IEEE transactions on neural networks and learning systems最新文献

筛选
英文 中文
Incremental Learning for Defect Segmentation With Efficient Transformer Semantic Complement. 基于高效互感器语义补充的增量学习缺陷分割。
IF 10.4 1区 计算机科学
IEEE transactions on neural networks and learning systems Pub Date : 2025-09-09 DOI: 10.1109/tnnls.2025.3604956
Xiqi Li,Zhifu Huang,Ge Ma,Yu Liu
{"title":"Incremental Learning for Defect Segmentation With Efficient Transformer Semantic Complement.","authors":"Xiqi Li,Zhifu Huang,Ge Ma,Yu Liu","doi":"10.1109/tnnls.2025.3604956","DOIUrl":"https://doi.org/10.1109/tnnls.2025.3604956","url":null,"abstract":"In industrial scenarios, semantic segmentation of surface defects is vital for identifying, localizing, and delineating defects. However, new defect types constantly emerge with product iterations or process updates. Existing defect segmentation models lack incremental learning capabilities, and direct fine-tuning (FT) often leads to catastrophic forgetting. Furthermore, low contrast between defects and background, as well as among defect classes, exacerbates this issue. To address these challenges, we introduce a plug-and-play Transformer-based semantic complement module (TSCM). With only a few added parameters, it injects global contextual features from multi-head self-attention into shallow convolutional neural network (CNN) feature maps, compensating for convolutional receptive-field limits and fusing global and local information for better segmentation. For incremental updates, we propose multi-scale spatial pooling distillation (MSPD), which uses pseudo-labeling and multi-scale pooling to preserve both short- and long-range spatial relations and provides smooth feature alignment between teacher and student. Additionally, we adopt an adaptive weight fusion (AWF) strategy with a dynamic threshold that assigns higher weights to parameters with larger updates, achieving an optimal balance between stability and plasticity. The experimental results on two industrial surface defect datasets demonstrate that our method outperforms existing approaches in various incremental segmentation scenarios.","PeriodicalId":13303,"journal":{"name":"IEEE transactions on neural networks and learning systems","volume":"11 1","pages":""},"PeriodicalIF":10.4,"publicationDate":"2025-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145025294","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Long-Tail Class Incremental Learning via Bias Calibration With Application to Continuous Fault Diagnosis 基于偏差校准的长尾类增量学习在连续故障诊断中的应用
IF 10.4 1区 计算机科学
IEEE transactions on neural networks and learning systems Pub Date : 2025-09-08 DOI: 10.1109/tnnls.2025.3602182
Dongyue Chen, Zongxia Xie, Wenlong Yu, Qinghua Hu
{"title":"Long-Tail Class Incremental Learning via Bias Calibration With Application to Continuous Fault Diagnosis","authors":"Dongyue Chen, Zongxia Xie, Wenlong Yu, Qinghua Hu","doi":"10.1109/tnnls.2025.3602182","DOIUrl":"https://doi.org/10.1109/tnnls.2025.3602182","url":null,"abstract":"","PeriodicalId":13303,"journal":{"name":"IEEE transactions on neural networks and learning systems","volume":"44 1","pages":""},"PeriodicalIF":10.4,"publicationDate":"2025-09-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145017727","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Expandable Residual Approximation for Knowledge Distillation 知识蒸馏的可扩展残差逼近
IF 10.4 1区 计算机科学
IEEE transactions on neural networks and learning systems Pub Date : 2025-09-08 DOI: 10.1109/tnnls.2025.3602118
Zhaoyi Yan, Binghui Chen, Yunfan Liu, Qixiang Ye
{"title":"Expandable Residual Approximation for Knowledge Distillation","authors":"Zhaoyi Yan, Binghui Chen, Yunfan Liu, Qixiang Ye","doi":"10.1109/tnnls.2025.3602118","DOIUrl":"https://doi.org/10.1109/tnnls.2025.3602118","url":null,"abstract":"","PeriodicalId":13303,"journal":{"name":"IEEE transactions on neural networks and learning systems","volume":"65 1","pages":""},"PeriodicalIF":10.4,"publicationDate":"2025-09-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145017725","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Evidential Graph Contrastive Alignment for Source-Free Blending-Target Domain Adaptation 无源混合-目标域自适应证据图对比对齐
