检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Wang, Yunyun Zheng, Weiwen Chen, Songcan The Jiangsu Key Laboratory of Big Data Security & Intelligent Processing Computer Science and Engineering Nanjing University of Posts & Telecommunications Nanjing210046 China The MIIT Key Laboratory of Pattern Analysis and Machine Intelligence Computer Science & Technology/AI Nanjing University of Aeronautics & Astronautics Nanjing210023 China

Previous unsupervised domain adaptation (UDA) methods aim to promote target learning via a single-directional knowledge transfer from label-rich source domain to unlabeled target domain, while its reverse adaption from target to source has not jointly been considered yet so far. In fact, in some real teaching practice, a teacher helps students learn while also gets promotion from students to some extent, which inspires us to explore a dual-directional knowledge transfer between domains, and thus propose a Dual-Correction Adaptation Network (DualCAN) in this paper. However, due to the asymmetrical label knowledge across domains, transfer from unlabeled target to labeled source poses a more difficult challenge than the common source-to-target counterpart. First, the target pseudo-labels predicted by source commonly involve noises due to model bias, hence in the reverse adaptation, they may hurt the source performance and bring a negative target-to-source transfer. Secondly, source domain usually contains innate noises, which will inevitably aggravate the target noises, leading to noise amplification across domains. To this end, we further introduce a Noise Identification and Correction (NIC) module to correct and recycle noises in both domains. To our best knowledge, this is the first naive attempt of dual-directional adaptation for noisy UDA, and naturally applicable to noise-free UDA. A theory justification is given to state the rationality of our intuition. Empirical results confirm the effectiveness of DualCAN with remarkable performance gains over state-of-the-arts, particularly for extreme noisy tasks (e.g., ∼+ 15% on Pw→Pr and Pr→Rw of Office-Home). Copyright © 2022, The Authors. All rights reserved.

关键词： Knowledge management

来源：评论

学校读者我要写书评

暂无评论

A Multi-Layer Random Walk Method for Local Dynamic Community Detection in Brain Functional Network

A Multi-Layer Random Walk Method for Local Dynamic Community...

引用

2021 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2021

作者： Wen, Xuyun Zhang, Daoqiang Nanjing University of Aeronautics and Astronautics College of Computer Science and Technology MIIT Key Laboratory of Pattern Analysis and Machine Intelligence Jiangsu Nanjing China Nanjing University of Aeronautics and Astronautics College of Computer Science and Technology Jiangsu Nanjing China Engineering Research Center of Traditional Chinese Medicine Intelligent Rehabilitation Ministry of Education Shanghai China

ISBN: (纸本)9781665401265

Detecting the time-varying community structure of brain functional network is very important to reveal dynamic properties of the human brain. Although several community detection methods have been proposed, they are limited in real application due to their poor performance in large dynamic network and difficulty in parameter setting without prior knowledge. To address these problems, this paper proposes a novel dynamic community detection method for the brain network based on random walk, named as ML-RW. This method uses local community discovery instead of global community detection to improve its ability to deal with large dynamic networks. Specifically, ML-RW first selects a query brain region and sends out multiple random walkers starting from this region to explore local community structures of all networks in dynamic network simultaneously. It updates the visiting probability vector of each walker by aggregating the transition probabilities from itself and two temporally adjacent networks. Since the influence strength from one network to another is adaptively tuned according to the relevance of visiting histories of two networks, ML-RW could guarantee the temporal smoothness of the detected modular structure without introducing the hyper-parameter and thus avoids the problem of parameter setting in existing methods. Experiments on two public real neuroimaging datasets demonstrate that our proposed method has more potential to capture subtle community variations in the brain region, stronger ability to discover biomarkers for brain diseases, and higher test-retest reliability than the conventional method. © 2021 IEEE.

