检索结果-内蒙古大学图书馆

Densely activated self-attention for semantic segmentation

Pattern Recognition 2025年

作者： Liwen Xiao Wenze Liu Zhicheng Wang Yiran Wang Zhiyu Pan Hao Lu Zhiguo Cao Key Laboratory of Image Processing and Intelligent Control Ministry of Education School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan 430074 China

In semantic segmentation, pixels often share the same mask labels across a vast region. However, in recent prevalent transformer-based models, predictions frequently suffer from incompleteness or discontinuities. The dilemma is caused by sparse activation of vanilla self-attention during feature extraction. During the vanilla self-attention, each query over-focuses on a small number of relevant keys but neglects numerous keys sharing the same category with it, restricting the capture of universal feature representation for its category. Such sparsely activated self-attention will further cause unignorable feature differences among tokens sharing the same class in feature maps, introducing noise on final predictions. To reduce such differences, we propose the Densely Activated self-attention Module (DAM), a novel pluggable module designed to generate densely activated self-attention. Inserted after the encoder, it encourages each query to attend to a broader range of keys, obtaining more consistent features. Experimental results on three widely used benchmarks with six different baselines demonstrate that DAM consistently improves performance with a negligible increase in parameters and FLOPs. Our work provides a new perspective on the behavior of self-attention in semantic segmentation.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Reversible adversarial information hiding based on the interpretation of neural network

引用

Digital Signal processing: A Review Journal 2025年 165卷

作者： Li, Ruiping Wang, Xi Cui, Qingchen Li, Ming Information Construction and Management Office Henan Normal University Xinxiang453007 China School of Artificial Intelligence and Software Engineering Nanyang Normal University Nanyang473061 China Henan Engineering Research Center of Intelligent Processing for Big Data of Digital Image Henan Nanyang473000 China College of Information Engineering Zhoukou Vocational College of Arts and Science Zhoukou466000 China College of Computer and Information Engineering Henan Normal University Xinxiang453007 China Key Laboratory of Artificial Intelligence and Personalized Learning in Education of Henan Province Xinxiang453007 China

The emerging technology of adversarial information hiding can generate adversarial example by embedding useful information instead of meaningless noise into the host image. The obtained image can deceive classification models and therefore equip the function of privacy protection. However, existing research mainly focuses on the effectiveness of attack rather than preserving the integrity of the protected image. It cannot meet the requirements in the fields such as medical imaging, financial transactions, and copyright protection where users' raw data should not be damaged. Therefore, we propose a novel reversible adversarial information hiding based on interpretability of neural networks. The Grad-CAM-generated heatmap is employed to identify a minimal set of high-impact pixels for embedding, ensuring that minor modifications can induce significant misclassification. Then, the user-defined secret bits are embedded into the identified pixels by using difference expansion. After extraction, the original image can be perfectly restored. The technologies of adversarial example and reversible information hiding are combined to accommodate wider applications. The proposed method is tested on CIFAR-10 with three different neural architectures (NiN, AlexNet, ResNet). Experimental results show that the proposed method can completely restore the cover image while ensuring the extraction of the embedded data and misleading the neural network. © 2025 Elsevier Inc.

关键词： Adversarial attacks Adversarial information hiding Neural network interpretability Reversibility

来源：评论

学校读者我要写书评

暂无评论

Domain generalization for mammographic image analysis with contrastive learning

引用

Computers in Biology and Medicine 2025年 185卷 109455-109455页

作者： Li, Zheren Cui, Zhiming Zhang, Lichi Wang, Sheng Lei, Chenjin Ouyang, Xi Chen, Dongdong Zhao, Xiangyu Liu, Chunling Liu, Zaiyi Gu, Yajia Shen, Dinggang Cheng, Jie-Zhi Shanghai United Imaging Intelligence Co. Ltd. Shanghai200030 China The School of Biomedical Engineering Shanghai Jiao Tong University Shanghai200240 China The School of Biomedical Engineering ShanghaiTech University Shanghai201210 China The Department of Radiology Guangdong Provincial People's Hospital Southern Medical University Guangzhou510080 China Guangdong Provincial Key Laboratory of Artificial Intelligence in Medical Image Analysis and Application Guangzhou510080 China The Department of Radiology Fudan University Shanghai Cancer Center 270 Dongan Road Shanghai200032 China

