Domain-aware Triplet loss in Domain Generalization

TL;DR

This paper introduces a domain-aware triplet loss for domain generalization that encourages clustering of semantic features while dispersing domain-specific information, improving model robustness across multiple datasets.

Contribution

The paper proposes a novel domain-aware triplet loss that disperses domain information in the embedding space, contrasting with previous distribution alignment methods.

Findings

Outperforms state-of-the-art on PACS, VLCS, and Office-Home datasets.

Significantly better results on RegnetY-16.

Effective normalization reduces covariate shift in embedding features.

Abstract

Despite much progress being made in the field of object recognition with the advances of deep learning, there are still several factors negatively affecting the performance of deep learning models. Domain shift is one of these factors and is caused by discrepancies in the distributions of the testing and training data. In this paper, we focus on the problem of compact feature clustering in domain generalization to help optimize the embedding space from multi-domain data. We design a domainaware triplet loss for domain generalization to help the model to not only cluster similar semantic features, but also to disperse features arising from the domain. Unlike previous methods focusing on distribution alignment, our algorithm is designed to disperse domain information in the embedding space. The basic idea is motivated based on the assumption that embedding features can be clustered based on domain information, which is mathematically and empirically supported in this paper. In addition, during our exploration of feature clustering in domain generalization, we note that factors affecting the convergence of metric learning loss in domain generalization are more important than the pre-defined domains. To solve this issue, we utilize two methods to normalize the embedding space, reducing the internal covariate shift of the embedding features. The ablation study demonstrates the effectiveness of our algorithm. Moreover, the experiments on the benchmark datasets, including PACS, VLCS and Office-Home, show that our method outperforms related methods focusing on domain discrepancy. In particular, our results on RegnetY-16 are significantly better than state-of-the-art methods on the benchmark datasets. Our code will be released at https://github.com/workerbcd/DCT