检索结果-内蒙古大学图书馆

Diffusion-Noise-based Augmentation for Long-Tailed Remote Sensing Image Classification

IEEE Transactions on Geoscience and Remote Sensing 2025年

作者： Wang, Qianqian Ye, Haibo Liang, Dong Huang, Sheng-Jun MIIT Key Laboratory of Pattern Analysis and Machine Intelligence Collaborative Innovation Center of Novel Software Technology and Industrialization College of Computer Science and Technology Nanjing university of Aeronautics and Astronautics Nanjing 211106 China

Remote sensing image classification refers to the task that using algorithms to categorize satellite or aerial imagery into different land cover types. In the real world, long-tailed data distribution is commonly present in remote sensing image classification tasks, causing models to excessively favor sufficient head classes during training and degrading prediction accuracy for scarce tail classes. Although existing methods such as resampling and re-weighting can alleviate the issue of data imbalance to a certain extent, they struggle to sufficiently enhance the diversity of tail class samples. In recent years, some works have begun to use diffusion models to generate diverse samples to balance the class distribution. However, these approaches often overlook the distribution inconsistency between generated and real images, which will hinder the improvement of model performance. To tackle these challenges, this paper proposes a novel diffusion-noise-based augmentation method (DONA) with a two-stage training process. Before training, our specially designed conditional prompts are used together with the original training set to guide the diffusion model in image generation. Furthermore, we propose two strategies to effectively leverage the generated images, which are applied respectively at the end of the first training stage and during the second training stage. First, we design DiffCam-Mix to fuse the background of the generated data with the foreground of the original data, preserving the essential information of the original real images while incorporating the diversity of the generated ones. Second, we use cosine similarity to minimize the differences between the mixed data and their corresponding original data, further calibrating the distribution of different samples. Extensive experiments on three public datasets—SIRI-WHU-LT, patternNet-LT, and RSI-CB256-LT—demonstrate the effectiveness of the proposed method. © 1980-2012 IEEE.

关键词： diffusion model long-tailed distribution remote sensing image classification visual recognition

来源：评论

学校读者我要写书评

暂无评论

Handling Noisy Annotation for Remote Sensing Semantic Segmentation via Boundary-Aware Knowledge Distillation

引用

IEEE Transactions on Geoscience and Remote Sensing 2025年 63卷

作者： Sun, Yue Liang, Dong Li, Shao-Yuan Chen, Songcan Huang, Sheng-Jun Nanjing University of Aeronautics and Astronautics College of Computer Science and Technology MIIT Key Laboratory of Pattern Analysis and Machine Intelligence Nanjing211106 China Shenzhen Research Institute Nanjing University of Aeronautics and Astronautics Shenzhen518131 China Joint Laboratory of Spatial Intelligent Perception and Large Model Application Nanjing211106 China

In recent years, image segmentation has made significant progress, but acquiring annotated data is still a considerable challenge, especially in remote sensing imagery (RSI). The complex structure and intercategory confusion of RSI increase the time consumption and cost of pixel-level annotation, and noisy annotations inevitably appear. This article proposes a boundary-aware knowledge distillation (BAKD) method to handle noisy annotations by evaluating their uncertainty. BAKD consists of two core strategies: predictive confidence evaluation (PCE) and boundary-annotated reliability evaluation (BRE). The predictive confidence (PC) jointly decided by the teacher and student networks reflects the annotation’s uncertainty. The boundary-annotated reliability (BR) directly measures the annotation’s uncertainty based on the distance from the annotation to the semantic boundary. Leveraging these two types of uncertainty information, BAKD assigns each sample a comprehensive boundary-aware weight to identify samples with potential noisy annotations. This alleviates the impact of noisy annotation on the model’s training and improves its generalization performance. Experimental results show that BAKD achieves competitive semantic segmentation performance on the Potsdam and Vaihingen benchmarks compared with the state-of-the-art KD methods. In addition, BAKD can be easily integrated into semantic segmentation methods based on KD (SSKD), extending their applicability in handling noisy annotations. © 1980-2012 IEEE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

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

引用

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

Consistent Brain Age Difference in Childhood Autism Spectrum Disorder and its Subtypes 4th

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

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

Group-Specific Fusion Model and Its Application in Identifying Multimodal Co-varying Diagnostic patterns for Psychiatric Disorders 4th

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

All-around Neural Collapse for Imbalanced Classification

引用

IEEE Transactions on Knowledge and Data Engineering 2025年

作者： Zhang, Enhao Li, Chaohua Geng, Chuanxing Chen, Songcan MIIT Key Laboratory of Pattern Analysis and Machine Intelligence China Nanjing University of Aeronautics and Astronautics (NUAA) College of Computer Science and Technology Nanjing 211106 China

Neural Collapse (NC) presents an elegant geometric structure that enables individual activations (features), class means and classifier (weights) vectors to reach optimal inter-class separability during the terminal phase of training on a balanced dataset. Once shifted to imbalanced classification, such an optimal structure of NC can be readily destroyed by the notorious minority collapse, where the classifier vectors corresponding to the minority classes are squeezed. In response, existing works mainly optimize classifiers in an effort to recover NC. However, we discover that this squeezing phenomenon is not only confined to classifier vectors but also occurs with class means. Consequently, reconstructing NC solely at the classifier aspect may be futile, as the class means remain compressed, leading to the violation of inherent self-duality in NC (i.e., class means and classifier vectors converge mutually) and incidentally, an unsatisfactory collapse of individual activations towards the corresponding class means. To shake off these dilemmas, we present a unified All-around Neural Collapse framework (AllNC), aiming to comprehensively restore NC across multiple aspects including individual activations, class means and classifier vectors. We thoroughly analyze its effectiveness and verify its performance on multiple benchmark datasets as state-of-the-art in both balanced and imbalanced settings. © 1989-2012 IEEE.

关键词： Contrastive learning Imbalanced classification Long-tailed Neural collapse

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

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：