The deep learning technique has been shown to be effectively addressed several image analysis tasks in the computer-aided diagnosis scheme for mammography. The training of an efficacious deep learning model requires large data with diverse styles and qualities. The diversity of data often comes from the use of various scanners of vendors. But, in practice, it is impractical to collect a sufficient amount of diverse data for training. To this end, a novel contrastive learning, MSVCL+, is developed to equip the deep learning models with better style generalizability. Specifically, the multi-style and multi-view unsupervised self-learning scheme is carried out to seek robust feature embedding against style diversity as a pretrained model. Afterward, the pretrained network is further fine-tuned to the downstream tasks, e.g., mass detection, matching, BI-RADS rating, and breast density classification. The proposed method has been evaluated extensively and rigorously with mammograms from various vendor style domains and several public datasets. The experimental results suggest that the proposed domain generalization method can effectively improve performance of four mammographic image tasks on the data from both seen and unseen domains, and outperform many state-of-the-art (SOTA) generalization methods. © 2024

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Real-time Multi-person Eyeblink Detection in the Wild for Untrimmed Video

arXiv

引用

arXiv 2023年

作者： Zeng, Wenzheng Xiao, Yang Wei, Sicheng Gan, Jinfang Zhang, Xintao Cao, Zhiguo Fang, Zhiwen Zhou, Joey Tianyi Key Laboratory of Image Processing and Intelligent Control Ministry of Education School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China School of Biomedical Engineering Southern Medical University Guangzhou510515 China Department of Rehabilitation Medicine Zhujiang Hospital Southern Medical University Guangzhou510280 China Singapore Singapore

Real-time eyeblink detection in the wild can widely serve for fatigue detection, face anti-spoofing, emotion analysis, etc. The existing research efforts generally focus on single-person cases towards trimmed video. However, multi-person scenario within untrimmed videos is also important for practical applications, which has not been well concerned yet. To address this, we shed light on this research field for the first time with essential contributions on dataset, theory, and practices. In particular, a large-scale dataset termed MPEblink that involves 686 untrimmed videos with 8748 eyeblink events is proposed under multi-person conditions. The samples are captured from unconstrained films to reveal "in the wild" characteristics. Meanwhile, a real-time multi-person eyeblink detection method is also proposed. Being different from the existing counterparts, our proposition runs in a one-stage spatio-temporal way with end-to-end learning capacity. Specifically, it simultaneously addresses the sub-tasks of face detection, face tracking, and human instance-level eyeblink detection. This paradigm holds 2 main advantages: (1) eyeblink features can be facilitated via the face's global context (e.g., head pose and illumination condition) with joint optimization and interaction, and (2) addressing these sub-tasks in parallel instead of sequential manner can save time remarkably to meet the real-time running requirement. Experiments on MPEblink verify the essential challenges of real-time multi-person eyeblink detection in the wild for untrimmed video. Our method also outperforms existing approaches by large margins and with a high inference speed. Copyright © 2023, The Authors. All rights reserved.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

A2J-Transformer: Anchor-to-Joint Transformer Network for 3D Interacting Hand Pose Estimation from a Single RGB image

A2J-Transformer: Anchor-to-Joint Transformer Network for 3D ...

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Changlong Jiang Yang Xiao Cunlin Wu Mingyang Zhang Jinghong Zheng Zhiguo Cao Joey Tianyi Zhou Key Laboratory of Image Processing and Intelligent Control Ministry of Education School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China Alibaba Group Centre for Frontier AI Research Agency for Science Technology and Research (A*STAR) Singapore Institute of High Performance Computing Agency for Science Technology and Research (A*STAR) Singapore

3D interacting hand pose estimation from a single RGB image is a challenging task, due to serious self-occlusion and inter-occlusion towards hands, confusing similar appearance patterns between 2 hands, ill-posed joint position mapping from 2D to 3D, etc.. To address these, we propose to extend A2J-the state-of-the-art depth-based 3D single hand pose estimation method-to RGB domain under interacting hand condition. Our key idea is to equip A2J with strong local-global aware ability to well capture interacting hands' local fine details and global articulated clues among joints jointly. To this end, A2J is evolved under Transformer's non-local encoding-decoding framework to build A2J- Transformer. It holds 3 main advantages over A2J. First, self-attention across local anchor points is built to make them global spatial context aware to better capture joints' articulation clues for resisting occlusion. Secondly, each anchor point is regarded as learnable query with adaptive feature learning for facilitating pattern fitting capacity, instead of having the same local representation with the others. Last but not least, anchor point locates in 3D space instead of 2D as in A2J, to leverage 3D pose prediction. Experiments on challenging InterHand 2.6M demonstrate that, A2J-Transformer can achieve state-of-the-art model-free performance (3.38mm MPJPE advancement in 2-hand case) and can also be applied to depth domain with strong generalization. The code is avaliable at https://***/ChanglongJiangGit/A2J-Transformer.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Dual-Path Supplemental Information Learning Architecture for Breast Cancer Ki-67 Status Prediction in T2w MRI

A Dual-Path Supplemental Information Learning Architecture f...

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Wentian Cai Yulin Cheng Ying Gao Weixiao Liu Xinyan Xie Xiongwen Luo Weixian Yang Zaiyi Liu Changhong Liang School of Computer Science and Engineering South China University of Technology Guangzhou China Guangdong Provincial Key Laboratory of Artificial Intelligence in Medical Image Analysis and Application Guangdong Provincial People’s Hospital Guangdong Academy of Medical Sciences Guangzhou China Department of Radiology The First Affiliated Hospital of Jinan University Guangzhou China

In this paper, we propose a Dual-path Supplemental Information Learning Architecture (DSILA) for predicting breast cancer Ki-67 status based on T2-weighted (T2w) magnetic resonance imaging (MRI). DSILA consists of two components: 1) a transfer network with multi-scale feature selection strategy to obtain generic multi-scale features most relative to target, 2) a supplemental learning network with a large receptive field and channel-level attention to mine scenario-related semantic information. A regulation item – Aspect Overlap Loss (AOL), is further added to force the supplemental learning network to pay more attention to the regions overlooked by the transfer network. The experimental results tested on the collected T2w MRI breast cancer Ki-67 dataset show that DSILA outperforms state-of-the-art techniques among all adopted evaluation metrics, even achieving 0.85 in Area under the Receiver Operating Characteristic Curve (AUC).

关键词：

来源：评论

学校读者我要写书评

暂无评论

Parametric Design Optimization of a Universal Supernumerary Robotic Limb

Parametric Design Optimization of a Universal Supernumerary ...

引用

International Symposium on Micromechatronics and Human Science (MHS)

作者： Jun Huo Bo Yang Hongge Ru Jian Huang Key Laboratory of Ministry of Education for Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology (HUST) Wuhan China

ISBN: (纸本)9781665407748

It is a positive trend for hemiplegia with wearable robots in rehabilitation training. Recently, wearable Supernumerary Robotic Limb (SRL) is rising to a hot spot. The difficulty in modeling SRL for hemiplegia is how to make the SRL mechanism match the human upper and lower limbs' size and function simultaneously. In this paper, a simplified model of a four Degree of Freedoms (DOFs) universal SRL (USRL) is introduced. Based on workspace similarity, which is evaluated by Jaccard Index (JI), we establish a multi-object optimization (MOO) model. By applying the Particle Swarm Optimization (PSO) algorithm, we have found the optimal SRL mechanism parameters that meet the requirement of the human upper limb and the cane simultaneously. Meanwhile, a few impact factors are discussed briefly in the present proposal. The simulation results show that the USRL has a sound match with the human and could assist the hemiplegia subject as a supplemental limb.

