Learning Invariant Representation with Consistency and Diversity for Semi-supervised Source Hypothesis Transfer

Abstract

Semi-supervised domain adaptation (SSDA) aims to solve tasks in target domain by utilizing transferable information learned from the available source domain and a few labeled target data. However, source data is not always accessible in practical scenarios, which restricts the application of SSDA in real world circumstances. In this paper, we propose a novel task named Semi-supervised Source Hypothesis Transfer (SSHT), which performs domain adaptation based on source trained model, to generalize well in target domain with a few supervisions. In SSHT, we are facing two challenges: (1) The insufficient labeled target data may result in target features near the decision boundary, with the increased risk of mis-classification; (2) The data are usually imbalanced in source domain, so the model trained with these data is biased. The biased model is prone to categorize samples of minority categories into majority ones, resulting in low prediction diversity. To tackle the above issues, we propose Consistency and Diversity Learning (CDL), a simple but effective framework for SSHT by facilitating prediction consistency between two randomly augmented unlabeled data and maintaining the prediction diversity when adapting model to target domain. Encouraging consistency regularization brings difficulty to memorize the few labeled target data and thus enhances the generalization ability of the learned model. We further integrate Batch Nuclear-norm Maximization into our method to enhance the discriminability and diversity. Experimental results show that our method outperforms existing SSDA methods and unsupervised model adaptation methods on DomainNet, Office-Home and Office-31 datasets. The code is available at https://github.com/Wang-xd1899/SSHT.

arXiv comment10 pages, 4 figures

References in corpus (20)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• mixup: Beyond Empirical Risk Minimization
• Learning Transferable Features with Deep Adaptation Networks
• Deep Domain Confusion: Maximizing for Domain Invariance
• FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence
• Temporal Ensembling for Semi-Supervised Learning
• Interpolation Consistency Training for Semi-Supervised Learning
• MixMatch: A Holistic Approach to Semi-Supervised Learning
• Regularization With Stochastic Transformations and Perturbations for Deep Semi-Supervised Learning
• Model Adaptation: Unsupervised Domain Adaptation without Source Data
• Central Moment Discrepancy (CMD) for Domain-Invariant Representation Learning
• On Learning Invariant Representation for Domain Adaptation
• Coupled Generative Adversarial Networks
• Domain Adaptation with Conditional Distribution Matching and Generalized Label Shift
• Adversarial Dropout Regularization
• Source Data-absent Unsupervised Domain Adaptation through Hypothesis Transfer and Labeling Transfer
• Learning Invariant Representations and Risks for Semi-supervised Domain Adaptation
• Heuristic Domain Adaptation
• Effective Label Propagation for Discriminative Semi-Supervised Domain Adaptation
• Selective Pseudo-Labeling with Reinforcement Learning for Semi-Supervised Domain Adaptation

Cited by in corpus (1)

• Uncertainty-Guided Mixup for Semi-Supervised Domain Adaptation without Source Data