Sheng Guo

Jiange Yang, Sheng Guo, Gangshan Wu et al.

Current RGB-D scene recognition approaches often train two standalone backbones for RGB and depth modalities with the same Places or ImageNet pre-training. However, the pre-trained depth network is still biased by RGB-based models which may result in a suboptimal solution. In this paper, we present a single-model self-supervised hybrid pre-training framework for RGB and depth modalities, termed as CoMAE. Our CoMAE presents a curriculum learning strategy to unify the two popular self-supervised representation learning algorithms: contrastive learning and masked image modeling. Specifically, we first build a patch-level alignment task to pre-train a single encoder shared by two modalities via cross-modal contrastive learning. Then, the pre-trained contrastive encoder is passed to a multi-modal masked autoencoder to capture the finer context features from a generative perspective. In addition, our single-model design without requirement of fusion module is very flexible and robust to generalize to unimodal scenario in both training and testing phases. Extensive experiments on SUN RGB-D and NYUDv2 datasets demonstrate the effectiveness of our CoMAE for RGB and depth representation learning. In addition, our experiment results reveal that CoMAE is a data-efficient representation learner. Although we only use the small-scale and unlabeled training set for pre-training, our CoMAE pre-trained models are still competitive to the state-of-the-art methods with extra large-scale and supervised RGB dataset pre-training. Code will be released at https://github.com/MCG-NJU/CoMAE.

Sheng Guo, Zihua Xiong, Yujie Zhong et al.

In this paper, we present a new cross-architecture contrastive learning (CACL) framework for self-supervised video representation learning. CACL consists of a 3D CNN and a video transformer which are used in parallel to generate diverse positive pairs for contrastive learning. This allows the model to learn strong representations from such diverse yet meaningful pairs. Furthermore, we introduce a temporal self-supervised learning module able to predict an Edit distance explicitly between two video sequences in the temporal order. This enables the model to learn a rich temporal representation that compensates strongly to the video-level representation learned by the CACL. We evaluate our method on the tasks of video retrieval and action recognition on UCF101 and HMDB51 datasets, where our method achieves excellent performance, surpassing the state-of-the-art methods such as VideoMoCo and MoCo+BE by a large margin. The code is made available at https://github.com/guoshengcv/CACL.

Wujiang Xu, Runzhong Wang, Xiaobo Guo et al.

Video summarization intends to produce a concise video summary by effectively capturing and combining the most informative parts of the whole content. Existing approaches for video summarization regard the task as a frame-wise keyframe selection problem and generally construct the frame-wise representation by combining the long-range temporal dependency with the unimodal or bimodal information. However, the optimal video summaries need to reflect the most valuable keyframe with its own information, and one with semantic power of the whole content. Thus, it is critical to construct a more powerful and robust frame-wise representation and predict the frame-level importance score in a fair and comprehensive manner. To tackle the above issues, we propose a multimodal hierarchical shot-aware convolutional network, denoted as MHSCNet, to enhance the frame-wise representation via combining the comprehensive available multimodal information. Specifically, we design a hierarchical ShotConv network to incorporate the adaptive shot-aware frame-level representation by considering the short-range and long-range temporal dependency. Based on the learned shot-aware representations, MHSCNet can predict the frame-level importance score in the local and global view of the video. Extensive experiments on two standard video summarization datasets demonstrate that our proposed method consistently outperforms state-of-the-art baselines. Source code will be made publicly available.

Zifan Shi, Yujun Shen, Yinghao Xu et al.

Existing methods for 3D-aware image synthesis largely depend on the 3D pose distribution pre-estimated on the training set. An inaccurate estimation may mislead the model into learning faulty geometry. This work proposes PoF3D that frees generative radiance fields from the requirements of 3D pose priors. We first equip the generator with an efficient pose learner, which is able to infer a pose from a latent code, to approximate the underlying true pose distribution automatically. We then assign the discriminator a task to learn pose distribution under the supervision of the generator and to differentiate real and synthesized images with the predicted pose as the condition. The pose-free generator and the pose-aware discriminator are jointly trained in an adversarial manner. Extensive results on a couple of datasets confirm that the performance of our approach, regarding both image quality and geometry quality, is on par with state of the art. To our best knowledge, PoF3D demonstrates the feasibility of learning high-quality 3D-aware image synthesis without using 3D pose priors for the first time.

Zewei Yu, Lirong Gao, Yuke Zhu et al.

Large Reasoning Models (LRMs) have demonstrated remarkable performance on complex reasoning tasks by employing test-time scaling. However, they often generate over-long chains-of-thought that, driven by substantial reflections such as repetitive self-questioning and circular reasoning, lead to high token consumption, substantial computational overhead, and increased latency without improving accuracy, particularly in smaller models. Our observation reveals that increasing problem complexity induces more excessive and unnecessary reflection, which in turn reduces accuracy and increases token overhead. To address this challenge, we propose Adaptive Reflection and Length Coordinated Penalty (ARLCP), a novel reinforcement learning framework designed to dynamically balance reasoning efficiency and solution accuracy. ARLCP introduces two key innovations: (1) a reflection penalty that adaptively curtails unnecessary reflective steps while preserving essential reasoning, and (2) a length penalty calibrated to the estimated complexity of the problem. By coordinating these penalties, ARLCP encourages the model to generate more concise and effective reasoning paths. We evaluate our method on five mathematical reasoning benchmarks using DeepSeek-R1-Distill-Qwen-1.5B and DeepSeek-R1-Distill-Qwen-7B models. Experimental results show that ARLCP achieves a superior efficiency-accuracy trade-off compared to existing approaches. For the 1.5B model, it reduces the average response length by 53.1% while simultaneously improving accuracy by 5.8%. For the 7B model, it achieves a 35.0% reduction in length with a 2.7% accuracy gain. The code is released at https://github.com/ZeweiYu1/ARLCP .

Hanlin Wang, Yilu Wu, Sheng Guo et al.

