -- to parse intricate spatial hierarchies and symbolic details -- and precise generative expression -- to synthesize syntactically sound and logically consistent code. Unlike traditional descriptive tasks, Omni-I2C requires a holistic understanding where any minor perceptual hallucination or coding error leads to a complete failure in visual reconstruction. Omni-I2C features 1080 meticulously curated samples, defined by its breadth across subjects, image modalities, and programming languages. By incorporating authentic user-sourced cases, the benchmark spans a vast spectrum of digital content -- from scientific visualizations to complex symbolic notations -- each paired with executable reference code. To complement this diversity, our evaluation framework provides necessary depth; by decoupling performance into perceptual fidelity and symbolic precision, it transcends surface-level accuracy to expose the granular structural failures and reasoning bottlenecks of current LMMs. Our evaluation reveals a substantial performance gap among leading LMMs; even state-of-the-art models struggle to preserve structural integrity in complex scenarios, underscoring that multimodal code generation remains a formidable challenge. Data and code are available at https://github.com/MiliLab/Omni-I2C.

Mingjin Zhang, Chi Zhang, Qiming Zhang et al.

Single hyperspectral image super-resolution (single-HSI-SR) aims to restore a high-resolution hyperspectral image from a low-resolution observation. However, the prevailing CNN-based approaches have shown limitations in building long-range dependencies and capturing interaction information between spectral features. This results in inadequate utilization of spectral information and artifacts after upsampling. To address this issue, we propose ESSAformer, an ESSA attention-embedded Transformer network for single-HSI-SR with an iterative refining structure. Specifically, we first introduce a robust and spectral-friendly similarity metric, \ie, the spectral correlation coefficient of the spectrum (SCC), to replace the original attention matrix and incorporates inductive biases into the model to facilitate training. Built upon it, we further utilize the kernelizable attention technique with theoretical support to form a novel efficient SCC-kernel-based self-attention (ESSA) and reduce attention computation to linear complexity. ESSA enlarges the receptive field for features after upsampling without bringing much computation and allows the model to effectively utilize spatial-spectral information from different scales, resulting in the generation of more natural high-resolution images. Without the need for pretraining on large-scale datasets, our experiments demonstrate ESSA's effectiveness in both visual quality and quantitative results.

Qian Xu, Chi Zhang, Qiming Zhang et al.

Infrared small target detection (IRSTD) faces the inherent challenge of precisely localizing dim targets amid complex background clutter. While progress has been made, existing methods usually follow conventional strategies to downsample features and discard small targets' details, resulting in suboptimal performance. In this paper, we present Na-IRSTD, a native-resolution feature extraction and fusion framework for IRSTD. This framework elegantly incorporates native-resolution features to preserve subtle target cues, overcoming the resolution limitations of existing infrared approaches and significantly improving the model's ability to localize small targets. We also introduce an effective token reduction and selection strategy, which selects target patches with high accuracy and confidence, boosting the low-level details of the feature while effectively reducing native-resolution patch tokens compared to dense processing, thereby avoiding imposing an unbearable computational burden. Extensive experiments demonstrate the robustness and effectiveness of our token reduction and selection strategy across multiple public datasets. Ultimately, our Na-IRSTD model achieves state-of-the-art performance on four benchmarks.

Lincan Li, Wei Shao, Wei Dong et al.

The aspiration of the next generation's autonomous driving (AD) technology relies on the dedicated integration and interaction among intelligent perception, prediction, planning, and low-level control. There has been a huge bottleneck regarding the upper bound of autonomous driving algorithm performance, a consensus from academia and industry believes that the key to surmount the bottleneck lies in data-centric autonomous driving technology. Recent advancement in AD simulation, closed-loop model training, and AD big data engine have gained some valuable experience. However, there is a lack of systematic knowledge and deep understanding regarding how to build efficient data-centric AD technology for AD algorithm self-evolution and better AD big data accumulation. To fill in the identified research gaps, this article will closely focus on reviewing the state-of-the-art data-driven autonomous driving technologies, with an emphasis on the comprehensive taxonomy of autonomous driving datasets characterized by milestone generations, key features, data acquisition settings, etc. Furthermore, we provide a systematic review of the existing benchmark closed-loop AD big data pipelines from the industrial frontier, including the procedure of closed-loop frameworks, key technologies, and empirical studies. Finally, the future directions, potential applications, limitations and concerns are discussed to arouse efforts from both academia and industry for promoting the further development of autonomous driving. The project repository is available at: https://github.com/LincanLi98/Awesome-Data-Centric-Autonomous-Driving.

