Learning to Detour: Shortcut Mitigating Augmentation for Weakly Supervised Semantic Segmentation
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Kwon, Junehyoung | - |
dc.contributor.author | Lee, Eunju | - |
dc.contributor.author | Cho, Yunsung | - |
dc.contributor.author | Kim, Youngbin | - |
dc.date.accessioned | 2024-05-21T05:30:33Z | - |
dc.date.available | 2024-05-21T05:30:33Z | - |
dc.date.issued | 2024 | - |
dc.identifier.uri | https://scholarworks.bwise.kr/cau/handle/2019.sw.cau/73852 | - |
dc.description.abstract | Weakly supervised semantic segmentation (WSSS) employing weak forms of labels has been actively studied to alleviate the annotation cost of acquiring pixel-level labels. However, classifiers trained on biased datasets tend to exploit shortcut features and make predictions based on spurious correlations between certain backgrounds and objects, leading to a poor generalization performance. In this paper, we propose shortcut mitigating augmentation (SMA) for WSSS, which generates synthetic representations of object-background combinations not seen in the training data to reduce the use of shortcut features. Our approach disentangles the object-relevant and background features. We then shuffle and combine the disentangled representations to create synthetic features of diverse object-background combinations. SMA-trained classifier depends less on contexts and focuses more on the target object when making predictions. In addition, we analyzed the behavior of the classifier on shortcut usage after applying our augmentation using an attribution method-based metric. The proposed method achieved the improved performance of semantic segmentation result on PASCAL VOC 2012 and MS COCO 2014 datasets. © 2024 IEEE. | - |
dc.format.extent | 10 | - |
dc.language | 영어 | - |
dc.language.iso | ENG | - |
dc.publisher | Institute of Electrical and Electronics Engineers Inc. | - |
dc.title | Learning to Detour: Shortcut Mitigating Augmentation for Weakly Supervised Semantic Segmentation | - |
dc.type | Article | - |
dc.identifier.doi | 10.1109/WACV57701.2024.00087 | - |
dc.identifier.bibliographicCitation | Proceedings - 2024 IEEE Winter Conference on Applications of Computer Vision, WACV 2024, pp 808 - 817 | - |
dc.description.isOpenAccess | N | - |
dc.identifier.scopusid | 2-s2.0-85191732093 | - |
dc.citation.endPage | 817 | - |
dc.citation.startPage | 808 | - |
dc.citation.title | Proceedings - 2024 IEEE Winter Conference on Applications of Computer Vision, WACV 2024 | - |
dc.type.docType | Conference paper | - |
dc.subject.keywordAuthor | Algorithms | - |
dc.subject.keywordAuthor | Algorithms | - |
dc.subject.keywordAuthor | and algorithms | - |
dc.subject.keywordAuthor | formulations | - |
dc.subject.keywordAuthor | Image recognition and understanding | - |
dc.subject.keywordAuthor | Machine learning architectures | - |
dc.description.journalRegisteredClass | scopus | - |
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.
84, Heukseok-ro, Dongjak-gu, Seoul, Republic of Korea (06974)02-820-6194
COPYRIGHT 2019 Chung-Ang University All Rights Reserved.
Certain data included herein are derived from the © Web of Science of Clarivate Analytics. All rights reserved.
You may not copy or re-distribute this material in whole or in part without the prior written consent of Clarivate Analytics.