In this paper, we study the problem of procedure planning in instructional videos, which aims to make a plan (i.e. a sequence of actions) given the current visual observation and the desired goal. Previous works cast this as a sequence modeling problem and leverage either intermediate visual observations or language instructions as supervision to make autoregressive planning, resulting in complex learning schemes and expensive annotation costs. To avoid intermediate supervision annotation and error accumulation caused by planning autoregressively, we propose a diffusion-based framework, coined as PDPP, to directly model the whole action sequence distribution with task label as supervision instead. Our core idea is to treat procedure planning as a distribution fitting problem under the given observations, thus transform the planning problem to a sampling process from this distribution during inference. The diffusion-based modeling approach also effectively addresses the uncertainty issue in procedure planning. Based on PDPP, we further apply joint training to our framework to generate plans with varying horizon lengths using a single model and reduce the number of training parameters required. We instantiate our PDPP with three popular diffusion models and investigate a series of condition-introducing methods in our framework, including condition embeddings, MoEs, two-stage prediction and Classifier-Free Guidance strategy. Finally, we apply our PDPP to the Visual Planners for human Assistance problem which requires the goal specified in natural language rather than visual observation. We conduct experiments on challenging datasets of different scales and our PDPP model achieves the state-of-the-art performance on multiple metrics, even compared with those strongly-supervised counterparts. These results further demonstrates the effectiveness and generalization ability of our model.

Yuanyuan Chen, Zichen Chen, Sheng Guo et al.

Artificial intelligence (AI)-empowered industrial fault diagnostics is important in ensuring the safe operation of industrial applications. Since complex industrial systems often involve multiple industrial plants (possibly belonging to different companies or subsidiaries) with sensitive data collected and stored in a distributed manner, collaborative fault diagnostic model training often needs to leverage federated learning (FL). As the scale of the industrial fault diagnostic models are often large and communication channels in such systems are often not exclusively used for FL model training, existing deployed FL model training frameworks cannot train such models efficiently across multiple institutions. In this paper, we report our experience developing and deploying the Federated Opportunistic Block Dropout (FEDOBD) approach for industrial fault diagnostic model training. By decomposing large-scale models into semantic blocks and enabling FL participants to opportunistically upload selected important blocks in a quantized manner, it significantly reduces the communication overhead while maintaining model performance. Since its deployment in ENN Group in February 2022, FEDOBD has served two coal chemical plants across two cities in China to build industrial fault prediction models. It helped the company reduce the training communication overhead by over 70% compared to its previous AI Engine, while maintaining model performance at over 85% test F1 score. To our knowledge, it is the first successfully deployed dropout-based FL approach.

Yao Teng, Haisong Liu, Sheng Guo et al.

Previous object detectors make predictions based on dense grid points or numerous preset anchors. Most of these detectors are trained with one-to-many label assignment strategies. On the contrary, recent query-based object detectors depend on a sparse set of learnable queries and a series of decoder layers. The one-to-one label assignment is independently applied on each layer for the deep supervision during training. Despite the great success of query-based object detection, however, this one-to-one label assignment strategy demands the detectors to have strong fine-grained discrimination and modeling capacity. To solve the above problems, in this paper, we propose a new query-based object detector with cross-stage interaction, coined as StageInteractor. During the forward propagation, we come up with an efficient way to improve this modeling ability by reusing dynamic operators with lightweight adapters. As for the label assignment, a cross-stage label assigner is applied subsequent to the one-to-one label assignment. With this assigner, the training target class labels are gathered across stages and then reallocated to proper predictions at each decoder layer. On MS COCO benchmark, our model improves the baseline by 2.2 AP, and achieves 44.8 AP with ResNet-50 as backbone, 100 queries and 12 training epochs. With longer training time and 300 queries, StageInteractor achieves 51.1 AP and 52.2 AP with ResNeXt-101-DCN and Swin-S, respectively.

Sheng Guo, Zengxiang Li, Hui Liu et al.

Intelligent fault diagnosis is essential to safe operation of machinery. However, due to scarce fault samples and data heterogeneity in field machinery, deep learning based diagnosis methods are prone to over-fitting with poor generalization ability. To solve the problem, this paper proposes a personalized federated learning framework, enabling multi-task fault diagnosis method across multiple factories in a privacypreserving manner. Firstly, rotating machines from different factories with similar vibration feature data are categorized into machine groups using a federated clustering method. Then, a multi-task deep learning model based on convolutional neural network is constructed to diagnose the multiple faults of machinery with heterogeneous information fusion. Finally, a personalized federated learning framework is proposed to solve data heterogeneity across different machines using adaptive hierarchical aggregation strategy. The case study on collected data from real machines verifies the effectiveness of the proposed framework. The result shows that the diagnosis accuracy could be improved significantly using the proposed personalized federated learning, especially for those machines with scarce fault samples.

Renhong Huang, Ning Tang, Jiarong Xu et al.

Social platforms serve as central hubs for information exchange, where user behaviors and platform interventions jointly shape opinions. However, intervention policies like recommendation and content filtering, can unintentionally amplify echo chambers and polarization, posing significant societal risks. Proactively evaluating the impact of such policies is therefore crucial. Existing approaches primarily rely on reactive online A/B testing, where risks are identified only after deployment, making risk identification delayed and costly. LLM-based social simulations offer a promising pre-deployment alternative, but current methods fall short in realistically modeling platform interventions and incorporating feedback from the platform. Bridging these gaps is essential for building actionable frameworks to assess and optimize platform policies. To this end, we propose PolicySim, an LLM-based social simulation sandbox for the proactive assessment and optimization of intervention policies. PolicySim models the bidirectional dynamics between user behavior and platform interventions through two key components: (1) a user agent module refined via supervised fine-tuning (SFT) and direct preference optimization (DPO) to achieve platform-specific behavioral realism; and (2) an adaptive intervention module that employs a contextual bandit with message passing to capture dynamic network structures. Experiments show that PolicySim can accurately simulate platform ecosystems at both micro and macro levels and support effective intervention policy.

Yiwen Chen, Xue Li, Sheng Guo et al.

Reinforcement learning has shown a wide usage in robotics tasks, such as insertion and grasping. However, without a practical sim2real strategy, the policy trained in simulation could fail on the real task. There are also wide researches in the sim2real strategies, but most of those methods rely on heavy image rendering, domain randomization training, or tuning. In this work, we solve the insertion task using a pure visual reinforcement learning solution with minimum infrastructure requirement. We also propose a novel sim2real strategy, Real2Sim, which provides a novel and easier solution in policy adaptation. We discuss the advantage of Real2Sim compared with Sim2Real.

