LGCVMar 5, 2021

Cycle Self-Training for Domain Adaptation

arXiv:2103.03571v3222 citations
AI Analysis

This addresses the challenge of domain shift for machine learning practitioners by offering a novel self-training approach that is incremental but with strong empirical gains.

The paper tackles the problem of unreliable pseudo-labels in unsupervised domain adaptation by proposing Cycle Self-Training (CST), which cycles between forward and reverse steps to enforce pseudo-label generalization across domains, resulting in significant improvements over state-of-the-art methods on visual recognition and sentiment analysis benchmarks.

Mainstream approaches for unsupervised domain adaptation (UDA) learn domain-invariant representations to narrow the domain shift. Recently, self-training has been gaining momentum in UDA, which exploits unlabeled target data by training with target pseudo-labels. However, as corroborated in this work, under distributional shift in UDA, the pseudo-labels can be unreliable in terms of their large discrepancy from target ground truth. Thereby, we propose Cycle Self-Training (CST), a principled self-training algorithm that explicitly enforces pseudo-labels to generalize across domains. CST cycles between a forward step and a reverse step until convergence. In the forward step, CST generates target pseudo-labels with a source-trained classifier. In the reverse step, CST trains a target classifier using target pseudo-labels, and then updates the shared representations to make the target classifier perform well on the source data. We introduce the Tsallis entropy as a confidence-friendly regularization to improve the quality of target pseudo-labels. We analyze CST theoretically under realistic assumptions, and provide hard cases where CST recovers target ground truth, while both invariant feature learning and vanilla self-training fail. Empirical results indicate that CST significantly improves over the state-of-the-arts on visual recognition and sentiment analysis benchmarks.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes