Shuffle Augmentation of Features from Unlabeled Data for Unsupervised Domain Adaptation

TL;DR

This paper introduces Shuffle Augmentation of Features (SAF), a novel framework for unsupervised domain adaptation that enhances classifiers by leveraging target feature representations, leading to improved transfer learning performance.

Contribution

SAF is a new UDA framework that provides classifiers with supervisory signals from target features, improving domain adaptation without target labels.

Findings

SAF can be integrated into existing adversarial UDA models.

SAF improves classification accuracy across multiple datasets.

SAF effectively guides classifiers to find comprehensive class boundaries.

Abstract

Unsupervised Domain Adaptation (UDA), a branch of transfer learning where labels for target samples are unavailable, has been widely researched and developed in recent years with the help of adversarially trained models. Although existing UDA algorithms are able to guide neural networks to extract transferable and discriminative features, classifiers are merely trained under the supervision of labeled source data. Given the inevitable discrepancy between source and target domains, the classifiers can hardly be aware of the target classification boundaries. In this paper, Shuffle Augmentation of Features (SAF), a novel UDA framework, is proposed to address the problem by providing the classifier with supervisory signals from target feature representations. SAF learns from the target samples, adaptively distills class-aware target features, and implicitly guides the classifier to find comprehensive class borders. Demonstrated by extensive experiments, the SAF module can be integrated into any existing adversarial UDA models to achieve performance improvements.