检索结果-内蒙古大学图书馆

A Unified Open Adapter for Open-World Noisy Label Learning: Data-Centric and Learning-Based Insights

IEEE Transactions on Circuits and Systems for Video Technology 2025年

作者： Zong, Chen-Chen Yang, Peng-Hui Xie, Ming-Kun Huang, Sheng-Jun Nanjing University of Aeronautics and Astronautics MIIT Key Laboratory of Pattern Analysis and Machine Intelligence Collaborative Innovation Center of Novel Software Technology and Industrialization College of Computer Science and Technology Nanjing211106 China Nanyang Technological University School of Computer Science and Engineering 639798 Singapore Tokyo103-0027 Japan

Noisy label learning (NLL) in open-world scenarios poses a novel challenge due to the presence of noisy data from both known and unknown classes. Most existing methods operate under the closed-set assumption, rendering them vulnerable to open-set noise, which significantly degrades their performance. While some approaches attempt to mitigate the impact of open-set examples, they struggle to learn effective discriminative representations for them, leading to unsatisfactory recognition performance. To address these issues, we propose a unified Open Adapter (OpenAda) that identifies open-set noise from both data-centric and learning-based perspectives, and can be easily integrated into mainstream NLL methods to improve their performance and robustness. Specifically, the data-centric part leverages label clusterability to sequentially identify basic clean and basic open-set examples both with high neighbor agreement. The learning-based part integrates one-vs-all classifiers with a progressive open disambiguation strategy to learn a reliable "inlier vs. outlier" boundary for each class. This enables the model to detect challenging open-set examples that partially overlap in the representation space with closed-set ones. Extensive experiments on synthetic and real-world datasets validate the superiority of our approach. Notably, with minor modifications, DivideMix with OpenAda achieves performance improvements of 9.31% and 18.26% on the open-world CIFAR-80 dataset under 80% symmetric noise and 40% asymmetric noise. The code is available at https://***/chenchenzong/OpenAda. © 2025 IEEE. All rights reserved.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Bi-Grid Reconstruction for Image Anomaly Detection

arXiv

引用

arXiv 2025年

作者： Huang, Huichuan Zhong, Zhiqing Wei, Guangyu Wan, Yonghao Sun, Wenlong Feng, Aimin Nanjing University of Aeronautics and Astronautics China MIIT Key Laboratory of Pattern Analysis and Machine Intelligence China

—In image anomaly detection, significant advancements have been made using un- and self-supervised methods with datasets containing only normal samples. However, these approaches often struggle with fine-grained anomalies. This paper introduces GRAD: Bi-Grid Reconstruction for Image Anomaly Detection, which employs two continuous grids to enhance anomaly detection from both normal and abnormal perspectives. In this work: 1) Grids as feature repositories that improve generalization and mitigate the Identical Shortcut (IS) issue;2) An abnormal feature grid that refines normal feature boundaries, boosting detection of fine-grained defects;3) The Feature Block Paste (FBP) module, which synthesizes various anomalies at the feature level for quick abnormal grid deployment. GRAD’s robust representation capabilities also allow it to handle multiple classes with a single model. Evaluations on datasets like MVTecAD, VisA, and GoodsAD show significant performance improvements in fine-grained anomaly detection. GRAD excels in overall accuracy and in discerning subtle differences, demonstrating its superiority over existing methods. © 2025, CC BY-NC-ND.

关键词： Error detection

来源：评论

学校读者我要写书评

暂无评论

Representation Auto-fused NMF based Hierarchical Clustering

引用

Expert Systems with Applications 2025年 283卷

作者： Lin, Yunxia Hu, Haoyu Li, Bentian Zhao, Shuchang Jing, Hengchang School of Information Engineering Yangzhou University Yangzhou225127 China Jiangsu Province Engineering Research Center of Knowledge Management and Intelligent Service Yangzhou University Yangzhou225127 China MIIT Key Laboratory of Pattern Analysis and Machine Intelligence Nanjing211106 China Institute of Intelligent Information Processing Taizhou University Taizhou318000 China Taizhou University Taizhou318000 China