IF 10.4 1区 计算机科学
IEEE transactions on neural networks and learning systems Pub Date : 2025-09-08 DOI: 10.1109/tnnls.2025.3603224
Juepeng Zheng, Guowen Li, Yibin Wen, Jinxiao Zhang, Runmin Dong, Haohuan Fu
{"title":"Evidential Graph Contrastive Alignment for Source-Free Blending-Target Domain Adaptation","authors":"Juepeng Zheng, Guowen Li, Yibin Wen, Jinxiao Zhang, Runmin Dong, Haohuan Fu","doi":"10.1109/tnnls.2025.3603224","DOIUrl":"https://doi.org/10.1109/tnnls.2025.3603224","url":null,"abstract":"","PeriodicalId":13303,"journal":{"name":"IEEE transactions on neural networks and learning systems","volume":"24 1","pages":""},"PeriodicalIF":10.4,"publicationDate":"2025-09-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145017726","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Koopman-Driven Linearized Model-Based Offline Planning With Application to Freeway Ramp Metering 基于koopman驱动线性化模型的离线规划及其在高速公路匝道计量中的应用
IF 10.4 1区 计算机科学
IEEE transactions on neural networks and learning systems Pub Date : 2025-09-08 DOI: 10.1109/tnnls.2025.3605015
Tao Zhou, Chuanye Gu, Chee Peng Lim, Jinlong Yuan
{"title":"Koopman-Driven Linearized Model-Based Offline Planning With Application to Freeway Ramp Metering","authors":"Tao Zhou, Chuanye Gu, Chee Peng Lim, Jinlong Yuan","doi":"10.1109/tnnls.2025.3605015","DOIUrl":"https://doi.org/10.1109/tnnls.2025.3605015","url":null,"abstract":"","PeriodicalId":13303,"journal":{"name":"IEEE transactions on neural networks and learning systems","volume":"130 1","pages":""},"PeriodicalIF":10.4,"publicationDate":"2025-09-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145017774","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
A Dual-Discriminator Generative Adversarial Network for Anomaly Detection 一种用于异常检测的双鉴别生成对抗网络
IF 8.9 1区 计算机科学
IEEE transactions on neural networks and learning systems Pub Date : 2025-09-05 DOI: 10.1109/TNNLS.2025.3585978
Da Ding;Youquan Wang;Haicheng Tao;Jia Wu;Jie Cao
{"title":"A Dual-Discriminator Generative Adversarial Network for Anomaly Detection","authors":"Da Ding;Youquan Wang;Haicheng Tao;Jia Wu;Jie Cao","doi":"10.1109/TNNLS.2025.3585978","DOIUrl":"10.1109/TNNLS.2025.3585978","url":null,"abstract":"Multivariate time series anomaly detection has shown potential in various fields, such as finance, aerospace, and security. The fuzzy definition of data anomalies, the complexity of data patterns, and the scarcity of abnormal data samples pose significant challenges to anomaly detection. Researchers have extensively employed autoencoders (AEs) and generative adversarial networks (GANs) in studying time series anomaly detection methods. However, relying on reconstruction error, the AE-based anomaly detection algorithm needs more effective regularization methods, rendering it susceptible to the problem of overfitting. Meanwhile, GAN-based anomaly detection algorithms require high-quality training data, significantly impacting their practical deployment. We propose a novel GAN based on a dual-discriminator structure to address these issues. The model first processes the data with the generator to obtain the reconstruction error and then calculates pseudo-labels to divide the data into two categories. One data category is input into the first discriminator, where a minor loss between the data and its reconstructed counterpart is better. The other data category is input into the second discriminator, where a larger loss between the data and its reconstructed counterpart is better. Through this process, the model can effectively constrain the generator, retaining information on normal data during data reconstruction while discarding information on abnormal data. After conducting experiments on multiple benchmark datasets, the proposed GAN based on a dual-discriminator structure achieved good results in anomaly detection, outperforming several advanced methods. Additionally, the model also performed well in practical transformer data.","PeriodicalId":13303,"journal":{"name":"IEEE transactions on neural networks and learning systems","volume":"36 10","pages":"19285-19296"},"PeriodicalIF":8.9,"publicationDate":"2025-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145002951","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Surfer: A World Model-Based Framework for Vision-Language Robot Manipulation Surfer:一个基于世界模型的视觉语言机器人操作框架
