Efficient Spatial-Attention Module for Human Pose Estimation
- Abstract
- Not only for human pose estimation but also other machine vision tasks (e.g. object recognition, semantic segmentation, image classification), convolution neural networks (CNNs) have obtained the highest performance today. Besides, their performance over other traditional networks is shown by the Attention Module (AM). Hence, this paper focuses on a valuable feed-forward AM for CNNs. First, feed the feature map into the attention module after a stage in the backbone network, divided into two different dimensions, channel and spatial. After that, by multiplication, the AM combines these two feature maps and gives them to the next stage in the backbone. In long-range dependencies (channel) and spatial data, the network can capture more information, which can gain better precision efficiency. Our experimental findings would also demonstrate the disparity between the use of the attention module and current methods. As a result, with the change to make the spatial better, the expected joint heatmap retains the accuracy while decreasing the number of parameters. In comparison, the proposed architecture benefits more than the baseline by 1.3 points in AP. In addition, the proposed network was trained on the benchmarks of COCO 2017, which is now an open dataset.
- Author(s)
- 쩐 띠엔 닷; 보 수언 투이; 웬 주이 린; 조강현
- Issued Date
- 2021
- Type
- Article
- Keyword
- Attention module; Deep learning; Human pose estimation; Spatial-attention module
- DOI
- 10.1007/978-3-030-81638-4_20
- URI
- https://oak.ulsan.ac.kr/handle/2021.oak/9157
https://ulsan-primo.hosted.exlibrisgroup.com/primo-explore/fulldisplay?docid=TN_cdi_springer_books_10_1007_978_3_030_81638_4_20&context=PC&vid=ULSAN&lang=ko_KR&search_scope=default_scope&adaptor=primo_central_multiple_fe&tab=default_tab&query=any,contains,Efficient%20Spatial-Attention%20Module%20for%20Human%20Pose%20Estimation&offset=0&pcAvailability=true
- Publisher
- Communications in Computer and Information Science
- Location
- 스위스
- Language
- 영어
- ISSN
- 1865-0929
- Citation Volume
- 1405
- Citation Number
- 1
- Citation Start Page
- 242
- Citation End Page
- 250
-
Appears in Collections:
- Engineering > IT Convergence
- Authorize & License
-
- Files in This Item:
-
Items in Repository are protected by copyright, with all rights reserved, unless otherwise indicated.