Learning to Learn Domain-invariant Parameters for Domain Generalization

TL;DR

This paper introduces a novel approach for domain generalization in deep neural networks by focusing on domain-invariant parameters, using two modules to enhance model focus and achieve state-of-the-art results.

Contribution

The paper proposes two modules, DDC and DIGB, that guide models to emphasize domain-invariant parameters, improving generalization across unseen domains.

Findings

Achieved state-of-the-art performance on two benchmarks.

Demonstrated strong generalization capability.

Enhanced focus on domain-invariant parameters.

Abstract

Due to domain shift, deep neural networks (DNNs) usually fail to generalize well on unknown test data in practice. Domain generalization (DG) aims to overcome this issue by capturing domain-invariant representations from source domains. Motivated by the insight that only partial parameters of DNNs are optimized to extract domain-invariant representations, we expect a general model that is capable of well perceiving and emphatically updating such domain-invariant parameters. In this paper, we propose two modules of Domain Decoupling and Combination (DDC) and Domain-invariance-guided Backpropagation (DIGB), which can encourage such general model to focus on the parameters that have a unified optimization direction between pairs of contrastive samples. Our extensive experiments on two benchmarks have demonstrated that our proposed method has achieved state-of-the-art performance with strong generalization capability.