关键词： Neuroimaging

来源：评论

学校读者我要写书评

暂无评论

Can Adversarial Training Be Manipulated By Non-Robust Features?

arXiv

引用

arXiv 2022年

作者： Tao, Lue Feng, Lei Wei, Hongxin Yi, Jinfeng Huang, Sheng-Jun Chen, Songcan National Key Laboratory for Novel Software Technology Nanjing University Nanjing China Chongqing University Chongqing China RIKEN Center for Advanced Intelligence Project Japan Nanyang Technological University Singapore JD AI Research Beijing China MIIT Key Laboratory of Pattern Analysis and Machine Intelligence Nanjing University of Aeronautics and Astronautics Nanjing China

Adversarial training, originally designed to resist test-time adversarial examples, has shown to be promising in mitigating training-time availability attacks. This defense ability, however, is challenged in this paper. We identify a novel threat model named stability attack, which aims to hinder robust availability by slightly manipulating the training data. Under this threat, we show that adversarial training using a conventional defense budget ∊provably fails to provide test robustness in a simple statistical setting, where the non-robust features of the training data can be reinforced by ∊-bounded perturbation. Further, we analyze the necessity of enlarging the defense budget to counter stability attacks. Finally, comprehensive experiments demonstrate that stability attacks are harmful on benchmark datasets, and thus the adaptive defense is necessary to maintain robustness.1 Copyright © 2022, The Authors. All rights reserved.

关键词： Budget control

来源：评论

学校读者我要写书评

暂无评论

Discrimination-Aware Domain Adversarial Neural Network

引用

Journal of Computer Science & Technology 2020年第2期35卷 259-267页

作者： Yun-Yun Wang Jian-Min Gu Chao Wang Song-Can Chen Hui Xue College of Computer Science and Engineering Nanjing University of Posts and Telecommunications Nanjing 210046China Jiangsu Key Laboratory of Big Data Security and Intelligent Processing Nanjing 210046China College of Computer Science and Technology/College of Artificial Intelligence Nanjing University of Aeronautics and AstronauticsNanjing 210023China Key Laboratory of Pattern Analysis and Machine Intelligence Ministry of Industry and Information Technology Nanjing 210023China School of Computer Science and Engineering Southeast UniversityNanjing 210096China

The domain adversarial neural network(DANN)methods have been successfully proposed and attracted much attention *** DANNs,a discriminator is trained to discriminate the domain labels of features generated by a generator,whereas the generator attempts to confuse it such that the distributions between domains are *** a result,it actually encourages the whole alignment or transfer between domains,while the inter-class discriminative information across domains is not *** this paper,we present a Discrimination-Aware Domain Adversarial Neural Network(DA2NN)method to introduce the discriminative information or the discrepancy of inter-class instances across domains into deep domain ***2NN considers both the alignment within the same class and the separation among different classes across domains in knowledge transfer via multiple *** results show that DA2NN can achieve better classification performance compared with the DANN methods.

关键词： adversarial learning inter-class separation deep neural network discrimination-aware domain adaptation

来源：评论

学校读者我要写书评

暂无评论

Label Structure Preserving Contrastive Embedding for Multi-Label Learning with Missing Labels

arXiv

引用

arXiv 2022年

作者： Ma, Zhongchen Li, Lisha Mao, Qirong Chen, Songcan The School of Computer Science and Communications Engineering Jiangsu University Zhenjiang212013 China Jiangsu Engineering Research Center of Big Data Ubiquitous Perception and Intelligent Agriculture Applications China MIIT Key Laboratory of Pattern Analysis and Machine Intelligence China Nanjing211106 China