Nonnegative matrix factorization (NMF) as a powerful representation learning technique has been extensively applied in clustering tasks across diverse domains, leading to the proliferation of various NMF-based clustering methods. However, most of these methods suffer from the suboptimal performance arising from the disjointed process of representation learning and clustering, and the necessity to manually predetermine the optimal number of clusters which is a critical factor affecting the quality of clustering results. To fill this gap and inspired by convex clustering, we propose a simple yet effective NMF-based clustering method named Representation Auto-fused NMF based Hierarchical Clustering (RAFNMF-HC) by incorporating the l2 norm penalty on the differences between pairs of representations into the NMF framework to foster the automatic fusion of representations during representation learning. As the fusion continuously proceeds, similar representations gradually coalesce into small clusters, which subsequently merge into larger ones until a largest cluster encompassing all representations is formed, enabling a joint representation learning and clustering paradigm. Moreover, a cluster hierarchy as a byproduct adaptively emerges without requiring a predefined number of clusters, thus providing us with interpretability of cluster structure of data to some degree. Additionally, RAFNMF-HC only incorporates a single hyperparameter, significantly simplifying the adjustment process and boosting its practical efficiency. Our proposed RAFNMF-HC method also boasts straightforward scalability to diverse NMF variants, enhancing its versatility. Extensive experiments on various real-world datasets demonstrate the superiority of RAFNMF-HC. © 2025 Elsevier Ltd

关键词： Hierarchical clustering

来源：评论

学校读者我要写书评

暂无评论

Consistent Brain Age Difference in Childhood Autism Spectrum Disorder and its Subtypes

Consistent Brain Age Difference in Childhood Autism Spectrum...

引用

4th International Workshop on Human Brain and Artificial intelligence, HBAI 2024

作者： Sun, Fangling Liang, Chuang Shao, Wei Fu, Zening Zhang, Daoqiang Jiang, Rongtao Qi, Shile Calhoun, Vince D. Department of Computer Science and Technology Nanjing University of Aeronautics and Astronautics Nanjing China Key Laboratory of Brain-Machine Intelligence Technology Ministry of Education Nanjing University of Aeronautics and Astronautics Nanjing China MIIT Key Laboratory of Pattern Analysis and Machine Intelligence Nanjing University of Aeronautics and Astronautics Nanjing China Georgia State University Institute of Technology Emory University AtlantaGA United States Department of Radiology and Biomedical Imaging Yale University New HavenCT United States

ISBN: (纸本)9789819640003

Autism spectrum disorder (ASD) is a neurodevelopmental condition characterized by impairments in social interaction and behavior as well as structural abnormalities regarding brain development. The difference between neuroimaging-predicted brain age and the chronological age (predicted age difference;PAD) is a potential biomarker reflecting individual differences in brain developmental trajectories. However, current findings of PAD in ASD are inconsistent due to the biases introduced by different prediction models. Here, 6 classic 3-dimensional convolutional neural network (3D-CNN) models were used to assess brain age to identify consistent and reliable PAD and its interpretable features for ASD. No significant PAD differences between ASD and typically developing controls (TDC) were observed, but PAD differences in younger age and subtypes were found. Occlusion sensitivity analysis showed that default mode network (DMN) and salience network (SAN) drove the atypical brain developmental trajectories in ASD. Our findings were replicable across 6 CNN models, showing the promise of neuroimaging targets for exploring atypical developmental patterns in ASD. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Group-Specific Fusion Model and Its Application in Identifying Multimodal Co-varying Diagnostic patterns for Psychiatric Disorders

Group-Specific Fusion Model and Its Application in Identifyi...

引用

4th International Workshop on Human Brain and Artificial intelligence, HBAI 2024

作者： Cao, Siyuan Liang, Chuang Zhu, Qi Jiang, Rongtao Zhang, Daoqiang Calhoun, Vince D. Qi, Shile Department of Computer Science and Technology Nanjing University of Aeronautics and Astronautics Nanjing China Key Laboratory of Brain-Machine Intelligence Technology Ministry of Education Nanjing University of Aeronautics and Astronautics Nanjing China MIIT Key Laboratory of Pattern Analysis and Machine Intelligence Nanjing University of Aeronautics and Astronautics Nanjing China Georgia State University Georgia Institute of Technology Emory University AtlantaGA United States Department of Radiology and Biomedical Imaging Yale University New HavenCT United States

ISBN: (纸本)9789819640003

Multimodal fusion offers a complementary perspective for understanding brain function and structure. Nevertheless, most existing multimodal fusion methods are unsupervised and thus ignore the diagnostic information. Previous supervised fusion models stack subjects from different diagnostic groups into a single feature matrix, resulting in potential interference between diagnostic groups. In this study, we propose a group-specific multimodal fusion method, called Group-specific Multiset Canonical Correlation analysis with Logistic Regression (GMCCALR) that can effectively leverage group specific information by incorporating a logistic regression term into mCCA and utilizing a group-specific fusion strategy. Results in human neuroimaging data show that GMCCALR provide higher diagnostic accuracy across several psychiatric disorders, including schizophrenia, schizoaffective disorder, bipolar disorder and autism spectrum disorder. We also show the identified disorder-specific multimodal patterns are replicable across multiple cohorts. Overall, results demonstrate the reliability and generalizability of the proposed GMCCALR approach and its efficacy for identifying multimodal co-varying diagnostic patterns for psychiatric disorders. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Logistic regression