Yang Chen, Sheng Guo, Bo Zheng et al.

Recently, dataset condensation has made significant progress in the image domain. Unlike images, videos possess an additional temporal dimension, which harbors considerable redundant information, making condensation even more crucial. However, video dataset condensation still remains an underexplored area. We aim to bridge this gap by providing a large-scale study with systematic design and fair comparison. Specifically, our work delves into three key aspects to provide valuable empirical insights: (1) temporal processing of video data, (2) the evaluation protocol for video dataset condensation, and (3) adaptation of condensation algorithms to the space-time domain. From this study, we derive several intriguing observations: (i) labeling methods greatly influence condensation performance, (ii) simple sliding-window sampling is effective for temporal processing, and (iii) dataset distillation methods perform better in challenging scenarios, while sample selection methods excel in easier ones. Furthermore, we propose a unified evaluation protocol for the fair comparison of different condensation algorithms and achieve state-of-the-art results on four widely-used action recognition datasets: HMDB51, UCF101, SSv2 and K400. Our code is available at https://github.com/MCG-NJU/Video-DC.

Yiwen Chen, Sheng Guo, Zedong Zhang et al.

Precision robotic manipulation tasks (insertion, screwing, precisely pick, precisely place) are required in many scenarios. Previous methods achieved good performance on such manipulation tasks. However, such methods typically require tedious calibration or expensive sensors. 3D/RGB-D cameras and torque/force sensors add to the cost of the robotic application and may not always be economical. In this work, we aim to solve these but using only weak-calibrated and low-cost webcams. We propose Binocular Alignment Learning (BAL), which could automatically learn the eye-hand coordination and points alignment capabilities to solve the four tasks. Our work focuses on working with unknown eye-hand coordination and proposes different ways of performing eye-in-hand camera calibration automatically. The algorithm was trained in simulation and used a practical pipeline to achieve sim2real and test it on the real robot. Our method achieves a competitively good result with minimal cost on the four tasks.

Bo Zheng, Yudong Chen, Zihua Xiong et al.

Tabular data forms the backbone of high-stakes decision systems in finance, healthcare, and beyond. Yet industrial tabular datasets are inherently difficult: high-dimensional, riddled with missing entries, and rarely labeled at scale. While foundation models have revolutionized vision and language, tabular learning still leans on handcrafted features and lacks a general self-supervised framework. We present MaskTab, a unified pre-training framework designed specifically for industrial-scale tabular data. MaskTab encodes missing values via dedicated learnable tokens, enabling the model to distinguish structural absence from random dropout. It jointly optimizes a hybrid supervised pre-training scheme--utilizing a twin-path architecture to reconcile masked reconstruction with task-specific supervision--and an MoE-augmented loss that adaptively routes features through specialized subnetworks. On industrial-scale benchmarks, it achieves +5.04% AUC and +8.28% KS over prior art under rigorous scaling. Moreover, its representations distill effectively into lightweight models, yielding +2.55% AUC and +4.85% KS under strict latency and interpretability constraints, while improving robustness to distribution shifts. Our work demonstrates that tabular data admits a foundation-model treatment--when its structural idiosyncrasies are respected.

Jianshuo Dong, Sheng Guo, Hao Wang et al.

Search agents connect LLMs to the Internet, enabling access to broader and more up-to-date information. However, unreliable search results may also pose safety threats to end users, establishing a new threat surface. In this work, we conduct two in-the-wild experiments to demonstrate both the prevalence of low-quality search results and their potential to misguide agent behaviors. To counter this threat, we introduce an automated red-teaming framework that is systematic, scalable, and cost-efficient, enabling lightweight and harmless safety assessments of search agents. Building on this framework, we construct the SafeSearch benchmark, which includes 300 test cases covering five categories of risks (e.g., misinformation and indirect prompt injection). Using this benchmark, we evaluate three representative search agent scaffolds, covering search workflow, tool-calling, and deep research, across 7 proprietary and 8 open-source backend LLMs. Our results reveal substantial vulnerabilities of LLM-based search agents: when exposed to unreliable websites, the highest ASR reached 90.5% for GPT-4.1-mini under a search workflow setting. Moreover, our analysis highlights the limited effectiveness of common defense practices, such as reminder prompting. This emphasizes the value of our framework in promoting transparency for safer agent development. Our codebase and test cases are publicly available: https://github.com/jianshuod/SafeSearch.

Min Yang, Zihan Jia, Zhilin Dai et al.

Efficient lightweight neural networks are with increasing attention due to their faster reasoning speed and easier deployment on mobile devices. However, existing video pre-trained models still focus on the common ViT architecture with high latency, and few works attempt to build efficient architecture on mobile devices. This paper bridges this gap by introducing temporal structural reparameterization into an efficient image-text model and training it on a large-scale high-quality video-text dataset, resulting in an efficient video-text model that can run on mobile devices with strong zero-shot classification and retrieval capabilities, termed as MobileViCLIP. In particular, in terms of inference speed on mobile devices, our MobileViCLIP-Small is 55.4x times faster than InternVideo2-L14 and 6.7x faster than InternVideo2-S14. In terms of zero-shot retrieval performance, our MobileViCLIP-Small obtains similar performance as InternVideo2-L14 and obtains 6.9\% better than InternVideo2-S14 on MSR-VTT. The code is available at https://github.com/MCG-NJU/MobileViCLIP.

Ziteng Gao, Limin Wang, Bing Han et al.

Traditional object detectors employ the dense paradigm of scanning over locations and scales in an image. The recent query-based object detectors break this convention by decoding image features with a set of learnable queries. However, this paradigm still suffers from slow convergence, limited performance, and design complexity of extra networks between backbone and decoder. In this paper, we find that the key to these issues is the adaptability of decoders for casting queries to varying objects. Accordingly, we propose a fast-converging query-based detector, named AdaMixer, by improving the adaptability of query-based decoding processes in two aspects. First, each query adaptively samples features over space and scales based on estimated offsets, which allows AdaMixer to efficiently attend to the coherent regions of objects. Then, we dynamically decode these sampled features with an adaptive MLP-Mixer under the guidance of each query. Thanks to these two critical designs, AdaMixer enjoys architectural simplicity without requiring dense attentional encoders or explicit pyramid networks. On the challenging MS COCO benchmark, AdaMixer with ResNet-50 as the backbone, with 12 training epochs, reaches up to 45.0 AP on the validation set along with 27.9 APs in detecting small objects. With the longer training scheme, AdaMixer with ResNeXt-101-DCN and Swin-S reaches 49.5 and 51.3 AP. Our work sheds light on a simple, accurate, and fast converging architecture for query-based object detectors. The code is made available at https://github.com/MCG-NJU/AdaMixer

Zelu Deng, Yujie Zhong, Sheng Guo et al.

