AdvST: Revisiting Data Augmentations for Single Domain Generalization

TL;DR

AdvST introduces a novel adversarial semantics transformation approach for single domain generalization, effectively augmenting data to improve model robustness against domain shifts, with theoretical and empirical validation across multiple datasets.

Contribution

The paper proposes AdvST, a learnable semantics transformation method that enhances data augmentation for SDG, backed by theoretical analysis and state-of-the-art experimental results.

Findings

AdvST achieves the best average SDG performance on multiple datasets.

Theoretically, AdvST optimizes a distributionally robust objective.

AdvST effectively expands target domain data coverage.

Abstract

Single domain generalization (SDG) aims to train a robust model against unknown target domain shifts using data from a single source domain. Data augmentation has been proven an effective approach to SDG. However, the utility of standard augmentations, such as translate, or invert, has not been fully exploited in SDG; practically, these augmentations are used as a part of a data preprocessing procedure. Although it is intuitive to use many such augmentations to boost the robustness of a model to out-of-distribution domain shifts, we lack a principled approach to harvest the benefit brought from multiple these augmentations. Here, we conceptualize standard data augmentations with learnable parameters as semantics transformations that can manipulate certain semantics of a sample, such as the geometry or color of an image. Then, we propose Adversarial learning with Semantics Transformations (AdvST) that augments the source domain data with semantics transformations and learns a robust model with the augmented data. We theoretically show that AdvST essentially optimizes a distributionally robust optimization objective defined on a set of semantics distributions induced by the parameters of semantics transformations. We demonstrate that AdvST can produce samples that expand the coverage on target domain data. Compared with the state-of-the-art methods, AdvST, despite being a simple method, is surprisingly competitive and achieves the best average SDG performance on the Digits, PACS, and DomainNet datasets. Our code is available at https://github.com/gtzheng/AdvST.