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.
@article{arxiv.2211.04582,
title = {Learning to Learn Domain-invariant Parameters for Domain Generalization},
author = {Feng Hou and Yao Zhang and Yang Liu and Jin Yuan and Cheng Zhong and Yang Zhang and Zhongchao Shi and Jianping Fan and Zhiqiang He},
journal= {arXiv preprint arXiv:2211.04582},
year = {2022}
}