Xiucheng Wang, Qiming Zhang, Nan Cheng et al.

Radio maps (RMs) serve as a critical foundation for enabling environment-aware wireless communication, as they provide the spatial distribution of wireless channel characteristics. Despite recent progress in RM construction using data-driven approaches, most existing methods focus solely on pathloss prediction in a fixed 2D plane, neglecting key parameters such as direction of arrival (DoA), time of arrival (ToA), and vertical spatial variations. Such a limitation is primarily due to the reliance on static learning paradigms, which hinder generalization beyond the training data distribution. To address these challenges, we propose UrbanRadio3D, a large-scale, high-resolution 3D RM dataset constructed via ray tracing in realistic urban environments. UrbanRadio3D is over 37$\times$3 larger than previous datasets across a 3D space with 3 metrics as pathloss, DoA, and ToA, forming a novel 3D$\times$33D dataset with 7$\times$3 more height layers than prior state-of-the-art (SOTA) dataset. To benchmark 3D RM construction, a UNet with 3D convolutional operators is proposed. Moreover, we further introduce RadioDiff-3D, a diffusion-model-based generative framework utilizing the 3D convolutional architecture. RadioDiff-3D supports both radiation-aware scenarios with known transmitter locations and radiation-unaware settings based on sparse spatial observations. Extensive evaluations on UrbanRadio3D validate that RadioDiff-3D achieves superior performance in constructing rich, high-dimensional radio maps under diverse environmental dynamics. This work provides a foundational dataset and benchmark for future research in 3D environment-aware communication. The dataset is available at https://github.com/UNIC-Lab/UrbanRadio3D.

Hui Zhong, Yichun Gao, Luyan Liu et al.

Building facade defect inspection is fundamental to structural health monitoring and sustainable urban maintenance, yet it remains a formidable challenge due to extreme geometric variability, low contrast against complex backgrounds, and the inherent complexity of composite defects (e.g., cracks co-occurring with spalling). Such characteristics lead to severe pixel imbalance and feature ambiguity, which, coupled with the critical scarcity of high-quality pixel-level annotations, hinder the generalization of existing detection and segmentation models. To address gaps, we propose \textit{FacadeFixer}, a unified multi-agent framework that treats defect perception as a collaborative reasoning task rather than isolated recognition. Specifically,\textit{FacadeFixer} orchestrates specialized agents for detection and segmentation to handle multi-type defect interference, working in tandem with a generative agent to enable semantic recomposition. This process decouples intricate defects from noisy backgrounds and realistically synthesizes them onto diverse clean textures, generating high-fidelity augmented data with precise expert-level masks. To support this, we introduce a comprehensive multi-task dataset covering six primary facade categories with pixel-level annotations. Extensive experiments demonstrate that \textit{FacadeFixer} significantly outperforms state-of-the-art (SOTA) baselines. Specifically, it excels in capturing pixel-level structural anomalies and highlights generative synthesis as a robust solution to data scarcity in infrastructure inspection. Our code and dataset will be made publicly available.

Chi Zhang, Haibo Qiu, Qiming Zhang et al.

We present Seirênes, a self-play RL framework that transforms contextual interference from a failure mode of LLM reasoning into an internal training signal for co-evolving more resilient reasoners. While RL with verifiable rewards has significantly advanced reasoning capabilities, models can still exhibit fragility when encountering non-idealized contexts: scenarios characterized by superfluous information, tangential instructions, or incidental correlations that differ from the clean distributions typical of standard benchmarks. Seirênes harnesses this vulnerability through a parameter-shared and adversarial self-play loop. Within this framework, a single model is trained to both construct plausible yet distracting contexts that expose its own reasoning blind spots, and solve problems by discerning the essential task from these perturbations to recover the core underlying logic. By pitting these competing objectives against each other, Seirênes compels the model to move beyond superficial pattern matching and anchors its capabilities in robust underlying reasoning. This continuous interaction sustains an informative co-evolutionary curriculum as the model improves. Across seven mathematical reasoning benchmarks and model scales from 4B to 30B, Seirênes achieves average gains of +10.2, +9.1, and +7.2 points. Besides, distracting contexts produced by the 4B Seirênes model reduce the accuracy of top-tier closed-source models (GPT and Gemini) by roughly 4--5 points, revealing Seirênes' general ability to uncover reasoning models' blind spots.

Yanbin Zhang, Hanhui Ye, Yue Bai et al.

Workflow automation promises substantial productivity gains in everyday document-related tasks. While prior agentic systems can execute isolated instructions, they struggle with automating multi-step, session-level workflows due to limited control over the operational process. To this end, we introduce AutoDW, a novel execution framework that enables stepwise, rollback-enabled operation orchestration. AutoDW incrementally plans API actions conditioned on user instructions, intent-filtered API candidates, and the evolving states of the document. It further employs robust rollback mechanisms at both the argument and API levels, enabling dynamic correction and fault tolerance. These designs together ensure that the execution trajectory of AutoDW remains aligned with user intent and document context across long-horizon workflows. To assess its effectiveness, we construct a comprehensive benchmark of 250 sessions and 1,708 human-annotated instructions, reflecting realistic document processing scenarios with interdependent instructions. AutoDW achieves 90% and 62% completion rates on instruction- and session-level tasks, respectively, outperforming strong baselines by 40% and 76%. Moreover, AutoDW also remains robust for the decision of backbone LLMs and on tasks with varying difficulty. Code and data will be open-sourced. Code: https://github.com/YJett/AutoDW

Tao Chen, Liang Lv, Di Wang et al.

With the world population rapidly increasing, transforming our agrifood systems to be more productive, efficient, safe, and sustainable is crucial to mitigate potential food shortages. Recently, artificial intelligence (AI) techniques such as deep learning (DL) have demonstrated their strong abilities in various areas, including language, vision, remote sensing (RS), and agrifood systems applications. However, the overall impact of AI on agrifood systems remains unclear. In this paper, we thoroughly review how AI techniques can transform agrifood systems and contribute to the modern agrifood industry. Firstly, we summarize the data acquisition methods in agrifood systems, including acquisition, storage, and processing techniques. Secondly, we present a progress review of AI methods in agrifood systems, specifically in agriculture, animal husbandry, and fishery, covering topics such as agrifood classification, growth monitoring, yield prediction, and quality assessment. Furthermore, we highlight potential challenges and promising research opportunities for transforming modern agrifood systems with AI. We hope this survey could offer an overall picture to newcomers in the field and serve as a starting point for their further research. The project website is https://github.com/Frenkie14/Agrifood-Survey.

Yufei Xu, Qiming Zhang, Jing Zhang et al.

Self-supervised methods (SSL) have achieved significant success via maximizing the mutual information between two augmented views, where cropping is a popular augmentation technique. Cropped regions are widely used to construct positive pairs, while the left regions after cropping have rarely been explored in existing methods, although they together constitute the same image instance and both contribute to the description of the category. In this paper, we make the first attempt to demonstrate the importance of both regions in cropping from a complete perspective and propose a simple yet effective pretext task called Region Contrastive Learning (RegionCL). Specifically, given two different images, we randomly crop a region (called the paste view) from each image with the same size and swap them to compose two new images together with the left regions (called the canvas view), respectively. Then, contrastive pairs can be efficiently constructed according to the following simple criteria, i.e., each view is (1) positive with views augmented from the same original image and (2) negative with views augmented from other images. With minor modifications to popular SSL methods, RegionCL exploits those abundant pairs and helps the model distinguish the regions features from both canvas and paste views, therefore learning better visual representations. Experiments on ImageNet, MS COCO, and Cityscapes demonstrate that RegionCL improves MoCo v2, DenseCL, and SimSiam by large margins and achieves state-of-the-art performance on classification, detection, and segmentation tasks. The code will be available at https://github.com/Annbless/RegionCL.git.

Haoyu He, Jing Zhang, Qiming Zhang et al.

Human parsing, or human body part semantic segmentation, has been an active research topic due to its wide potential applications. In this paper, we propose a novel GRAph PYramid Mutual Learning (Grapy-ML) method to address the cross-dataset human parsing problem, where the annotations are at different granularities. Starting from the prior knowledge of the human body hierarchical structure, we devise a graph pyramid module (GPM) by stacking three levels of graph structures from coarse granularity to fine granularity subsequently. At each level, GPM utilizes the self-attention mechanism to model the correlations between context nodes. Then, it adopts a top-down mechanism to progressively refine the hierarchical features through all the levels. GPM also enables efficient mutual learning. Specifically, the network weights of the first two levels are shared to exchange the learned coarse-granularity information across different datasets. By making use of the multi-granularity labels, Grapy-ML learns a more discriminative feature representation and achieves state-of-the-art performance, which is demonstrated by extensive experiments on the three popular benchmarks, e.g. CIHP dataset. The source code is publicly available at https://github.com/Charleshhy/Grapy-ML.

Qiming Zhang, Jing Zhang, Wei Liu et al.

Unsupervised domain adaptation (UDA) aims to enhance the generalization capability of a certain model from a source domain to a target domain. UDA is of particular significance since no extra effort is devoted to annotating target domain samples. However, the different data distributions in the two domains, or \emph{domain shift/discrepancy}, inevitably compromise the UDA performance. Although there has been a progress in matching the marginal distributions between two domains, the classifier favors the source domain features and makes incorrect predictions on the target domain due to category-agnostic feature alignment. In this paper, we propose a novel category anchor-guided (CAG) UDA model for semantic segmentation, which explicitly enforces category-aware feature alignment to learn shared discriminative features and classifiers simultaneously. First, the category-wise centroids of the source domain features are used as guided anchors to identify the active features in the target domain and also assign them pseudo-labels. Then, we leverage an anchor-based pixel-level distance loss and a discriminative loss to drive the intra-category features closer and the inter-category features further apart, respectively. Finally, we devise a stagewise training mechanism to reduce the error accumulation and adapt the proposed model progressively. Experiments on both the GTA5$\rightarrow $Cityscapes and SYNTHIA$\rightarrow $Cityscapes scenarios demonstrate the superiority of our CAG-UDA model over the state-of-the-art methods. The code is available at \url{https://github.com/RogerZhangzz/CAG_UDA}.

Huan Wang, Qiming Zhang, Yuehai Wang et al.

Parameter pruning is a promising approach for CNN compression and acceleration by eliminating redundant model parameters with tolerable performance degrade. Despite its effectiveness, existing regularization-based parameter pruning methods usually drive weights towards zero with large and constant regularization factors, which neglects the fragility of the expressiveness of CNNs, and thus calls for a more gentle regularization scheme so that the networks can adapt during pruning. To achieve this, we propose a new and novel regularization-based pruning method, named IncReg, to incrementally assign different regularization factors to different weights based on their relative importance. Empirical analysis on CIFAR-10 dataset verifies the merits of IncReg. Further extensive experiments with popular CNNs on CIFAR-10 and ImageNet datasets show that IncReg achieves comparable to even better results compared with state-of-the-arts. Our source codes and trained models are available here: https://github.com/mingsun-tse/caffe_increg.

Xusen Guo, Qiming Zhang, Junyue Jiang et al.

Traffic forecasting is crucial for intelligent transportation systems. It has experienced significant advancements thanks to the power of deep learning in capturing latent patterns of traffic data. However, recent deep-learning architectures require intricate model designs and lack an intuitive understanding of the mapping from input data to predicted results. Achieving both accuracy and explainability in traffic prediction models remains a challenge due to the complexity of traffic data and the inherent opacity of deep learning models. To tackle these challenges, we propose a Traffic flow Prediction model based on Large Language Models (LLMs) to generate explainable traffic predictions, named xTP-LLM. By transferring multi-modal traffic data into natural language descriptions, xTP-LLM captures complex time-series patterns and external factors from comprehensive traffic data. The LLM framework is fine-tuned using language-based instructions to align with spatial-temporal traffic flow data. Empirically, xTP-LLM shows competitive accuracy compared with deep learning baselines, while providing an intuitive and reliable explanation for predictions. This paper contributes to advancing explainable traffic prediction models and lays a foundation for future exploration of LLM applications in transportation. To the best of our knowledge, this is the first study to use LLM for explainable prediction of traffic flows.

