.png){kind=icon}
返回
Learning double weights via data augmentation for robust sparse and collaborative representation-based classification
.png){kind=icon}
PRE
AI
DOI：10.1007/s11042-020-08918-2.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Image classification is a hot technique applied in many multimedia systems, where both l(1) and l(2) regularizations have shown potential for robust sparse representation-based image classification. However, previous studies showed that l(1) or l(2) alone cannot ensure a robust result. The robustness of a classifier depends on the nature of the dataset most of the time. What is worse, data augmentation may make the dataset more complicated, which leads a sparse model become harder to optimize. In this paper, a novel sparse representation that learns double weights through data augmentation is proposed for robust image classification. The first weight combines the two coefficients solved by l(1) and l(2) regularizations to obtain a more discriminative representation, while the second weight integrates the residuals obtained from the original and virtual samples, to take full advantage of diversity created by data augmentation. The double-weight process builds a robust model that is able to deal with the augmented but variational datasets. Experiments on popular facial and object datasets demonstrate the promising performance of the proposed method. Learning double weights via sample virtualization is helpful to develop multimedia applications.
Keyword:
Image classification
Sparse representation
Regularization
Augmentation
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
3
论文数:
1.9W
被引数:
3.2W
机构
引用论文
.png){kind=icon}
Room temperature photo-promoted iron-catalysed arene C–H alkenylation without Grignard reagents
PREAI
分享收藏分享收藏分享收藏Copper ferrocyanide loaded track etched membrane: an effective cesium adsorbent负载亚铁氰化铜的径迹蚀刻膜: 一种有效的铯吸附剂
PREAI
分享收藏
查看更多内容