POEM: Polarization of Embeddings for Domain-Invariant Representations

Abstract

Handling out-of-distribution samples is a long-lasting challenge for deep visual models. In particular, domain generalization (DG) is one of the most relevant tasks that aims to train a model with a generalization capability on novel domains. Most existing DG approaches share the same philosophy to minimize the discrepancy between domains by finding the domain-invariant representations. On the contrary, our proposed method called POEM acquires a strong DG capability by learning domain-invariant and domain-specific representations and polarizing them. Specifically, POEM cotrains category-classifying and domain-classifying embeddings while regularizing them to be orthogonal via minimizing the cosine-similarity between their features, i.e., the polarization of embeddings. The clear separation of embeddings suppresses domain-specific features in the domain-invariant embeddings. The concept of POEM shows a unique direction to enhance the domain robustness of representations that brings considerable and consistent performance gains when combined with existing DG methods. Extensive simulation results in popular DG benchmarks with the PACS, VLCS, OfficeHome, TerraIncognita, and DomainNet datasets show that POEM indeed facilitates the category-classifying embedding to be more domain-invariant.

In Proceedings of the 37th AAAI Conference on Artificial Intelligence (AAAI) 2023, Washington D.C. USA

References in corpus (9)

• Unsupervised Domain Adaptation by Backpropagation
• Domain Generalization via Model-Agnostic Learning of Semantic Features
• Deep CORAL: Correlation Alignment for Deep Domain Adaptation
• Learning to Generalize: Meta-Learning for Domain Generalization
• Learning Robust Representations by Projecting Superficial Statistics Out
• Efficient Domain Generalization via Common-Specific Low-Rank Decomposition
• Ensemble of Averages: Improving Model Selection and Boosting Performance in Domain Generalization
• Learning from Extrinsic and Intrinsic Supervisions for Domain Generalization
• Domain Generalization by Mutual-Information Regularization with Pre-trained Models