2021 IEEE 31st International Workshop on Machine Learning for Signal Processing (MLSP)最新文献_第6页

Estimating Partially Observed Graph Signals by Learning Spectrally Concentrated Graph Kernels 用谱集中图核学习估计部分观测图信号

2021 IEEE 31st International Workshop on Machine Learning for Signal Processing (MLSP) Pub Date : 2021-10-25 DOI: 10.1109/mlsp52302.2021.9596282

Gülce Turhan, Elif Vural

{"title":"Estimating Partially Observed Graph Signals by Learning Spectrally Concentrated Graph Kernels","authors":"Gülce Turhan, Elif Vural","doi":"10.1109/mlsp52302.2021.9596282","DOIUrl":"https://doi.org/10.1109/mlsp52302.2021.9596282","url":null,"abstract":"Graph models provide flexible tools for the representation and analysis of signals defined over irregular domains such as social or sensor networks. However, in real applications data observations are often not available over the whole graph, due to practical problems such as sensor failure or connection loss. In this paper, we study the estimation of partially observed graph signals on multiple graphs. We learn a sparse representation of partially observed graph signals over spectrally concentrated graph dictionaries. Our dictionary model consists of several sub-dictionaries each of which is generated from a Gaussian kernel centered at a certain graph frequency in order to capture a particular spectral component of the graph signals at hand. The problem of jointly learning the spectral kernels and the sparse codes is solved with an alternating optimization approach. Finally, the incomplete entries of the given graph signals are estimated using the learnt dictionaries and the sparse coefficients. Experimental results on synthetic and real graph data sets suggest that the proposed method yields promising performance in comparison to reference solutions.","PeriodicalId":156116,"journal":{"name":"2021 IEEE 31st International Workshop on Machine Learning for Signal Processing (MLSP)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129219603","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 5

Recognizing Activities from Egocentric Images with Appearance and Motion Features 从具有外观和运动特征的自我中心图像中识别活动

2021 IEEE 31st International Workshop on Machine Learning for Signal Processing (MLSP) Pub Date : 2021-10-25 DOI: 10.1109/mlsp52302.2021.9596178

Yanhua Chen, Mingtao Pei, Z. Nie

引用次数: 1

Deep Low-Dimensional Spectral Image Representation for Compressive Spectral Reconstruction 压缩光谱重构的深度低维光谱图像表示

2021 IEEE 31st International Workshop on Machine Learning for Signal Processing (MLSP) Pub Date : 2021-10-25 DOI: 10.1109/mlsp52302.2021.9596541

Brayan Monroy, Jorge Bacca, H. Arguello

引用次数: 2

Self-Trained Video Anomaly Detection Based on Teacher-Student Model 基于师生模型的自训练视频异常检测

2021 IEEE 31st International Workshop on Machine Learning for Signal Processing (MLSP) Pub Date : 2021-10-25 DOI: 10.1109/mlsp52302.2021.9596140

Xusheng Wang, Mingtao Pei, Z. Nie

引用次数: 2

Multimodal Graph Coarsening for Interpretable, MRI-Based Brain Graph Neural Network 多模态图粗化可解释，基于核磁共振的脑图神经网络

2021 IEEE 31st International Workshop on Machine Learning for Signal Processing (MLSP) Pub Date : 2021-10-25 DOI: 10.1109/mlsp52302.2021.9596100

引用次数: 4

Convolutional Neural Network Denoising of Focused Ion Beam Micrographs 聚焦离子束显微照片的卷积神经网络去噪

2021 IEEE 31st International Workshop on Machine Learning for Signal Processing (MLSP) Pub Date : 2021-10-25 DOI: 10.1109/mlsp52302.2021.9596272

Minxu Peng, Mertcan Cokbas, U. D. Gallastegi, P. Ishwar, J. Konrad, B. Kulis, V. Goyal

引用次数: 3

Robustness-Aware Filter Pruning for Robust Neural Networks Against Adversarial Attacks 鲁棒神经网络抗对抗性攻击的鲁棒感知滤波剪枝

2021 IEEE 31st International Workshop on Machine Learning for Signal Processing (MLSP) Pub Date : 2021-10-25 DOI: 10.1109/mlsp52302.2021.9596121

Hyuntak Lim, Si-Dong Roh, Sangki Park, Ki-Seok Chung

{"title":"Robustness-Aware Filter Pruning for Robust Neural Networks Against Adversarial Attacks","authors":"Hyuntak Lim, Si-Dong Roh, Sangki Park, Ki-Seok Chung","doi":"10.1109/mlsp52302.2021.9596121","DOIUrl":"https://doi.org/10.1109/mlsp52302.2021.9596121","url":null,"abstract":"Today, neural networks show remarkable performance in various computer vision tasks, but they are vulnerable to adversarial attacks. By adversarial training, neural networks may improve robustness against adversarial attacks. However, it is a time-consuming and resource-intensive task. An earlier study analyzed adversarial attacks on the image features and proposed a robust dataset that would contain only features robust to the adversarial attack. By training with the robust dataset, neural networks can achieve a decent accuracy under adversarial attacks without carrying out time-consuming adversarial perturbation tasks. However, even if a network is trained with the robust dataset, it may still be vulnerable to adversarial attacks. In this paper, to overcome this limitation, we propose a new method called Robustness-aware Filter Pruning (RFP). To the best of our knowledge, it is the first attempt to utilize a filter pruning method to enhance the robustness against the adversarial attack. In the proposed method, the filters that are involved with non-robust features are pruned. With the proposed method, 52.1 % accuracy against one of the most powerful adversarial attacks is achieved, which is 3.8% better than the previous robust dataset training while maintaining clean image test accuracy. Also, our method achieves the best performance when compared with the other filter pruning methods on robust dataset.","PeriodicalId":156116,"journal":{"name":"2021 IEEE 31st International Workshop on Machine Learning for Signal Processing (MLSP)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125927668","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

Online DOA Estimation for Noninteger Linear Antenna Arrays in Coarray Domain 共阵域非整数线性天线阵列的在线DOA估计

2021 IEEE 31st International Workshop on Machine Learning for Signal Processing (MLSP) Pub Date : 2021-10-25 DOI: 10.1109/mlsp52302.2021.9596114

Yitian Chen, H. Nosrati, E. Aboutanios

引用次数: 0

A Constrained Linearly Involved Generalized Moreau Enhanced Model and Its Proximal Splitting Algorithm 约束线性涉及广义Moreau增强模型及其近端分裂算法

2021 IEEE 31st International Workshop on Machine Learning for Signal Processing (MLSP) Pub Date : 2021-10-25 DOI: 10.1109/mlsp52302.2021.9596347

Wataru Yata, M. Yamagishi, I. Yamada

引用次数: 1

Object Detection in SAR Via Generative Knowledge Transfer 基于生成知识转移的SAR目标检测

2021 IEEE 31st International Workshop on Machine Learning for Signal Processing (MLSP) Pub Date : 2021-10-25 DOI: 10.1109/mlsp52302.2021.9596254

Xin Lou, Han Wang

引用次数: 3