Wentao Jiang, Jing Zhang, Di Wang et al.

Due to spatial redundancy in remote sensing images, sparse tokens containing rich information are usually involved in self-attention (SA) to reduce the overall token numbers within the calculation, avoiding the high computational cost issue in Vision Transformers. However, such methods usually obtain sparse tokens by hand-crafted or parallel-unfriendly designs, posing a challenge to reach a better balance between efficiency and performance. Different from them, this paper proposes to use learnable meta tokens to formulate sparse tokens, which effectively learn key information meanwhile improving the inference speed. Technically, the meta tokens are first initialized from image tokens via cross-attention. Then, we propose Dual Cross-Attention (DCA) to promote information exchange between image tokens and meta tokens, where they serve as query and key (value) tokens alternatively in a dual-branch structure, significantly reducing the computational complexity compared to self-attention. By employing DCA in the early stages with dense visual tokens, we obtain the hierarchical architecture LeMeViT with various sizes. Experimental results in classification and dense prediction tasks show that LeMeViT has a significant $1.7 \times$ speedup, fewer parameters, and competitive performance compared to the baseline models, and achieves a better trade-off between efficiency and performance.

Xiucheng Wang, Qiming Zhang, Nan Cheng et al.

In this paper, we propose a novel physics-informed generative learning approach, named RadioDiff-$k^2$, for accurate and efficient multipath-aware radio map (RM) construction. As future wireless communication evolves towards environment-aware paradigms, the accurate construction of RMs becomes crucial yet highly challenging. Conventional electromagnetic (EM)-based methods, such as full-wave solvers and ray-tracing approaches, exhibit substantial computational overhead and limited adaptability to dynamic scenarios. Although existing neural network (NN) approaches have efficient inferencing speed, they lack sufficient consideration of the underlying physics of EM wave propagation, limiting their effectiveness in accurately modeling critical EM singularities induced by complex multipath environments. To address these fundamental limitations, we propose a novel physics-inspired RM construction method guided explicitly by the Helmholtz equation, which inherently governs EM wave propagation. Specifically, based on the analysis of partial differential equations (PDEs), we theoretically establish a direct correspondence between EM singularities, which correspond to the critical spatial features influencing wireless propagation, and regions defined by negative wave numbers in the Helmholtz equation. We then design an innovative dual diffusion model (DM)-based large artificial intelligence framework comprising one DM dedicated to accurately inferring EM singularities and another DM responsible for reconstructing the complete RM using these singularities along with environmental contextual information. Experimental results demonstrate that the proposed RadioDiff-$k^2$ framework achieves state-of-the-art (SOTA) performance in both image-level RM construction and localization tasks, while maintaining inference latency within a few hundred milliseconds.

Weidi Luo, Tianyu Lu, Qiming Zhang et al.

Recent advances in multi-modal large reasoning models (MLRMs) have shown significant ability to interpret complex visual content. While these models enable impressive reasoning capabilities, they also introduce novel and underexplored privacy risks. In this paper, we identify a novel category of privacy leakage in MLRMs: Adversaries can infer sensitive geolocation information, such as a user's home address or neighborhood, from user-generated images, including selfies captured in private settings. To formalize and evaluate these risks, we propose a three-level visual privacy risk framework that categorizes image content based on contextual sensitivity and potential for location inference. We further introduce DoxBench, a curated dataset of 500 real-world images reflecting diverse privacy scenarios. Our evaluation across 11 advanced MLRMs and MLLMs demonstrates that these models consistently outperform non-expert humans in geolocation inference and can effectively leak location-related private information. This significantly lowers the barrier for adversaries to obtain users' sensitive geolocation information. We further analyze and identify two primary factors contributing to this vulnerability: (1) MLRMs exhibit strong reasoning capabilities by leveraging visual clues in combination with their internal world knowledge; and (2) MLRMs frequently rely on privacy-related visual clues for inference without any built-in mechanisms to suppress or avoid such usage. To better understand and demonstrate real-world attack feasibility, we propose GeoMiner, a collaborative attack framework that decomposes the prediction process into two stages: clue extraction and reasoning to improve geolocation performance while introducing a novel attack perspective. Our findings highlight the urgent need to reassess inference-time privacy risks in MLRMs to better protect users' sensitive information.

