FixCLR: Negative-Class Contrastive Learning for Semi-Supervised Domain Generalization

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Son, Ha Min, Rezaei, Shahbaz, Liu, Xin
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912450450817024
author Son, Ha Min
Rezaei, Shahbaz
Liu, Xin
author_facet Son, Ha Min
Rezaei, Shahbaz
Liu, Xin
contents Semi-supervised domain generalization (SSDG) aims to solve the problem of generalizing to out-of-distribution data when only a few labels are available. Due to label scarcity, applying domain generalization methods often underperform. Consequently, existing SSDG methods combine semi-supervised learning methods with various regularization terms. However, these methods do not explicitly regularize to learn domains invariant representations across all domains, which is a key goal for domain generalization. To address this, we introduce FixCLR. Inspired by success in self-supervised learning, we change two crucial components to adapt contrastive learning for explicit domain invariance regularization: utilization of class information from pseudo-labels and using only a repelling term. FixCLR can also be added on top of most existing SSDG and semi-supervised methods for complementary performance improvements. Our research includes extensive experiments that have not been previously explored in SSDG studies. These experiments include benchmarking different improvements to semi-supervised methods, evaluating the performance of pretrained versus non-pretrained models, and testing on datasets with many domains. Overall, FixCLR proves to be an effective SSDG method, especially when combined with other semi-supervised methods.
format Preprint
id arxiv_https___arxiv_org_abs_2506_20841
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle FixCLR: Negative-Class Contrastive Learning for Semi-Supervised Domain Generalization
Son, Ha Min
Rezaei, Shahbaz
Liu, Xin
Computer Vision and Pattern Recognition
Artificial Intelligence
Semi-supervised domain generalization (SSDG) aims to solve the problem of generalizing to out-of-distribution data when only a few labels are available. Due to label scarcity, applying domain generalization methods often underperform. Consequently, existing SSDG methods combine semi-supervised learning methods with various regularization terms. However, these methods do not explicitly regularize to learn domains invariant representations across all domains, which is a key goal for domain generalization. To address this, we introduce FixCLR. Inspired by success in self-supervised learning, we change two crucial components to adapt contrastive learning for explicit domain invariance regularization: utilization of class information from pseudo-labels and using only a repelling term. FixCLR can also be added on top of most existing SSDG and semi-supervised methods for complementary performance improvements. Our research includes extensive experiments that have not been previously explored in SSDG studies. These experiments include benchmarking different improvements to semi-supervised methods, evaluating the performance of pretrained versus non-pretrained models, and testing on datasets with many domains. Overall, FixCLR proves to be an effective SSDG method, especially when combined with other semi-supervised methods.
title FixCLR: Negative-Class Contrastive Learning for Semi-Supervised Domain Generalization
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2506.20841