Contrastive learning (CL) has shown impressive advances in image representation learning in whichever supervised multi-class classification or unsupervised learning. However, these CL methods fail to be directly adapted to multi-label image classification due to the difficulty in defining the positive and negative instances to contrast a given anchor image in multi-label scenario, let the label missing one alone, implying that borrowing a commonly-used way from contrastive multi-class learning to define them will incur a lot of false negative instances unfavorable for learning. In this paper, with the introduction of a label correction mechanism to identify missing labels, we first elegantly generate positives and negatives for individual semantic labels of an anchor image, then define a unique contrastive loss for multilabel image classification with missing labels (CLML), the loss is able to accurately bring images close to their true positive images and false negative images, far away from their true negative images. Different from existing multi-label CL losses, CLML also preserves low-rank global and local label dependencies in the latent representation space where such dependencies have been shown to be helpful in dealing with missing labels. To the best of our knowledge, this is the first general multi-label CL loss in the missing-label scenario and thus can seamlessly be paired with those losses of any existing multi-label learning methods just via a single hyperparameter. The proposed strategy has been shown to improve the classification performance of the Resnet101 model by margins of 1.2%, 1.6%, and 1.3% respectively on three standard datasets, MSCOCO, VOC, and NUS-WIDE. Code is available at https://***/chuangua/ContrastiveLossMLML. Copyright © 2022, The Authors. All rights reserved.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

Variational OOD State Correction for Offline Reinforcement Learning

arXiv

引用

arXiv 2025年

作者： Jiang, Ke Jiang, Wen Fujisawa, Masahiro Tan, Xiaoyang College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics MIIT Key Laboratory of Pattern Analysis and Machine Intelligence China The University of Osaka Japan RIKEN AIP Japan

The performance of Offline reinforcement learning is significantly impacted by the issue of state distributional shift, and out-of-distribution (OOD) state correction is a popular approach to address this problem. In this paper, we propose a novel method named Density-Aware Safety Perception (DASP) for OOD state correction. Specifically, our method encourages the agent to prioritize actions that lead to outcomes with higher data density, thereby promoting its operation within or the return to in-distribution (safe) regions. To achieve this, we optimize the objective within a variational framework that concurrently considers both the potential outcomes of decision-making and their density, thus providing crucial contextual information for safe decision-making. Finally, we validate the effectiveness and feasibility of our proposed method through extensive experimental evaluations on the offline MuJoCo and AntMaze suites. © 2025, CC BY-NC-ND.

关键词： Variational techniques

来源：评论

学校读者我要写书评

暂无评论

Complementary Labels Learning with Augmented Classes

SSRN

引用

SSRN 2023年

作者： Li, Zhongnian Xu, Mengting Xu, Xinzheng Zhang, Daoqiang School of Computer Science and Technology China University of Ming and Technogy Jiangsu Xuzhou221000 China College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics Jiangsu Nanjing210000 China College of Computer Science and Technology Zhejiang University Zhejiang Hangzhou310000 China MIIT Key Laboratory of Pattern Analysis and Machine Intelligence Jiangsu Nanjing210000 China

Complementary Labels Learning (CLL) arises in many real-world tasks such as private questions classification and online learning, which aims to alleviate the annotation cost compared with standard supervised ***, most previous CLL algorithms were in a stable environment rather than an open and dynamic scenarios, where data collected from unseen augmented classes in the training process might emerge in the testing *** this paper, we propose a novel problem setting called Complementary Labels Learning with Augmented Classes (CLLAC), which brings the challenge that classifiers trained by complementary labels should not only be able to classify the instances from observed classes accurately, but also recognize the instance from the Augmented Classes in the testing phase. Specifically, by using unlabeled data, we propose an unbiased estimator of classification risk for CLLAC, which is guaranteed to be provably consistent. Moreover, we provide generalization error bound for proposed method which shows that the optimal parametric convergence rate is achieved for estimation error. Finally, the experimental results on several benchmark datasets verify the effectiveness of the proposed method. © 2023, The Authors. All rights reserved.

