Work

DASO: Distribution-Aware Semantics-Oriented Pseudo-label for Imbalanced Semi-Supervised Learning

Year: 2022

Type: conference-paper

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.

Source: IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings

DOI: 10.1109/cvpr52688.2022.00956

Authors: Youngtaek Oh, Dong-Jin Kim, In So Kweon

Institutions: Korea Advanced Institute of Science and Technology, International Computer Science Institute, University of California, Berkeley

Language: English

Topic: Domain Adaptation and Few-Shot Learning

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

SDG: Reduced inequalities

Open Access status: green

Funders: National Research Foundation, National Research Foundation of Korea, Ministry of Science and ICT, South Korea