OpenCoS: Contrastive Semi-supervised Learning for Handling Open-Set Unlabeled Data
- Authors
- Park, Jongjin; Yun, Sukmin; Jeong, Jongheon; Shin, Jinwoo
- Issue Date
- Oct-2022
- Publisher
- Springer Verlag
- Keywords
- Class-distribution mismatch; Contrastive learning; Open-set semi-supervised learning; Realistic semi-supervised learning
- Citation
- Computer Vision – ECCV 2022 Workshops Tel Aviv, Israel, October 23–27, 2022, Proceedings, Part II, pp 134 - 149
- Pages
- 16
- Indexed
- SCOPUS
- Journal Title
- Computer Vision – ECCV 2022 Workshops Tel Aviv, Israel, October 23–27, 2022, Proceedings, Part II
- Start Page
- 134
- End Page
- 149
- URI
- https://scholarworks.bwise.kr/erica/handle/2021.sw.erica/118656
- DOI
- 10.1007/978-3-031-25063-7_9
- Abstract
- Semi-supervised learning (SSL) has been a powerful strategy to incorporate few labels in learning better representations. In this paper, we focus on a practical scenario that one aims to apply SSL when unlabeled data may contain out-of-class samples - those that cannot have one-hot encoded labels from a closed-set of classes in label data, i.e., the unlabeled data is an open-set. Specifically, we introduce OpenCoS, a simple framework for handling this realistic semi-supervised learning scenario based upon a recent framework of self-supervised visual representation learning. We first observe that the out-of-class samples in the open-set unlabeled dataset can be identified effectively via self-supervised contrastive learning. Then, OpenCoS utilizes this information to overcome the failure modes in the existing state-of-the-art semi-supervised methods, by utilizing one-hot pseudo-labels and soft-labels for the identified in- and out-of-class unlabeled data, respectively. Our extensive experimental results show the effectiveness of OpenCoS under the presence of out-of-class samples, fixing up the state-of-the-art semi-supervised methods to be suitable for diverse scenarios involving open-set unlabeled data. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.
- Files in This Item
-
Go to Link
- Appears in
Collections - COLLEGE OF COMPUTING > DEPARTMENT OF ARTIFICIAL INTELLIGENCE > 1. Journal Articles
![qrcode](https://api.qrserver.com/v1/create-qr-code/?size=55x55&data=https://scholarworks.bwise.kr/erica/handle/2021.sw.erica/118656)
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.