关键词： machine learning

来源：评论

学校读者我要写书评

暂无评论

CE-AH: A contrast-enhanced attention hierarchical network for Alzheimer's disease diagnosis based on structural MRI

引用

pattern Recognition 2026年 169卷

作者： Tianxiang Wang Qun Dai Han Lu College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics Nanjing 211106 China MIIT Key Laboratory of Pattern Analysis and Machine Intelligence Nanjing 211106 China

Numerous deep learning-based methods utilizing structural magnetic resonance imaging (sMRI) have been developed for diagnosing Alzheimer's disease (AD). However, the majority of these methods overlook the localized nature of brain atrophy. Moreover, they often rely on a single scale, neglecting the global structural information. To address these issues concurrently, this study introduces a Contrast-Enhanced Attention Hierarchical (CE-AH) network for AD diagnosis. Initially, we employ pretraining through contrastive learning to bolster the network's feature extraction capabilities. Subsequently, we engineer a hierarchical model that integrates dual attention mechanisms to extract multi-scale discriminative features. To overcome the convergence challenges and training instability inherent in patch-based methods, we implement group normalization in place of batch normalization. The CE-AH model's performance is assessed on the ADNI dataset, yielding outstanding classification outcomes. Furthermore, experimental results indicate that the training process of our proposed model is remarkably stable.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A lightweight multi-scale context network for salient object detection in optical remote sensing images

arXiv

引用

arXiv 2022年

作者： Lin, Yuhan Sun, Han Liu, Ningzhong Bian, Yetong Cen, Jun Zhou, Huiyu College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics Nanjing China MIIT Key Laboratory of Pattern Analysis and Machine Intelligence Nanjing China School of Computing and Mathematical Sciences University of Leicester LeicesterLE1 7RH United Kingdom

Due to the more dramatic multi-scale variations and more complicated foregrounds and backgrounds in optical remote sensing images (RSIs), the salient object detection (SOD) for optical RSIs becomes a huge challenge. However, different from natural scene images (NSIs), the discussion on the optical RSI SOD task still remains scarce. In this paper, we propose a multi-scale context network, namely MSCNet, for SOD in optical RSIs. Specifically, a multi-scale context extraction module is adopted to address the scale variation of salient objects by effectively learning multi-scale contextual information. Meanwhile, in order to accurately detect complete salient objects in complex backgrounds, we design an attention-based pyramid feature aggregation mechanism for gradually aggregating and refining the salient regions from the multi-scale context extraction module. Extensive experiments on two benchmarks demonstrate that MSCNet achieves competitive performance with only 3.26M parameters. The code will be available at https://***/NuaaYH/MSCNet. © 2022, CC BY.

关键词： Extraction

来源：评论

学校读者我要写书评

暂无评论

Nlkd: Using Coarse Annotations For Semantic Segmentation Based on Knowledge Distillation

Nlkd: Using Coarse Annotations For Semantic Segmentation Bas...

引用

IEEE International Conference on Acoustics, Speech and Signal Processing

作者： Dong Liang Yun Du Han Sun Liyan Zhang Ningzhong Liu Mingqiang Wei College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics MIIT Key Laboratory of Pattern Analysis and Machine Intelligence Collaborative Innovation Center of Novel Software Technology and Industrialization

ISBN: (纸本)9781728176055;9781728176062

Modern supervised learning relies on a large amount of training data, yet there are many noisy annotations in real datasets. For semantic segmentation tasks, pixel-level annotation noise is typically located at the edge of an object, while pixels within objects are fine-annotated. We argue the coarse annotations can provide instructive supervised information to guide model training rather than be discarded. This paper proposes a noise learning framework based on knowledge distillation NLKD, to improve segmentation performance on unclean data. It utilizes a teacher network to guide the student network that constitutes the knowledge distillation process. The teacher and student generate the pseudo-labels and jointly evaluate the quality of annotations to generate weights for each sample. Experiments demonstrate the effectiveness of NLKD, and we observe better performance with boundary-aware teacher networks and evaluation metrics. Furthermore, the proposed approach is model-independent and easy to implement, appropriate for integration with other tasks and models.

关键词： Training Annotations Semantics Supervised learning Training data Signal processing Noise robustness

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：