This work aims at improving instance retrieval with self-supervision. We find that fine-tuning using the recently developed self-supervised (SSL) learning methods, such as SimCLR and MoCo, fails to improve the performance of instance retrieval. In this work, we identify that the learnt representations for instance retrieval should be invariant to large variations in viewpoint and background etc., whereas self-augmented positives applied by the current SSL methods can not provide strong enough signals for learning robust instance-level representations. To overcome this problem, we propose InsCLR, a new SSL method that builds on the \textit{instance-level} contrast, to learn the intra-class invariance by dynamically mining meaningful pseudo positive samples from both mini-batches and a memory bank during training. Extensive experiments demonstrate that InsCLR achieves similar or even better performance than the state-of-the-art SSL methods on instance retrieval. Code is available at https://github.com/zeludeng/insclr.

Zhenxi Zhu, Limin Wang, Sheng Guo et al.

The existing few-shot video classification methods often employ a meta-learning paradigm by designing customized temporal alignment module for similarity calculation. While significant progress has been made, these methods fail to focus on learning effective representations, and heavily rely on the ImageNet pre-training, which might be unreasonable for the few-shot recognition setting due to semantics overlap. In this paper, we aim to present an in-depth study on few-shot video classification by making three contributions. First, we perform a consistent comparative study on the existing metric-based methods to figure out their limitations in representation learning. Accordingly, we propose a simple classifier-based baseline without any temporal alignment that surprisingly outperforms the state-of-the-art meta-learning based methods. Second, we discover that there is a high correlation between the novel action class and the ImageNet object class, which is problematic in the few-shot recognition setting. Our results show that the performance of training from scratch drops significantly, which implies that the existing benchmarks cannot provide enough base data. Finally, we present a new benchmark with more base data to facilitate future few-shot video classification without pre-training. The code will be made available at https://github.com/MCG-NJU/FSL-Video.

Qiufu Li, Linlin Shen, Sheng Guo et al.

Though widely used in image classification, convolutional neural networks (CNNs) are prone to noise interruptions, i.e. the CNN output can be drastically changed by small image noise. To improve the noise robustness, we try to integrate CNNs with wavelet by replacing the common down-sampling (max-pooling, strided-convolution, and average pooling) with discrete wavelet transform (DWT). We firstly propose general DWT and inverse DWT (IDWT) layers applicable to various orthogonal and biorthogonal discrete wavelets like Haar, Daubechies, and Cohen, etc., and then design wavelet integrated CNNs (WaveCNets) by integrating DWT into the commonly used CNNs (VGG, ResNets, and DenseNet). During the down-sampling, WaveCNets apply DWT to decompose the feature maps into the low-frequency and high-frequency components. Containing the main information including the basic object structures, the low-frequency component is transmitted into the following layers to generate robust high-level features. The high-frequency components are dropped to remove most of the data noises. The experimental results show that %wavelet accelerates the CNN training, and WaveCNets achieve higher accuracy on ImageNet than various vanilla CNNs. We have also tested the performance of WaveCNets on the noisy version of ImageNet, ImageNet-C and six adversarial attacks, the results suggest that the proposed DWT/IDWT layers could provide better noise-robustness and adversarial robustness. When applying WaveCNets as backbones, the performance of object detectors (i.e., faster R-CNN and RetinaNet) on COCO detection dataset are consistently improved. We believe that suppression of aliasing effect, i.e. separation of low frequency and high frequency information, is the main advantages of our approach. The code of our DWT/IDWT layer and different WaveCNets are available at https://github.com/CVI-SZU/WaveCNet.

Guanting Liu, Yujie Zhong, Sheng Guo et al.

Differentiable architecture search (DAS) has made great progress in searching for high-performance architectures with reduced computational cost. However, DAS-based methods mainly focus on searching for a repeatable cell structure, which is then stacked sequentially in multiple stages to form the networks. This configuration significantly reduces the search space, and ignores the importance of connections between the cells. To overcome this limitation, in this paper, we propose a Hierarchical Differentiable Architecture Search (H-DAS) that performs architecture search both at the cell level and at the stage level. Specifically, the cell-level search space is relaxed so that the networks can learn stage-specific cell structures. For the stage-level search, we systematically study the architectures of stages, including the number of cells in each stage and the connections between the cells. Based on insightful observations, we design several search rules and losses, and mange to search for better stage-level architectures. Such hierarchical search space greatly improves the performance of the networks without introducing expensive search cost. Extensive experiments on CIFAR10 and ImageNet demonstrate the effectiveness of the proposed H-DAS. Moreover, the searched stage-level architectures can be combined with the cell structures searched by existing DAS methods to further boost the performance. Code is available at: https://github.com/MalongTech/research-HDAS

Sheng Guo, Weilin Huang, Xiao Zhang et al.

Large-scale image databases such as ImageNet have significantly advanced image classification and other visual recognition tasks. However much of these datasets are constructed only for single-label and coarse object-level classification. For real-world applications, multiple labels and fine-grained categories are often needed, yet very few such datasets exist publicly, especially those of large-scale and high quality. In this work, we contribute to the community a new dataset called iMaterialist Fashion Attribute (iFashion-Attribute) to address this problem in the fashion domain. The dataset is constructed from over one million fashion images with a label space that includes 8 groups of 228 fine-grained attributes in total. Each image is annotated by experts with multiple, high-quality fashion attributes. The result is the first known million-scale multi-label and fine-grained image dataset. We conduct extensive experiments and provide baseline results with modern deep Convolutional Neural Networks (CNNs). Additionally, we demonstrate models pre-trained on iFashion-Attribute achieve superior transfer learning performance on fashion related tasks compared with pre-training from ImageNet or other fashion datasets. Data is available at: https://github.com/visipedia/imat_fashion_comp

Sheng Guo, Weilin Huang, Haozhi Zhang et al.