关键词： Training Simulation Wearable robots Market research Manufacturing Indexes Proposals

来源：评论

学校读者我要写书评

暂无评论

Contamination-resilient anomaly detection via adversarial learning on partially-observed normal and anomalous data 24

Contamination-resilient anomaly detection via adversarial le...

引用

Proceedings of the 41st International Conference on Machine Learning

作者： Wenxi Lv Qinliang Su Hai Wan Hongteng Xu Wenchao Xu School of Computer Science and Engineering Sun Yat-sen University Guangzhou China School of Computer Science and Engineering Sun Yat-sen University Guangzhou China and Guangdong Key Laboratory of Big Data Analysis and Processing Guangzhou China Gaoling School of Artifical Intelligence Renmin University of China Beijing China Department of Computing The Hong Kong Polytechnic University Hong Kong SAR

Many existing anomaly detection methods assume the availability of a large-scale normal dataset. But for many applications, limited by resources, removing all anomalous samples from a large unlabeled dataset is unrealistic, resulting in contaminated datasets. To detect anomalies accurately under such scenarios, from the probabilistic perspective, the key question becomes how to learn the normal-data distribution from a contaminated dataset. To this end, we propose to collect two additional small datasets that are comprised of partially-observed normal and anomaly samples, and then use them to help learn the distribution under an adversarial learning scheme. We prove that under some mild conditions, the proposed method is able to learn the correct normal-data distribution. Then, we consider the overfitting issue caused by the small size of the two additional datasets, and a correctness-guaranteed flipping mechanism is further developed to alleviate it. Theoretical results under incomplete observed anomaly types are also presented. Extensive experimental results demonstrate that our method outperforms representative baselines when detecting anomalies under contaminated datasets.

关键词：

来源：评论

学校读者我要写书评

暂无评论

SeaConvNeXt:A Lightweight Two-Branch Network Architecture for Efficient Prediction of Specific IHC Proteins and Antigens on Hematoxylin and Eosin(H&E)images

引用

Big Data Mining and Analytics 2024年第4期7卷 1212-1236页

作者： Yuli Chen Guoping Chen Guoying Shi Yao Zhou Jiayang Bai Germán Corredor Cheng Lu Xiujuan Lei School of Computer Science Shaanxi Normal UniversityXi’an 710119China Department of Pathology Shaanxi Provincial Hospital of Traditional Chinese MedicineXi’an 710003China Wallace H.Coulter Department of Biomedical Engineering Emory University and Georgia Institute of TechnologyAtlanta 30322GAUSAand also with Joseph Maxwell Cleland Atlanta VA Medical CenterDecatur 30033GAUSA Department of Radiology and Medical Research Institute Guangdong Provincial People’s Hospital(Guangdong Academy of Medical Sciences)Southern Medical UniversityGuangzhou 510080Chinaand also with Guangdong Provincial Key Laboratory of Artificial Intelligence in Medical Image Analysis and ApplicationGuangzhou 510080China

