FixCLR: Negative-Class Contrastive Learning for Semi-Supervised Domain Generalization
This addresses the challenge of generalizing to out-of-distribution data with limited labels, which is incremental as it builds on existing SSDG and semi-supervised approaches.
The paper tackles the problem of semi-supervised domain generalization (SSDG) by introducing FixCLR, a method that adapts contrastive learning to explicitly regularize for domain-invariant representations, resulting in improved performance when combined with other semi-supervised methods.
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.