We present a simple yet efficient approach capable of training deep neural networks on large-scale weakly-supervised web images, which are crawled raw from the Internet by using text queries, without any human annotation. We develop a principled learning strategy by leveraging curriculum learning, with the goal of handling a massive amount of noisy labels and data imbalance effectively. We design a new learning curriculum by measuring the complexity of data using its distribution density in a feature space, and rank the complexity in an unsupervised manner. This allows for an efficient implementation of curriculum learning on large-scale web images, resulting in a high-performance CNN model, where the negative impact of noisy labels is reduced substantially. Importantly, we show by experiments that those images with highly noisy labels can surprisingly improve the generalization capability of the model, by serving as a manner of regularization. Our approaches obtain state-of-the-art performance on four benchmarks: WebVision, ImageNet, Clothing-1M and Food-101. With an ensemble of multiple models, we achieved a top-5 error rate of 5.2% on the WebVision challenge for 1000-category classification. This result was the top performance by a wide margin, outperforming second place by a nearly 50% relative error rate. Code and models are available at: https://github.com/MalongTech/CurriculumNet .

Limin Wang, Sheng Guo, Weilin Huang et al.

Convolutional Neural Networks (CNNs) have made remarkable progress on scene recognition, partially due to these recent large-scale scene datasets, such as the Places and Places2. Scene categories are often defined by multi-level information, including local objects, global layout, and background environment, thus leading to large intra-class variations. In addition, with the increasing number of scene categories, label ambiguity has become another crucial issue in large-scale classification. This paper focuses on large-scale scene recognition and makes two major contributions to tackle these issues. First, we propose a multi-resolution CNN architecture that captures visual content and structure at multiple levels. The multi-resolution CNNs are composed of coarse resolution CNNs and fine resolution CNNs, which are complementary to each other. Second, we design two knowledge guided disambiguation techniques to deal with the problem of label ambiguity. (i) We exploit the knowledge from the confusion matrix computed on validation data to merge ambiguous classes into a super category. (ii) We utilize the knowledge of extra networks to produce a soft label for each image. Then the super categories or soft labels are employed to guide CNN training on the Places2. We conduct extensive experiments on three large-scale image datasets (ImageNet, Places, and Places2), demonstrating the effectiveness of our approach. Furthermore, our method takes part in two major scene recognition challenges, and achieves the second place at the Places2 challenge in ILSVRC 2015, and the first place at the LSUN challenge in CVPR 2016. Finally, we directly test the learned representations on other scene benchmarks, and obtain the new state-of-the-art results on the MIT Indoor67 (86.7\%) and SUN397 (72.0\%). We release the code and models at~\url{https://github.com/wanglimin/MRCNN-Scene-Recognition}.

Zhenhua Zou, Sheng Guo, Qiuyang Zhan et al.

The evolution of Large Language Models (LLMs) has shifted mobile computing from App-centric interactions to system-level autonomous agents. Current implementations predominantly rely on a "Screen-as-Interface" paradigm, which inherits structural vulnerabilities and conflicts with the mobile ecosystem's economic foundations. In this paper, we conduct a systematic security analysis of state-of-the-art mobile agents using Doubao Mobile Assistant as a representative case. We decompose the threat landscape into four dimensions - Agent Identity, External Interface, Internal Reasoning, and Action Execution - revealing critical flaws such as fake App identity, visual spoofing, indirect prompt injection, and unauthorized privilege escalation stemming from a reliance on unstructured visual data. To address these challenges, we propose Aura, an Agent Universal Runtime Architecture for a clean-slate secure agent OS. Aura replaces brittle GUI scraping with a structured, agent-native interaction model. It adopts a Hub-and-Spoke topology where a privileged System Agent orchestrates intent, sandboxed App Agents execute domain-specific tasks, and the Agent Kernel mediates all communication. The Agent Kernel enforces four defense pillars: (i) cryptographic identity binding via a Global Agent Registry; (ii) semantic input sanitization through a multilayer Semantic Firewall; (iii) cognitive integrity via taint-aware memory and plan-trajectory alignment; and (iv) granular access control with non-deniable auditing. Evaluation on MobileSafetyBench shows that, compared to Doubao, Aura improves low-risk Task Success Rate from roughly 75% to 94.3%, reduces high-risk Attack Success Rate from roughly 40% to 4.4%, and achieves near-order-of-magnitude latency gains. These results demonstrate Aura as a viable, secure alternative to the "Screen-as-Interface" paradigm.

Qiao Liang, Yuke Zhu, Chao Ge et al.

Tool-integrated reasoning (TIR) enables LLM agents to solve tasks through planning, tool use, and iterative revision, but outcome-only reinforcement learning in this setting suffers from sparse, delayed rewards and weak step-level credit assignment. In long-horizon TIR trajectories, an early irrecoverable mistake can determine success or failure, making it crucial to localize the first irrecoverable step and leverage it for fine-grained credit assignment. We propose Error-Localized Policy Optimization (ELPO), which localizes the first irrecoverable step via binary-search rollout trees under a fixed rollout budget, converts the resulting tree into stable learning signals through hierarchical advantage attribution, and applies error-localized adaptive clipping to strengthen corrective updates on the critical step and its suffix. Across TIR benchmarks in math, science QA, and code execution, ELPO consistently outperforms strong Agentic RL baselines under comparable sampling budgets, with additional gains in Pass@K and Major@K scaling, rollout ranking quality, and tool-call efficiency. Our code will be publicly released soon.

Yuke Zhu, Chi Xie, Shuang Liang et al.

Recent advances on Multi-modal Large Language Models have demonstrated that high-resolution image input is crucial for model capabilities, especially for fine-grained tasks. However, high-resolution images lead to a quadratic increase in the number of visual tokens input into LLMs, resulting in significant computational costs. Current work develop visual token compression methods to achieve efficiency improvements, often at the expense of performance. We argue that removing visual redundancy can simultaneously improve both efficiency and performance. We build a coarse-to-fine visual token compression method, with a vision-guided sampler for compressing redundant regions with low information density, and a text-guided sampler for selecting visual tokens that are strongly correlated with the user instructions.With these two modules, the proposed FocusLLaVA achieves improvements in both efficiency and performance. We validate the effectiveness of our approach on a wide range of evaluation datasets.

