Timezone: »

 
Poster
Exploiting Domain-Specific Features to Enhance Domain Generalization
Manh-Ha Bui · Toan Tran · Anh Tran · Dinh Phung

Wed Dec 08 12:30 AM -- 02:00 AM (PST) @ Virtual
in Poster Session 3 »

Domain Generalization (DG) aims to train a model, from multiple observed source domains, in order to perform well on unseen target domains. To obtain the generalization capability, prior DG approaches have focused on extracting domain-invariant information across sources to generalize on target domains, while useful domain-specific information which strongly correlates with labels in individual domains and the generalization to target domains is usually ignored. In this paper, we propose meta-Domain Specific-Domain Invariant (mDSDI) - a novel theoretically sound framework that extends beyond the invariance view to further capture the usefulness of domain-specific information. Our key insight is to disentangle features in the latent space while jointly learning both domain-invariant and domain-specific features in a unified framework. The domain-specific representation is optimized through the meta-learning framework to adapt from source domains, targeting a robust generalization on unseen domains. We empirically show that mDSDI provides competitive results with state-of-the-art techniques in DG. A further ablation study with our generated dataset, Background-Colored-MNIST, confirms the hypothesis that domain-specific is essential, leading to better results when compared with only using domain-invariant.

Keywords: Meta Learning · Domain Adaptation · Representation Learning

Author Information

Manh-Ha Bui (VinAI Research)
Toan Tran (Vinai artificial intelligence application and research JSC)
Anh Tran (VinAI Research)
Dinh Phung (Monash University)

More from the Same Authors