Cycle Self-Training for Domain Adaptation
arXiv:2103.03571
Abstract
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.
References in corpus (21)
- PyTorch: An Imperative Style, High-Performance Deep Learning Library
- Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
- How transferable are features in deep neural networks?
- Learning Transferable Features with Deep Adaptation Networks
- On Calibration of Modern Neural Networks
- Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results
- Conditional Adversarial Domain Adaptation
- Unsupervised Domain Adaptation with Residual Transfer Networks
- MixMatch: A Holistic Approach to Semi-Supervised Learning
- Semi-Supervised Learning with Ladder Networks
- VisDA: The Visual Domain Adaptation Challenge
- A DIRT-T Approach to Unsupervised Domain Adaptation
- Rethinking Pre-training and Self-training
- On Exact Computation with an Infinitely Wide Neural Net
- Learning with Pseudo-Ensembles
- Bridging Theory and Algorithm for Domain Adaptation
- On Learning Invariant Representation for Domain Adaptation
- Theoretical Analysis of Self-Training with Deep Networks on Unlabeled Data
- Implicit Class-Conditioned Domain Alignment for Unsupervised Domain Adaptation
- Rethinking Distributional Matching Based Domain Adaptation
- Self-training Converts Weak Learners to Strong Learners in Mixture Models