OpenCoS: Contrastive Semi-supervised Learning for Handling Open-set Unlabeled Data
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.
Cite
@article{arxiv.2107.08943,
title = {OpenCoS: Contrastive Semi-supervised Learning for Handling Open-set Unlabeled Data},
author = {Jongjin Park and Sukmin Yun and Jongheon Jeong and Jinwoo Shin},
journal= {arXiv preprint arXiv:2107.08943},
year = {2022}
}
Comments
ECCV Workshop on Learning from Limited and Imperfect Data, 2022. Code is available at https://github.com/alinlab/OpenCoS