Recursive Multi-Scale Channel-Spatial Attention for Fine-Grained Image Classification
-
- LIU Dichao
- Graduate School of Informatics, Nagoya University
-
- WANG Yu
- College of Information Science and Engineering, Ritsumeikan University
-
- MASE Kenji
- Graduate School of Informatics, Nagoya University
-
- KATO Jien
- College of Information Science and Engineering, Ritsumeikan University
抄録
<p>Fine-grained image classification is a difficult problem, and previous studies mainly overcome this problem by locating multiple discriminative regions in different scales and then aggregating complementary information explored from the located regions. However, locating discriminative regions introduces heavy overhead and is not suitable for real-world application. In this paper, we propose the recursive multi-scale channel-spatial attention module (RMCSAM) for addressing this problem. Following the experience of previous research on fine-grained image classification, RMCSAM explores multi-scale attentional information. However, the attentional information is explored by recursively refining the deep feature maps of a convolutional neural network (CNN) to better correspond to multi-scale channel-wise and spatial-wise attention, instead of localizing attention regions. In this way, RMCSAM provides a lightweight module that can be inserted into standard CNNs. Experimental results show that RMCSAM can improve the classification accuracy and attention capturing ability over baselines. Also, RMCSAM performs better than other state-of-the-art attention modules in fine-grained image classification, and is complementary to some state-of-the-art approaches for fine-grained image classification. Code is available at https://github.com/Dichao-Liu/Recursive-Multi-Scale-Channel-Spatial-Attention-Module.</p>
収録刊行物
-
- IEICE Transactions on Information and Systems
-
IEICE Transactions on Information and Systems E105.D (3), 713-726, 2022-03-01
一般社団法人 電子情報通信学会
- Tweet
キーワード
詳細情報 詳細情報について
-
- CRID
- 1390573242455038848
-
- NII論文ID
- 130008165626
-
- ISSN
- 17451361
- 09168532
-
- 本文言語コード
- en
-
- データソース種別
-
- JaLC
- Crossref
- CiNii Articles
- KAKEN
-
- 抄録ライセンスフラグ
- 使用不可