Domain Generalization with MixStyle

TL;DR

MixStyle is a simple yet effective domain generalization technique that mixes style features at the instance level during training, enhancing model robustness to unseen domains across various tasks.

Contribution

The paper introduces MixStyle, a novel style-mixing method that improves domain generalization by synthesizing diverse styles during training.

Findings

MixStyle improves generalization in CNNs across multiple tasks.

MixStyle is easy to implement and integrates seamlessly with mini-batch training.

Experimental results show significant performance gains on unseen domains.

Abstract

Though convolutional neural networks (CNNs) have demonstrated remarkable ability in learning discriminative features, they often generalize poorly to unseen domains. Domain generalization aims to address this problem by learning from a set of source domains a model that is generalizable to any unseen domain. In this paper, a novel approach is proposed based on probabilistically mixing instance-level feature statistics of training samples across source domains. Our method, termed MixStyle, is motivated by the observation that visual domain is closely related to image style (e.g., photo vs.~sketch images). Such style information is captured by the bottom layers of a CNN where our proposed style-mixing takes place. Mixing styles of training instances results in novel domains being synthesized implicitly, which increase the domain diversity of the source domains, and hence the generalizability of the trained model. MixStyle fits into mini-batch training perfectly and is extremely easy to implement. The effectiveness of MixStyle is demonstrated on a wide range of tasks including category classification, instance retrieval and reinforcement learning.