来源：评论

学校读者我要写书评

暂无评论

Multiband decomposition and spectral discriminative analysis for motor imagery BCI via deep neural network

引用

Frontiers of Computer Science 2022年第5期16卷 71-83页

作者： Pengpai WANG Mingliang WANG Yueying ZHOU Ziming XU Daoqiang ZHANG College of Computer Science and Technology Nanjing University of Aeronautics and AstronauticsMIIT Key Laboratory of Pattern Analysis and Machine IntelligenceNanjing 211106China

Human limb movement imagery,which can be used in limb neural disorders rehabilitation and brain-controlled external devices,has become a significant control paradigm in the domain of brain-computer interface(BCI).Although numerous pioneering studies have been devoted to motor imagery classification based on electroencephalography(EEG)signal,their performance is somewhat limited due to insufficient analysis of key effective frequency bands of EEG *** this paper,we propose a model of multiband decomposition and spectral discriminative analysis for motor imagery classification,which is called variational sample-long short term memory(VS-LSTM)***,we first use a channel fusion operator to reduce the signal channels of the raw EEG ***,we use the variational mode decomposition(VMD)model to decompose the EEG signal into six band-limited intrinsic mode functions(BIMFs)for further signal noise *** order to select discriminative frequency bands,we calculate the sample entropy(SampEn)value of each frequency band and select the maximum ***,to predict the classification of motor imagery,a LSTM model is used to predict the class of frequency band with the largest SampEn *** open-access public data is used to evaluated the effectiveness of the proposed *** the data,15 subjects performed motor imagery tasks with elbow flexion/extension,forearm supination/pronation and hand open/close of right upper *** experiment results show that the average classification result of seven kinds of motor imagery was 76.2%,the average accuracy of motor imagery binary classification is 96.6%(imagery ***),respectively,which outperforms the state-of-the-art deep learning-based *** framework significantly improves the accuracy of motor imagery by selecting effective frequency *** research is very meaningful for BCIs,and it is inspiring for end-to-end learning research.

关键词： brain computer interface EEG long short-term memory VMD sample entropy motor imagery

来源：评论

学校读者我要写书评

暂无评论

A Deep Model for Partial Multi-label Image Classification with Curriculum-based Disambiguation

引用

machine intelligence Research 2024年第4期21卷 801-814页

作者： Feng Sun Ming-Kun Xie Sheng-Jun Huang MIIT Key Laboratory of Pattern Analysis and Machine Intelligence College of Computer Science and TechnologyNanjing University of AeronauticsandAstronauticsNanjing211106China

In this paper,we study the partial multi-label(PML)image classification problem,where each image is annotated with a candidate label set consisting of multiple relevant labels and other noisy *** PML methods typically design a disambiguation strategy to filter out noisy labels by utilizing prior knowledge with extra assumptions,which unfortunately is unavailable in many real ***,because the objective function for disambiguation is usually elaborately designed on the whole training set,it can hardly be optimized in a deep model with stochastic gradient descent(SGD)on *** this paper,for the first time,we propose a deep model for PML to enhance the representation and discrimination *** the one hand,we propose a novel curriculum-based disambiguation strategy to progressively identify ground-truth labels by incorporating the varied difficulties of different *** the other hand,consistency regularization is introduced for model training to balance fitting identified easy labels and exploiting potential relevant *** experimental results on the commonly used benchmark datasets show that the proposed method significantlyoutperforms the SOTA methods.

关键词： Partial multi-label image classification curriculum-based disambiguation consistency regularization label difficulty candidatelabel set.

来源：评论

学校读者我要写书评

暂无评论

Relative difficulty distillation for semantic segmentation

引用

Science China(Information Sciences) 2024年第9期67卷 126-145页

作者： Dong LIANG Yue SUN Yun DU Songcan CHEN Sheng-Jun HUANG MIIT Key Laboratory of Pattern Analysis and Machine Intelligence College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics Shenzhen Research Institute Nanjing University of Aeronautics and Astronautics

Current knowledge distillation(KD) methods primarily focus on transferring various structured knowledge and designing corresponding optimization goals to encourage the student network to imitate the output of the teacher network. However, introducing too many additional optimization objectives may lead to unstable training, such as gradient conflicts. Moreover, these methods ignored the guidelines of relative learning difficulty between the teacher and student networks. Inspired by human cognitive science, in this paper, we redefine knowledge from a new perspective — the student and teacher networks' relative difficulty of samples, and propose a pixel-level KD paradigm for semantic segmentation named relative difficulty distillation(RDD). We propose a two-stage RDD framework: teacher-full evaluated RDD(TFE-RDD) and teacher-student evaluated RDD(TSE-RDD). RDD allows the teacher network to provide effective guidance on learning focus without additional optimization goals, thus avoiding adjusting learning weights for multiple losses. Extensive experimental evaluations using a general distillation loss function on popular datasets such as Cityscapes, Cam Vid, Pascal VOC, and ADE20k demonstrate the effectiveness of RDD against state-ofthe-art KD methods. Additionally, our research showcases that RDD can integrate with existing KD methods to improve their upper performance bound. Codes are available at https://***/sunyueue/***.

关键词： knowledge distillation semantic segmentation relative difficulty sample weighting prediction discrepancy

来源：评论

学校读者我要写书评

暂无评论

fMRI-based Decoding of Visual Information from Human Brain Activity: A Brief Review

引用

International Journal of Automation and computing 2021年第2期18卷 170-184页

作者： Shuo Huang Wei Shao Mei-Ling Wang Dao-Qiang Zhang College of Computer Science and Technology Nanjing University of Aeronautics and AstronauticsNanjing 211106China MIIT Key Laboratory of Pattern Analysis and Machine Intelligence Nanjing 211106China

One of the most significant challenges in the neuroscience community is to understand how the human brain *** progress in neuroimaging techniques have validated that it is possible to decode a person′s thoughts,memories,and emotions via functional magnetic resonance imaging(i.e.,fMRI)since it can measure the neural activation of human brains with satisfied spatiotemporal ***,the unprecedented scale and complexity of the fMRI data have presented critical computational bottlenecks requiring new scientific analytic *** the increasingly important role of machine learning in neuroscience,a great many machine learning algorithms are presented to analyze brain activities from the fMRI *** this paper,we mainly provide a comprehensive and up-to-date review of machine learning methods for analyzing neural activities with the following three aspects,i.e.,brain image functional alignment,brain activity pattern analysis,and visual stimuli *** addition,online resources and open research problems on brain pattern analysis are also provided for the convenience of future research.

关键词： Functional magnetic resonance imaging(fMRI) functional alignment brain activity brain decoding visual stimuli reconstruction

来源：评论

学校读者我要写书评

暂无评论

Deep Learning in Palmprint Recognition-A Comprehensive Survey

arXiv

引用

arXiv 2025年

作者： Gao, Chengrui Yang, Ziyuan Jia, Wei Leng, Lu Zhang, Bob Teoh, Andrew Beng Jin College of Computer Science Sichuan University Chengdu610065 China Singapore School of Computer and Information Hefei University of Technology Hefei China Jiangxi Provincial Key Laboratory of Image Processing and Pattern Recognition Nanchang Hangkong University Nanchang China Pattern Analysis and Machine Intelligence Group Department of Computer and Information Science University of Macau Taipa China School of Electrical and Electronic Engineering College of Engineering Yonsei University Seoul Korea Republic of

Palmprint recognition has emerged as a prominent biometric technology, widely applied in diverse scenarios. Traditional handcrafted methods for palmprint recognition often fall short in representation capability, as they heavily depend on researchers' prior knowledge. Deep learning (DL) has been introduced to address this limitation, leveraging its remarkable successes across various domains. While existing surveys focus narrowly on specific tasks within palmprint recognition-often grounded in traditional methodologies-there remains a significant gap in comprehensive research exploring DL-based approaches across all facets of palmprint recognition. This paper bridges that gap by thoroughly reviewing recent advancements in DL-powered palmprint recognition. The paper systematically examines progress across key tasks, including region-of-interest segmentation, feature extraction, and security/privacy-oriented challenges. Beyond highlighting these advancements, the paper identifies current challenges and uncovers promising opportunities for future research. By consolidating state-of-the-art progress, this review serves as a valuable resource for researchers, enabling them to stay abreast of cutting-edge technologies and drive innovation in palmprint recognition. Copyright © 2025, The Authors. All rights reserved.

关键词： Biometrics

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：