Score-based Aggregation for Attention Modules in Image Classification Tasks
- Authors
- Lee, C; Chung, KS
- Issue Date
- Nov-2019
- Publisher
- Institute of Electrical and Electronics Engineers Inc.
- Citation
- Proceedings of the 2019 IEEE 4th International Conference on Technology, Informatics, Management, Engineering and Environment, TIME-E 2019, pp.43 - 48
- Indexed
- SCOPUS
- Journal Title
- Proceedings of the 2019 IEEE 4th International Conference on Technology, Informatics, Management, Engineering and Environment, TIME-E 2019
- Start Page
- 43
- End Page
- 48
- URI
- https://scholarworks.bwise.kr/hanyang/handle/2021.sw.hanyang/146736
- DOI
- 10.1109/TIME-E47986.2019.9353302
- Abstract
- Deep Convolutional Neural Networks (CNNs) have been widely used for various computer vision tasks because they hierarchically extract bountiful features from a highdimensional image. Also, some CNNs incorporate channel attention mechanisms that re-scale each channel of intermediate feature maps based on their importance. The channel attention modules squeeze the spatial information of a feature into a representative value to transform it as a re-scaling value. In order to reduce the amount of information, attention modules have utilized hand-designed pooling functions such as max pooling or average pooling which have been widely adopted in CNNs, because they add negligible computational complexity. However, a significant amount of spatial information is lost due to these pooling functions. In this paper, we propose a generalized pooling function that scales down spatial information with respect to the importance of each pixel. Unlike max pooling or average pooling, our score-based aggregation is capable of flexibly adjusting to input. Also, the score-based aggregation function learns how to squeeze the spatial information into the must appropriate representative value, which will convert the pooling into a spatial attention mechanism. Finally, we propose a novel method called Score-based Aggregated Attention Module (SAAM) that utilizes the proposed score-based aggregation. Our experimental results on CIFAR-10 and CIFAR-100 datasets demonstrate that SAAM achieves the highest classification accuracy improvement among existing channel attention modules since the score-based aggregation in SAAM is a more dynamic and effective method than the hand-designed aggregations.
- Files in This Item
-
Go to Link
- Appears in
Collections - 서울 공과대학 > 서울 융합전자공학부 > 1. Journal Articles
![qrcode](https://api.qrserver.com/v1/create-qr-code/?size=55x55&data=https://scholarworks.bwise.kr/hanyang/handle/2021.sw.hanyang/146736)
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.