OpenCoS: Contrastive Semi-supervised Learning for Handling Open-Set Unlabeled Data
- Title
- OpenCoS: Contrastive Semi-supervised Learning for Handling Open-Set Unlabeled Data
- Author
- 윤석민
- Keywords
- Contrastive learning; Realistic semi-supervised learning; Open-set semi-supervised learning; Class-distribution mismatch
- Issue Date
- 2023-02-16
- Publisher
- Springer Verlag
- Citation
- Lecture Notes in Computer Science, page. 134-149
- 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.
- URI
- https://link.springer.com/chapter/10.1007/978-3-031-25063-7_9https://repository.hanyang.ac.kr/handle/20.500.11754/191419
- ISSN
- 0302-9743; 1611-3349
- DOI
- https://doi.org/10.1007/978-3-031-25063-7
- Appears in Collections:
- ETC[S] > 연구정보
- Files in This Item:
There are no files associated with this item.
- Export
- RIS (EndNote)
- XLS (Excel)
- XML