IF 10.4 1区 计算机科学
IEEE transactions on neural networks and learning systems Pub Date : 2025-09-05 DOI: 10.1109/tnnls.2025.3594117
Pengzhen Ren, Kaidong Zhang, Hetao Zheng, Zixuan Li, Yuhang Wen, Fengda Zhu, Shikui Ma, Xiaodan Liang
{"title":"Surfer: A World Model-Based Framework for Vision-Language Robot Manipulation","authors":"Pengzhen Ren, Kaidong Zhang, Hetao Zheng, Zixuan Li, Yuhang Wen, Fengda Zhu, Shikui Ma, Xiaodan Liang","doi":"10.1109/tnnls.2025.3594117","DOIUrl":"https://doi.org/10.1109/tnnls.2025.3594117","url":null,"abstract":"","PeriodicalId":13303,"journal":{"name":"IEEE transactions on neural networks and learning systems","volume":"16 1","pages":""},"PeriodicalIF":10.4,"publicationDate":"2025-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145002953","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Integrating Clinical Knowledge Graphs and Gradient-Based Neural Systems for Enhanced Melanoma Diagnosis via the Seven-Point Checklist 整合临床知识图谱和基于梯度的神经系统,通过七点检查表增强黑色素瘤诊断
IF 10.4 1区 计算机科学
IEEE transactions on neural networks and learning systems Pub Date : 2025-09-04 DOI: 10.1109/tnnls.2025.3600443
Yuheng Wang, Tianze Yu, Jiayue Cai, Sunil Kalia, Harvey Lui, Z. Jane Wang, Tim K. Lee
{"title":"Integrating Clinical Knowledge Graphs and Gradient-Based Neural Systems for Enhanced Melanoma Diagnosis via the Seven-Point Checklist","authors":"Yuheng Wang, Tianze Yu, Jiayue Cai, Sunil Kalia, Harvey Lui, Z. Jane Wang, Tim K. Lee","doi":"10.1109/tnnls.2025.3600443","DOIUrl":"https://doi.org/10.1109/tnnls.2025.3600443","url":null,"abstract":"","PeriodicalId":13303,"journal":{"name":"IEEE transactions on neural networks and learning systems","volume":"62 1","pages":""},"PeriodicalIF":10.4,"publicationDate":"2025-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144995204","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
IEEE Transactions on Neural Networks and Learning Systems Publication Information IEEE神经网络与学习系统汇刊
IF 8.9 1区 计算机科学
IEEE transactions on neural networks and learning systems Pub Date : 2025-09-04 DOI: 10.1109/TNNLS.2025.3599349
{"title":"IEEE Transactions on Neural Networks and Learning Systems Publication Information","authors":"","doi":"10.1109/TNNLS.2025.3599349","DOIUrl":"10.1109/TNNLS.2025.3599349","url":null,"abstract":"","PeriodicalId":13303,"journal":{"name":"IEEE transactions on neural networks and learning systems","volume":"36 9","pages":"C2-C2"},"PeriodicalIF":8.9,"publicationDate":"2025-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11151720","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144995326","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
IEEE Computational Intelligence Society Information IEEE计算智能学会信息
IF 8.9 1区 计算机科学
IEEE transactions on neural networks and learning systems Pub Date : 2025-09-04 DOI: 10.1109/TNNLS.2025.3599347
{"title":"IEEE Computational Intelligence Society Information","authors":"","doi":"10.1109/TNNLS.2025.3599347","DOIUrl":"https://doi.org/10.1109/TNNLS.2025.3599347","url":null,"abstract":"","PeriodicalId":13303,"journal":{"name":"IEEE transactions on neural networks and learning systems","volume":"36 9","pages":"C3-C3"},"PeriodicalIF":8.9,"publicationDate":"2025-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11151719","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144990105","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信