LFME: A Simple Framework for Learning from Multiple Experts in Domain Generalization

Liang Chen, Yong Zhang, Yibing Song, Zhiqiang Shen, Lingqiao Liu

Keywords: Domain generalization, Knowledge distillation

TL;DR: A new knowledge distillation paradigm to enable effective learning from multiple experts for domain generalization

Abstract: Domain generalization (DG) methods aim to maintain good performance in an unseen target domain by using training data from multiple source domains. While success on certain occasions are observed, enhancing the baseline across most scenarios remains challenging. This work introduces a simple yet effective framework, dubbed learning from multiple experts (LFME), that aims to make the target model an expert in all source domains to improve DG. Specifically, besides learning the target model used in inference, LFME will also train multiple experts specialized in different domains, whose output probabilities provide professional guidance by simply regularizing the logit of the target model. Delving deep into the framework, we reveal that the introduced logit regularization term implicitly provides effects of enabling the target model to harness more information, and mining hard samples from the experts during training. Extensive experiments on benchmarks from different DG tasks demonstrate that LFME is consistently beneficial to the baseline and can achieve comparable performance to existing arts. Code is available at https://github.com/liangchen527/LFME.

Primary Area: Machine vision

Submission Number: 11736