Railroad is not a Train: Saliency as Pseudo-pixel Supervision for Weakly Supervised Semantic Segmentation
- Authors
- Lee, S[Lee, Seungho]; Lee, M[Lee, Minhyun]; Lee, J[Lee, Jongwuk]; Shim, H[Shim, Hyunjung]
- Issue Date
- 2021
- Publisher
- IEEE COMPUTER SOC
- Citation
- 2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021, pp.5491 - 5501
- Indexed
- SCOPUS
- Journal Title
- 2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021
- Start Page
- 5491
- End Page
- 5501
- URI
- https://scholarworks.bwise.kr/skku/handle/2021.sw.skku/95352
- DOI
- 10.1109/CVPR46437.2021.00545
- ISSN
- 1063-6919
- Abstract
- Existing studies in weakly-supervised semantic segmentation (WSSS) using image-level weak supervision have several limitations: sparse object coverage, inaccurate object boundaries, and co-occurring pixels from non-target objects. To overcome these challenges, we propose a novel framework, namely Explicit Pseudo-pixel Supervision (EPS), which learns from pixel-level feedback by combining two weak supervisions; the image-level label provides the object identity via the localization map and the saliency map from the off-the-shelf saliency detection model offers rich boundaries. We devise a joint training strategy to fully utilize the complementary relationship between both information. Our method can obtain accurate object boundaries and discard co-occurring pixels, thereby significantly improving the quality of pseudo-masks. Experimental results show that the proposed method remarkably outperforms existing methods by resolving key challenges of WSSS and achieves the new state-of-the-art performance on both PASCAL VOC 2012 and MS COCO 2014 datasets. The code is available at https://github.com/halbielee/EPS.
- Files in This Item
- There are no files associated with this item.
- Appears in
Collections - Computing and Informatics > Computer Science and Engineering > 1. Journal Articles
![qrcode](https://api.qrserver.com/v1/create-qr-code/?size=55x55&data=https://scholarworks.bwise.kr/skku/handle/2021.sw.skku/95352)
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.