Chi Zhang, Chengjian Feng, Feng Yan et al.

Video editing according to instructions is a highly challenging task due to the difficulty in collecting large-scale, high-quality edited video pair data. This scarcity not only limits the availability of training data but also hinders the systematic exploration of model architectures and training strategies. While prior work has improved specific aspects of video editing (e.g., synthesizing a video dataset using image editing techniques or decomposed video editing training), a holistic framework addressing the above challenges remains underexplored. In this study, we introduce InstructVEdit, a full-cycle instructional video editing approach that: (1) establishes a reliable dataset curation workflow to initialize training, (2) incorporates two model architectural improvements to enhance edit quality while preserving temporal consistency, and (3) proposes an iterative refinement strategy leveraging real-world data to enhance generalization and minimize train-test discrepancies. Extensive experiments show that InstructVEdit achieves state-of-the-art performance in instruction-based video editing, demonstrating robust adaptability to diverse real-world scenarios. Project page: https://o937-blip.github.io/InstructVEdit.

Chi Zhang, Haibo Qiu, Qiming Zhang et al.

The "thinking with images" paradigm represents a pivotal shift in the reasoning of Vision Language Models (VLMs), moving from text-dominant chain-of-thought to image-interactive reasoning. By invoking visual tools or generating intermediate visual representations, VLMs can iteratively attend to fine-grained regions, enabling deeper image understanding and more faithful multimodal reasoning. As an emerging paradigm, however, it still leaves substantial room for exploration in data construction accuracy, structural design, and broader application scenarios, which offer rich opportunities for advancing multimodal reasoning. To further advance this line of work, we present DeepSketcher, a comprehensive suite comprising both an image-text interleaved dataset and a self-contained model. The dataset contains 31k chain-of-thought (CoT) reasoning trajectories with diverse tool calls and resulting edited images, covering a wide range of data types and manipulation instructions with high annotation accuracy. Building on this resource, we design a model that performs interleaved image-text reasoning and natively generates "visual thoughts" by operating directly in the visual embedding space, rather than invoking external tools and repeatedly re-encoding generated images. This design enables tool-free and more flexible "thinking with images". Extensive experiments on multimodal reasoning benchmarks demonstrate strong performance, validating both the utility of the dataset and the effectiveness of the model design.

Chi Zhang, Haibo Qiu, Qiming Zhang et al.

Reinforcement Learning with Verifiable Rewards (RLVR) has significantly advanced the reasoning capabilities of Large Language Models (LLMs) and is now being applied to Vision-Language Models (VLMs). However, vanilla RLVR for VLMs verifies only the final textual output, critically neglecting the foundational step of visual perception. This oversight leads to visual hallucinations and reward hacking, as reasoning built upon flawed perception is inherently unreliable. To address this, we propose PEARL (Perceptual-Evidence Anchored Reinforced Learning), a dual-branch, perception-reasoning synergistic that strengthens multimodal reasoning by explicitly anchoring it to verified visual evidence. For each reasoning-oriented QA instance, PEARL first derive a perception checklist -- a set of perception-oriented sub-questions with verifiable answers that probe the model's understanding of key visual evidence. During training, auxiliary rollouts on this checklist yield a perceptual reward that both directly reinforces the model's perception ability and acts as a fidelity gate for reasoning. If the model passes the perception check, its policy update is biased towards evidence-anchored reasoning. Otherwise, the process is halted to prevent reasoning from flawed premises. PEARL can be seamlessly integrated with popular RL methods like GRPO and DAPO. Comprehensive experiments show PEARL achieves substantial gains on multimodal reasoning benchmarks, e.g., a +9.7% improvement over the baseline and +6.6% over GRPO on MathVerse.

