The Devil is in the Channels: Mutual-Channel Loss for Fine-Grained Image Classification | |
Chang, Dongliang2; Ding, Yifeng2; Xie, Jiyang2; Bhunia, Ayan Kumar1; Li, Xiaoxu3; Ma, Zhanyu2; Wu, Ming2; Guo, Jun2; Song, Yi-Zhe1 | |
刊名 | IEEE Transactions on Image Processing |
2020 | |
卷号 | 29页码:4683-4695 |
关键词 | Complex networks Deep learning Training aircraft Attention mechanisms Feature representation Fine grained Image Categorization Loss functions mutual channel State-of-the-art performance Visual classification |
ISSN号 | 10577149 |
DOI | 10.1109/TIP.2020.2973812 |
英文摘要 | The key to solving fine-grained image categorization is finding discriminate and local regions that correspond to subtle visual traits. Great strides have been made, with complex networks designed specifically to learn part-level discriminate feature representations. In this paper, we show that it is possible to cultivate subtle details without the need for overly complicated network designs or training mechanisms - a single loss is all it takes. The main trick lies with how we delve into individual feature channels early on, as opposed to the convention of starting from a consolidated feature map. The proposed loss function, termed as mutual-channel loss (MC-Loss), consists of two channel-specific components: a discriminality component and a diversity component. The discriminality component forces all feature channels belonging to the same class to be discriminative, through a novel channel-wise attention mechanism. The diversity component additionally constraints channels so that they become mutually exclusive across the spatial dimension. The end result is therefore a set of feature channels, each of which reflects different locally discriminative regions for a specific class. The MC-Loss can be trained end-to-end, without the need for any bounding-box/part annotations, and yields highly discriminative regions during inference. Experimental results show our MC-Loss when implemented on top of common base networks can achieve state-of-the-art performance on all four fine-grained categorization datasets (CUB-Birds, FGVC-Aircraft, Flowers-102, and Stanford Cars). Ablative studies further demonstrate the superiority of the MC-Loss when compared with other recently proposed general-purpose losses for visual classification, on two different base networks. Codes are available at: https://github.com/dongliangchang/Mutual-Channel-Loss. © 1992-2012 IEEE. |
WOS研究方向 | Computer Science ; Engineering |
语种 | 英语 |
出版者 | Institute of Electrical and Electronics Engineers Inc., United States |
WOS记录号 | WOS:000526697100002 |
内容类型 | 期刊论文 |
源URL | [http://ir.lut.edu.cn/handle/2XXMBERH/115639] |
专题 | 兰州理工大学 |
作者单位 | 1.Centre for Vision, Speech and Signal Processing, University of Surrey, Guildford, United Kingdom; 2.Pattern Recognition and Intelligent System Laboratory, School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China; 3.School of Computer and Communication, Lanzhou University of Technology, Lanzhou, China |
推荐引用方式 GB/T 7714 | Chang, Dongliang,Ding, Yifeng,Xie, Jiyang,et al. The Devil is in the Channels: Mutual-Channel Loss for Fine-Grained Image Classification[J]. IEEE Transactions on Image Processing,2020,29:4683-4695. |
APA | Chang, Dongliang.,Ding, Yifeng.,Xie, Jiyang.,Bhunia, Ayan Kumar.,Li, Xiaoxu.,...&Song, Yi-Zhe.(2020).The Devil is in the Channels: Mutual-Channel Loss for Fine-Grained Image Classification.IEEE Transactions on Image Processing,29,4683-4695. |
MLA | Chang, Dongliang,et al."The Devil is in the Channels: Mutual-Channel Loss for Fine-Grained Image Classification".IEEE Transactions on Image Processing 29(2020):4683-4695. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论