Learning to Balance Specificity and Invariance for In and Out of Domain Generalization

TL;DR

This paper proposes domain-specific masks that balance invariant and specific features to improve both in-domain and out-of-domain generalization, outperforming existing methods on PACS and DomainNet datasets.

Contribution

Introduction of domain-specific masks that learn a balance of invariant and domain-specific features for enhanced generalization.

Findings

Achieves competitive results on PACS and DomainNet datasets.

Balances domain-invariant and domain-specific features effectively.

Outperforms naive baselines and state-of-the-art methods.

Abstract

We introduce Domain-specific Masks for Generalization, a model for improving both in-domain and out-of-domain generalization performance. For domain generalization, the goal is to learn from a set of source domains to produce a single model that will best generalize to an unseen target domain. As such, many prior approaches focus on learning representations which persist across all source domains with the assumption that these domain agnostic representations will generalize well. However, often individual domains contain characteristics which are unique and when leveraged can significantly aid in-domain recognition performance. To produce a model which best generalizes to both seen and unseen domains, we propose learning domain specific masks. The masks are encouraged to learn a balance of domain-invariant and domain-specific features, thus enabling a model which can benefit from the predictive power of specialized features while retaining the universal applicability of domain-invariant features. We demonstrate competitive performance compared to naive baselines and state-of-the-art methods on both PACS and DomainNet.