Qi Zhang, Shouqing Yang, Lirong Gao et al.

Large language models (LLMs) have demonstrated impressive capabilities in reasoning with the emergence of reasoning models like OpenAI-o1 and DeepSeek-R1. Recent research focuses on integrating reasoning capabilities into the realm of retrieval-augmented generation (RAG) via outcome-supervised reinforcement learning (RL) approaches, while the correctness of intermediate think-and-search steps is usually neglected. To address this issue, we design a process-level reward module to mitigate the unawareness of intermediate reasoning steps in outcome-level supervision without additional annotation. Grounded on this, we propose Learning to Think-and-Search (LeTS), a novel framework that hybridizes stepwise process reward and outcome-based reward to current RL methods for RAG. Extensive experiments demonstrate the generalization and inference efficiency of LeTS across various RAG benchmarks. In addition, these results reveal the potential of process- and outcome-level reward hybridization in boosting LLMs' reasoning ability via RL under other scenarios. The code will be released soon.

Yuke Zhu, Yumeng Ruan, Zihua Xiong et al.

Regression loss design is an essential topic for oriented object detection. Due to the periodicity of the angle and the ambiguity of width and height definition, traditional L1-distance loss and its variants have been suffered from the metric discontinuity and the square-like problem. As a solution, the distribution based methods show significant advantages by representing oriented boxes as distributions. Differing from exploited the Gaussian distribution to get analytical form of distance measure, we propose a novel oriented regression loss, Wasserstein Distance(EWD) loss, to alleviate the square-like problem. Specifically, for the oriented box(OBox) representation, we choose a specially-designed distribution whose probability density function is only nonzero over the edges. On this basis, we develop Wasserstein distance as the measure. Besides, based on the edge representation of OBox, the EWD loss can be generalized to quadrilateral and polynomial regression scenarios. Experiments on multiple popular datasets and different detectors show the effectiveness of the proposed method.

Yajiao Dai, Jun Li, Zhen Mei et al.

Intelligent fault diagnosis (IFD) plays a crucial role in ensuring the safe operation of industrial machinery and improving production efficiency. However, traditional supervised deep learning methods require a large amount of training data and labels, which are often located in different clients. Additionally, the cost of data labeling is high, making labels difficult to acquire. Meanwhile, differences in data distribution among clients may also hinder the model's performance. To tackle these challenges, this paper proposes a semi-supervised federated learning framework, SSFL-DCSL, which integrates dual contrastive loss and soft labeling to address data and label scarcity for distributed clients with few labeled samples while safeguarding user privacy. It enables representation learning using unlabeled data on the client side and facilitates joint learning among clients through prototypes, thereby achieving mutual knowledge sharing and preventing local model divergence. Specifically, first, a sample weighting function based on the Laplace distribution is designed to alleviate bias caused by low confidence in pseudo labels during the semi-supervised training process. Second, a dual contrastive loss is introduced to mitigate model divergence caused by different data distributions, comprising local contrastive loss and global contrastive loss. Third, local prototypes are aggregated on the server with weighted averaging and updated with momentum to share knowledge among clients. To evaluate the proposed SSFL-DCSL framework, experiments are conducted on two publicly available datasets and a dataset collected on motors from the factory. In the most challenging task, where only 10\% of the data are labeled, the proposed SSFL-DCSL can improve accuracy by 1.15% to 7.85% over state-of-the-art methods.

Feng Wei, Zhenbo Chen, Zhenghong Hao et al.

Most dialogue systems in real world rely on predefined intents and answers for QA service, so discovering potential intents from large corpus previously is really important for building such dialogue services. Considering that most scenarios have few intents known already and most intents waiting to be discovered, we focus on semi-supervised text clustering and try to make the proposed method benefit from labeled samples for better overall clustering performance. In this paper, we propose Deep Contrastive Semi-supervised Clustering (DCSC), which aims to cluster text samples in a semi-supervised way and provide grouped intents to operation staff. To make DCSC fully utilize the limited known intents, we propose a two-stage training procedure for DCSC, in which DCSC will be trained on both labeled samples and unlabeled samples, and achieve better text representation and clustering performance. We conduct experiments on two public datasets to compare our model with several popular methods, and the results show DCSC achieve best performance across all datasets and circumstances, indicating the effect of the improvements in our work.

Haoxian Tan, Sheng Guo, Yujie Zhong et al.

Differentiable architecture search is prevalent in the field of NAS because of its simplicity and efficiency, where two paradigms, multi-path algorithms and single-path methods, are dominated. Multi-path framework (e.g. DARTS) is intuitive but suffers from memory usage and training collapse. Single-path methods (e.g.GDAS and ProxylessNAS) mitigate the memory issue and shrink the gap between searching and evaluation but sacrifice the performance. In this paper, we propose a conceptually simple yet efficient method to bridge these two paradigms, referred as Mutually-aware Sub-Graphs Differentiable Architecture Search (MSG-DAS). The core of our framework is a differentiable Gumbel-TopK sampler that produces multiple mutually exclusive single-path sub-graphs. To alleviate the severer skip-connect issue brought by multiple sub-graphs setting, we propose a Dropblock-Identity module to stabilize the optimization. To make best use of the available models (super-net and sub-graphs), we introduce a memory-efficient super-net guidance distillation to improve training. The proposed framework strikes a balance between flexible memory usage and searching quality. We demonstrate the effectiveness of our methods on ImageNet and CIFAR10, where the searched models show a comparable performance as the most recent approaches.

Yujie Zhong, Zelu Deng, Sheng Guo et al.