Xiucheng Wang, Qiming Zhang, Nan Cheng

Accurate localization of non-cooperative signal sources in non-line-of-sight (NLoS) environments remains a critical challenge with a wide range of applications, including autonomous navigation, industrial automation, and emergency response. In such settings, traditional positioning techniques relying on line-of-sight (LoS) or cooperative signaling fail due to severe multipath propagation and unknown transmit power. This paper proposes a novel generative inference framework for NLoS localization based on conditional diffusion models. By leveraging the physical insight that diffracted electromagnetic energy concentrates near building edges, we develop a sampling strategy that collects sparse received signal strength (RSS) measurements at the geometric vertices of obstacles--locations that maximize Fisher information and mutual information with respect to the unknown source. To overcome the lack of known transmission power, we normalize all sampled RSS values relative to the maximum observed intensity, enabling the construction of a power-invariant radio map (RM). A conditional diffusion model is trained to reconstruct the full RM based on environmental layout and sparse RSS observations. Localization is then achieved by identifying the brightest point on the generated RM. Moreover, the proposed framework is compatible with existing RSS-based localization algorithms, enabling a dual-driven paradigm that fuses physical knowledge and data-driven inference for improved accuracy. Extensive theoretical analysis and empirical validation demonstrate that our approach achieves high localization accuracy with significantly reduced sampling cost, offering a scalable and physically grounded solution for non-cooperative NLoS emitter localization.

Wenxin Mao, Zhitao Wang, Long Wang et al.

Large language models (LLMs) excel at generating code from natural language (NL) descriptions. However, the plain textual descriptions are inherently ambiguous and often fail to capture complex requirements like intricate system behaviors, conditional logic, and architectural constraints; implicit data dependencies in service-oriented architectures are difficult to infer and handle correctly. To bridge this gap, we propose a novel step-by-step code generation framework named UML2Dep by leveraging unambiguous formal specifications of complex requirements. First, we introduce an enhanced Unified Modeling Language (UML) sequence diagram tailored for service-oriented architectures. This diagram extends traditional visual syntax by integrating decision tables and API specifications, explicitly formalizing structural relationships and business logic flows in service interactions to rigorously eliminate linguistic ambiguity. Second, recognizing the critical role of data flow, we introduce a dedicated data dependency inference (DDI) task. DDI systematically constructs an explicit data dependency graph prior to actual code synthesis. To ensure reliability, we formalize DDI as a constrained mathematical reasoning task through novel prompting strategies, aligning with LLMs' excellent mathematical strengths. Additional static parsing and dependency pruning further reduce context complexity and cognitive load associated with intricate specifications, thereby enhancing reasoning accuracy and efficiency.

Qiming Zhang, Yufei Xu, Jing Zhang et al.

Vision transformers have shown great potential in various computer vision tasks owing to their strong capability to model long-range dependency using the self-attention mechanism. Nevertheless, they treat an image as a 1D sequence of visual tokens, lacking an intrinsic inductive bias (IB) in modeling local visual structures and dealing with scale variance, which is instead learned implicitly from large-scale training data with longer training schedules. In this paper, we propose a Vision Transformer Advanced by Exploring intrinsic IB from convolutions, i.e., ViTAE. Technically, ViTAE has several spatial pyramid reduction modules to downsample and embed the input image into tokens with rich multi-scale context using multiple convolutions with different dilation rates. In this way, it acquires an intrinsic scale invariance IB and can learn robust feature representation for objects at various scales. Moreover, in each transformer layer, ViTAE has a convolution block parallel to the multi-head self-attention module, whose features are fused and fed into the feed-forward network. Consequently, it has the intrinsic locality IB and is able to learn local features and global dependencies collaboratively. The proposed two kinds of cells are stacked in both isotropic and multi-stage manners to formulate two families of ViTAE models, i.e., the vanilla ViTAE and ViTAEv2. Experiments on the ImageNet dataset as well as downstream tasks on the MS COCO, ADE20K, and AP10K datasets validate the superiority of our models over the baseline transformer models and concurrent works. Besides, we scale up our ViTAE model to 644M parameters and obtain the state-of-the-art classification performance, i.e., 88.5% Top-1 classification accuracy on ImageNet validation set and the best 91.2% Top-1 accuracy on ImageNet real validation set, without using extra private data.

