Daso: Distribution-aware semantics-oriented pseudo-label for imbalanced semi-supervised learning
- Authors
- Oh, Youngtaek; Kim, Dong Jin; Kweon, In So
- Issue Date
- Jun-2022
- Publisher
- IEEE computer society & The computer vision foundation (CVF)
- Keywords
- Self- & semi- & meta- Machine learning; Transfer/low-shot/long-tail learning
- Citation
- Conference on Computer Vision and Pattern Recognition, pp.9776 - 9786
- Indexed
- SCOPUS
- Journal Title
- Conference on Computer Vision and Pattern Recognition
- Start Page
- 9776
- End Page
- 9786
- URI
- https://scholarworks.bwise.kr/hanyang/handle/2021.sw.hanyang/188942
- DOI
- 10.1109/CVPR52688.2022.00956
- ISSN
- 1063-6919
- Abstract
- The capability of the traditional semi-supervised learning (SSL) methods is far from real-world application due to severely biased pseudo-labels caused by (1) class imbalance and (2) class distribution mismatch between labeled and unlabeled data. This paper addresses such a relatively under-explored problem. First, we propose a general pseudo-labeling framework that class-adaptively blends the semantic pseudo-label from a similarity-based classifier to the linear one from the linear classifier, after making the observation that both types of pseudo-labels have complementary properties in terms of bias. We further introduce a novel semantic alignment loss to establish balanced feature representation to reduce the biased predictions from the classifier. We term the whole framework as Distribution-Aware Semantics-Oriented (DASO) Pseudo-label. We conduct extensive experiments in a wide range of imbalanced benchmarks: CIFAR10/100-LT, STL10-LT, and large-scale long-tailed Semi-Aves with open-set class, and demonstrate that, the proposed DASO framework reliably improves SSL learners with unlabeled data especially when both (1) class imbalance and (2) distribution mismatch dominate.
- Files in This Item
-
Go to Link
- Appears in
Collections - ETC > 1. Journal Articles
![qrcode](https://api.qrserver.com/v1/create-qr-code/?size=55x55&data=https://scholarworks.bwise.kr/hanyang/handle/2021.sw.hanyang/188942)
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.