A3: Active Adversarial Alignment for Source-Free Domain Adaptation

TL;DR

A3 introduces a novel framework for source-free unsupervised domain adaptation that combines active learning, adversarial training, and self-supervised methods to improve domain alignment and reduce noise without source data.

Contribution

It presents a new active adversarial alignment approach that effectively integrates active sampling, adversarial loss, and self-supervised learning for source-free UDA.

Findings

Improves domain alignment without source data.

Reduces noise from pseudo-labels.

Enhances adaptation robustness.

Abstract

Unsupervised domain adaptation (UDA) aims to transfer knowledge from a labeled source domain to an unlabeled target domain. Recent works have focused on source-free UDA, where only target data is available. This is challenging as models rely on noisy pseudo-labels and struggle with distribution shifts. We propose Active Adversarial Alignment (A3), a novel framework combining self-supervised learning, adversarial training, and active learning for robust source-free UDA. A3 actively samples informative and diverse data using an acquisition function for training. It adapts models via adversarial losses and consistency regularization, aligning distributions without source data access. A3 advances source-free UDA through its synergistic integration of active and adversarial learning for effective domain alignment and noise reduction.