Yufei Xu, Qiming Zhang, Jing Zhang et al.

Transformers have shown great potential in various computer vision tasks owing to their strong capability in modeling long-range dependency using the self-attention mechanism. Nevertheless, vision transformers treat an image as 1D sequence of visual tokens, lacking an intrinsic inductive bias (IB) in modeling local visual structures and dealing with scale variance. Alternatively, they require large-scale training data and longer training schedules to learn the IB implicitly. In this paper, we propose a novel Vision Transformer Advanced by Exploring intrinsic IB from convolutions, ie, ViTAE. Technically, ViTAE has several spatial pyramid reduction modules to downsample and embed the input image into tokens with rich multi-scale context by using multiple convolutions with different dilation rates. In this way, it acquires an intrinsic scale invariance IB and is able to learn robust feature representation for objects at various scales. Moreover, in each transformer layer, ViTAE has a convolution block in parallel to the multi-head self-attention module, whose features are fused and fed into the feed-forward network. Consequently, it has the intrinsic locality IB and is able to learn local features and global dependencies collaboratively. Experiments on ImageNet as well as downstream tasks prove the superiority of ViTAE over the baseline transformer and concurrent works. Source code and pretrained models will be available at GitHub.

Agrim Gupta, Cedric Girerd, Manideep Dunna et al.

Contact force is a natural way for humans to interact with the physical world around us. However, most of our interactions with the digital world are largely based on a simple binary sense of touch (contact or no contact). Similarly, when interacting with robots to perform complex tasks, such as surgery, richer force information that includes both magnitude and contact location is important for task performance. To address these challenges, we present the design and fabrication of WiForce which is a 'wireless' sensor, sentient to contact force magnitude and location. WiForce achieves this by transducing force magnitude and location, to phase changes of an incident RF signal of a backscattering tag. The phase changes are thus modulated into the backscattered RF signal, which enables measurement of force magnitude and contact location by inferring the phases of the reflected RF signal. WiForce's sensor is designed to support wide-band frequencies all the way up to 3 GHz. We evaluate the force sensing wirelessly in different environments, including through phantom tissue, and achieve force accuracy of 0.3 N and contact location accuracy of 0.6 mm.

Huan Wang, Qiming Zhang, Yuehai Wang et al.

Parameter pruning is a promising approach for CNN compression and acceleration by eliminating redundant model parameters with tolerable performance loss. Despite its effectiveness, existing regularization-based parameter pruning methods usually drive weights towards zero with large and constant regularization factors, which neglects the fact that the expressiveness of CNNs is fragile and needs a more gentle way of regularization for the networks to adapt during pruning. To solve this problem, we propose a new regularization-based pruning method (named IncReg) to incrementally assign different regularization factors to different weight groups based on their relative importance, whose effectiveness is proved on popular CNNs compared with state-of-the-art methods.

Huan Wang, Qiming Zhang, Yuehai Wang et al.

In this paper, we propose a novel progressive parameter pruning method for Convolutional Neural Network acceleration, named Structured Probabilistic Pruning (SPP), which effectively prunes weights of convolutional layers in a probabilistic manner. Unlike existing deterministic pruning approaches, where unimportant weights are permanently eliminated, SPP introduces a pruning probability for each weight, and pruning is guided by sampling from the pruning probabilities. A mechanism is designed to increase and decrease pruning probabilities based on importance criteria in the training process. Experiments show that, with 4x speedup, SPP can accelerate AlexNet with only 0.3% loss of top-5 accuracy and VGG-16 with 0.8% loss of top-5 accuracy in ImageNet classification. Moreover, SPP can be directly applied to accelerate multi-branch CNN networks, such as ResNet, without specific adaptations. Our 2x speedup ResNet-50 only suffers 0.8% loss of top-5 accuracy on ImageNet. We further show the effectiveness of SPP on transfer learning tasks.