Region Proposal Network (RPN) provides strong support for handling the scale variation of objects in two-stage object detection. For one-stage detectors which do not have RPN, it is more demanding to have powerful sub-networks capable of directly capturing objects of unknown sizes. To enhance such capability, we propose an extremely efficient neural architecture search method, named Fast And Diverse (FAD), to better explore the optimal configuration of receptive fields and convolution types in the sub-networks for one-stage detectors. FAD consists of a designed search space and an efficient architecture search algorithm. The search space contains a rich set of diverse transformations designed specifically for object detection. To cope with the designed search space, a novel search algorithm termed Representation Sharing (RepShare) is proposed to effectively identify the best combinations of the defined transformations. In our experiments, FAD obtains prominent improvements on two types of one-stage detectors with various backbones. In particular, our FAD detector achieves 46.4 AP on MS-COCO (under single-scale testing), outperforming the state-of-the-art detectors, including the most recent NAS-based detectors, Auto-FPN (searched for 16 GPU-days) and NAS-FCOS (28 GPU-days), while significantly reduces the search cost to 0.6 GPU-days. Beyond object detection, we further demonstrate the generality of FAD on the more challenging instance segmentation, and expect it to benefit more tasks.

Qiufu Li, Linlin Shen, Sheng Guo et al.

Convolutional Neural Networks (CNNs) are generally prone to noise interruptions, i.e., small image noise can cause drastic changes in the output. To suppress the noise effect to the final predication, we enhance CNNs by replacing max-pooling, strided-convolution, and average-pooling with Discrete Wavelet Transform (DWT). We present general DWT and Inverse DWT (IDWT) layers applicable to various wavelets like Haar, Daubechies, and Cohen, etc., and design wavelet integrated CNNs (WaveCNets) using these layers for image classification. In WaveCNets, feature maps are decomposed into the low-frequency and high-frequency components during the down-sampling. The low-frequency component stores main information including the basic object structures, which is transmitted into the subsequent layers to extract robust high-level features. The high-frequency components, containing most of the data noise, are dropped during inference to improve the noise-robustness of the WaveCNets. Our experimental results on ImageNet and ImageNet-C (the noisy version of ImageNet) show that WaveCNets, the wavelet integrated versions of VGG, ResNets, and DenseNet, achieve higher accuracy and better noise-robustness than their vanilla versions.

Chulun Zhou, Liangyu Chen, Jiachen Liu et al.

Unsupervised style transfer aims to change the style of an input sentence while preserving its original content without using parallel training data. In current dominant approaches, owing to the lack of fine-grained control on the influence from the target style,they are unable to yield desirable output sentences. In this paper, we propose a novel attentional sequence-to-sequence (Seq2seq) model that dynamically exploits the relevance of each output word to the target style for unsupervised style transfer. Specifically, we first pretrain a style classifier, where the relevance of each input word to the original style can be quantified via layer-wise relevance propagation. In a denoising auto-encoding manner, we train an attentional Seq2seq model to reconstruct input sentences and repredict word-level previously-quantified style relevance simultaneously. In this way, this model is endowed with the ability to automatically predict the style relevance of each output word. Then, we equip the decoder of this model with a neural style component to exploit the predicted wordlevel style relevance for better style transfer. Particularly, we fine-tune this model using a carefully-designed objective function involving style transfer, style relevance consistency, content preservation and fluency modeling loss terms. Experimental results show that our proposed model achieves state-of-the-art performance in terms of both transfer accuracy and content preservation.

Shiwen Zhang, Sheng Guo, Limin Wang et al.

In this work, we propose Knowledge Integration Networks (referred as KINet) for video action recognition. KINet is capable of aggregating meaningful context features which are of great importance to identifying an action, such as human information and scene context. We design a three-branch architecture consisting of a main branch for action recognition, and two auxiliary branches for human parsing and scene recognition which allow the model to encode the knowledge of human and scene for action recognition. We explore two pre-trained models as teacher networks to distill the knowledge of human and scene for training the auxiliary tasks of KINet. Furthermore, we propose a two-level knowledge encoding mechanism which contains a Cross Branch Integration (CBI) module for encoding the auxiliary knowledge into medium-level convolutional features, and an Action Knowledge Graph (AKG) for effectively fusing high-level context information. This results in an end-to-end trainable framework where the three tasks can be trained collaboratively, allowing the model to compute strong context knowledge efficiently. The proposed KINet achieves the state-of-the-art performance on a large-scale action recognition benchmark Kinetics-400, with a top-1 accuracy of 77.8%. We further demonstrate that our KINet has strong capability by transferring the Kinetics-trained model to UCF-101, where it obtains 97.8% top-1 accuracy.

Shiwen Zhang, Sheng Guo, Weilin Huang et al.

Most existing 3D CNNs for video representation learning are clip-based methods, and thus do not consider video-level temporal evolution of spatio-temporal features. In this paper, we propose Video-level 4D Convolutional Neural Networks, referred as V4D, to model the evolution of long-range spatio-temporal representation with 4D convolutions, and at the same time, to preserve strong 3D spatio-temporal representation with residual connections. Specifically, we design a new 4D residual block able to capture inter-clip interactions, which could enhance the representation power of the original clip-level 3D CNNs. The 4D residual blocks can be easily integrated into the existing 3D CNNs to perform long-range modeling hierarchically. We further introduce the training and inference methods for the proposed V4D. Extensive experiments are conducted on three video recognition benchmarks, where V4D achieves excellent results, surpassing recent 3D CNNs by a large margin.

Weifeng Ge, Sheng Guo, Weilin Huang et al.

Weakly-supervised instance segmentation aims to detect and segment object instances precisely, given imagelevel labels only. Unlike previous methods which are composed of multiple offline stages, we propose Sequential Label Propagation and Enhancement Networks (referred as Label-PEnet) that progressively transform image-level labels to pixel-wise labels in a coarse-to-fine manner. We design four cascaded modules including multi-label classification, object detection, instance refinement and instance segmentation, which are implemented sequentially by sharing the same backbone. The cascaded pipeline is trained alternatively with a curriculum learning strategy that generalizes labels from high-level images to low-level pixels gradually with increasing accuracy. In addition, we design a proposal calibration module to explore the ability of classification networks to find key pixels that identify object parts, which serves as a post validation strategy running in the inverse order. We evaluate the efficiency of our Label-PEnet in mining instance masks on standard benchmarks: PASCAL VOC 2007 and 2012. Experimental results show that Label-PEnet outperforms the state-of-the-art algorithms by a clear margin, and obtains comparable performance even with the fully-supervised approaches.

Spyridon Bakas, Mauricio Reyes, Andras Jakab et al.

Gliomas are the most common primary brain malignancies, with different degrees of aggressiveness, variable prognosis and various heterogeneous histologic sub-regions, i.e., peritumoral edematous/invaded tissue, necrotic core, active and non-enhancing core. This intrinsic heterogeneity is also portrayed in their radio-phenotype, as their sub-regions are depicted by varying intensity profiles disseminated across multi-parametric magnetic resonance imaging (mpMRI) scans, reflecting varying biological properties. Their heterogeneous shape, extent, and location are some of the factors that make these tumors difficult to resect, and in some cases inoperable. The amount of resected tumor is a factor also considered in longitudinal scans, when evaluating the apparent tumor for potential diagnosis of progression. Furthermore, there is mounting evidence that accurate segmentation of the various tumor sub-regions can offer the basis for quantitative image analysis towards prediction of patient overall survival. This study assesses the state-of-the-art machine learning (ML) methods used for brain tumor image analysis in mpMRI scans, during the last seven instances of the International Brain Tumor Segmentation (BraTS) challenge, i.e., 2012-2018. Specifically, we focus on i) evaluating segmentations of the various glioma sub-regions in pre-operative mpMRI scans, ii) assessing potential tumor progression by virtue of longitudinal growth of tumor sub-regions, beyond use of the RECIST/RANO criteria, and iii) predicting the overall survival from pre-operative mpMRI scans of patients that underwent gross total resection. Finally, we investigate the challenge of identifying the best ML algorithms for each of these tasks, considering that apart from being diverse on each instance of the challenge, the multi-institutional mpMRI BraTS dataset has also been a continuously evolving/growing dataset.

Sheng Guo, Weilin Huang, Limin Wang et al.

Convolutional neural networks (CNN) have recently achieved remarkable successes in various image classification and understanding tasks. The deep features obtained at the top fully-connected layer of the CNN (FC-features) exhibit rich global semantic information and are extremely effective in image classification. On the other hand, the convolutional features in the middle layers of the CNN also contain meaningful local information, but are not fully explored for image representation. In this paper, we propose a novel Locally-Supervised Deep Hybrid Model (LS-DHM) that effectively enhances and explores the convolutional features for scene recognition. Firstly, we notice that the convolutional features capture local objects and fine structures of scene images, which yield important cues for discriminating ambiguous scenes, whereas these features are significantly eliminated in the highly-compressed FC representation. Secondly, we propose a new Local Convolutional Supervision (LCS) layer to enhance the local structure of the image by directly propagating the label information to the convolutional layers. Thirdly, we propose an efficient Fisher Convolutional Vector (FCV) that successfully rescues the orderless mid-level semantic information (e.g. objects and textures) of scene image. The FCV encodes the large-sized convolutional maps into a fixed-length mid-level representation, and is demonstrated to be strongly complementary to the high-level FC-features. Finally, both the FCV and FC-features are collaboratively employed in the LSDHM representation, which achieves outstanding performance in our experiments. It obtains 83.75% and 67.56% accuracies respectively on the heavily benchmarked MIT Indoor67 and SUN397 datasets, advancing the stat-of-the-art substantially.

Limin Wang, Zhe Wang, Sheng Guo et al.

Event recognition from still images is one of the most important problems for image understanding. However, compared with object recognition and scene recognition, event recognition has received much less research attention in computer vision community. This paper addresses the problem of cultural event recognition in still images and focuses on applying deep learning methods on this problem. In particular, we utilize the successful architecture of Object-Scene Convolutional Neural Networks (OS-CNNs) to perform event recognition. OS-CNNs are composed of object nets and scene nets, which transfer the learned representations from the pre-trained models on large-scale object and scene recognition datasets, respectively. We propose four types of scenarios to explore OS-CNNs for event recognition by treating them as either "end-to-end event predictors" or "generic feature extractors". Our experimental results demonstrate that the global and local representations of OS-CNNs are complementary to each other. Finally, based on our investigation of OS-CNNs, we come up with a solution for the cultural event recognition track at the ICCV ChaLearn Looking at People (LAP) challenge 2015. Our team secures the third place at this challenge and our result is very close to the best performance.

Limin Wang, Sheng Guo, Weilin Huang et al.

VGGNets have turned out to be effective for object recognition in still images. However, it is unable to yield good performance by directly adapting the VGGNet models trained on the ImageNet dataset for scene recognition. This report describes our implementation of training the VGGNets on the large-scale Places205 dataset. Specifically, we train three VGGNet models, namely VGGNet-11, VGGNet-13, and VGGNet-16, by using a Multi-GPU extension of Caffe toolbox with high computational efficiency. We verify the performance of trained Places205-VGGNet models on three datasets: MIT67, SUN397, and Places205. Our trained models achieve the state-of-the-art performance on these datasets and are made public available.

Sheng Guo, Weilin Huang, Yu Qiao

Image representation and classification are two fundamental tasks towards multimedia content retrieval and understanding. The idea that shape and texture information (e.g. edge or orientation) are the key features for visual representation is ingrained and dominated in current multimedia and computer vision communities. A number of low-level features have been proposed by computing local gradients (e.g. SIFT, LBP and HOG), and have achieved great successes on numerous multimedia applications. In this paper, we present a simple yet efficient local descriptor for image classification, referred as Local Color Contrastive Descriptor (LCCD), by leveraging the neural mechanisms of color contrast. The idea originates from the observation in neural science that color and shape information are linked inextricably in visual cortical processing. The color contrast yields key information for visual color perception and provides strong linkage between color and shape. We propose a novel contrastive mechanism to compute the color contrast in both spatial location and multiple channels. The color contrast is computed by measuring \emph{f}-divergence between the color distributions of two regions. Our descriptor enriches local image representation with both color and contrast information. We verified experimentally that it can compensate strongly for the shape based descriptor (e.g. SIFT), while keeping computationally simple. Extensive experimental results on image classification show that our descriptor improves the performance of SIFT substantially by combinations, and achieves the state-of-the-art performance on three challenging benchmark datasets. It improves recent Deep Learning model (DeCAF) [1] largely from the accuracy of 40.94% to 49.68% in the large scale SUN397 database. Codes for the LCCD will be available.