Immunohistochemistry(IHC)is a vital technique for detecting specific proteins and antigens in tissue sections using antibodies,aiding in the analysis of tumor growth and ***,IHC is costly and time-consuming,making it challenging to implement on a large *** address this issue,we introduce a method that enables virtual IHC staining directly on Hematoxylin and Eosin(H&E)***,we have developed a novel registration technique,called Bi-stage Registration based on density Clustering(BiReC),to enhance the registration efficiency between H&E and IHC *** method involves automatically generating numerous Regions Of Interest(ROI)labels on the H&E image for model training,with the labels being determined by the intensity of IHC ***,we propose a novel two-branch network architecture,called SeaConvNeXt,which integrates a lightweight Squeeze-Enhanced Axial(SEA)attention mechanism to efficiently extract and fuse multi-level local and global features from H&E images for direct prediction of specific proteins and *** SeaConvNeXt consists of a ConvNeXt branch and a global fusion *** ConvNeXt branch extracts multi-level local features at four stages,while the global fusion branch,including an SEA Transformer module and three global blocks,is designed for global feature extraction and multiple feature *** experiments demonstrate that SeaConvNeXt outperforms current state-of-the-art methods on two public datasets with corresponding IHC and H&E images,achieving an AUC of 90.7%on the HER2SC dataset and 82.5%on the CRC *** results suggest that SeaConvNeXt has great potential for predicting virtual IHC staining on H&E images.

关键词： Immunohistochemistry(IHC) Bi-stage Registration based on density Clustering(BiReC) automatic label generation SeaConvNeXt attention mechanism multi-level local and global features virtual IHC staning prediction

来源：评论

学校读者我要写书评

暂无评论

NavCoT: Boosting LLM-Based Vision-and-Language Navigation via Learning Disentangled Reasoning

引用

IEEE Transactions on Pattern analysis and Machine intelligence 2025年第7期47卷 5945-5957页

作者： Bingqian Lin Yunshuang Nie Ziming Wei Jiaqi Chen Shikui Ma Jianhua Han Hang Xu Xiaojun Chang Xiaodan Liang Shenzhen Campus Sun Yat-sen University Shenzhen China Shanghai Jiao Tong University Shanghai China University of Hong Kong Pok Fu Lam Hong Kong Dataa Robotics Company Beijing China Huawei Noah's Ark Lab Shanghai China School of Information Science and Technology University of Science and Technology of China Hefei China Department of Computer Vision Mohamed bin Zayed University of Artificial Intelligence (MBZUAI) Abu Dhabi UAE Peng Cheng Laboratory Shenzhen China Guangdong Key Laboratory of Big Data Analysis and Processing Guangzhou China

Vision-and-Language Navigation (VLN), as a crucial research problem of Embodied AI, requires an embodied agent to navigate through complex 3D environments following natural language instructions. Recent research has highlighted the promising capacity of large language models (LLMs) in VLN by improving navigational reasoning accuracy and interpretability. However, their predominant use in an offline manner usually suffers from substantial domain gap between the VLN task and the LLM training corpus. This paper proposes a novel strategy called Nav igational C hain- o f- T hought (NavCoT), where we fulfill parameter-efficient in-domain training to enable self-guided navigational decision, leading to a significant mitigation of the domain gap in a cost-effective manner. Specifically, at each timestep, the LLM is prompted to forecast the navigational chain-of-thought by: 1) acting as a world model to imagine the next observation according to the instruction, 2) selecting the candidate observation that best aligns with the imagination, and 3) determining the action based on the reasoning from the prior steps. In this way, the action prediction can be effectively simplified benefiting from the disentangled reasoning. Through constructing formalized labels for training, the LLM can learn to generate desired and reasonable chain-of-thought outputs for improving the action decision. Experimental results across various training settings and popular VLN benchmarks (e.g., Room-to-Room (R2R), Room-across-Room (RxR), Room-for-Room (R4R)) show the significant superiority of NavCoT over the direct action prediction variants. Through simple parameter-efficient finetuning, our NavCoT outperforms a recent GPT4-based approach with $\sim$ 7% relative improvement on the R2R dataset. We believe that NavCoT will help unlock more task-adaptive and scalable LLM-based embodied agents, which are helpful for developing real-world robotics applications.

关键词： Navigation Cognition Training Scalability Glass Planning Large language models History Electronic mail Visualization

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：