Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptation

Abstract

Unsupervised domain adaptation (UDA) aims to leverage the knowledge learned from a labeled source dataset to solve similar tasks in a new unlabeled domain. Prior UDA methods typically require to access the source data when learning to adapt the model, making them risky and inefficient for decentralized private data. This work tackles a practical setting where only a trained source model is available and investigates how we can effectively utilize such a model without source data to solve UDA problems. We propose a simple yet generic representation learning framework, named \emph{Source HypOthesis Transfer} (SHOT). SHOT freezes the classifier module (hypothesis) of the source model and learns the target-specific feature extraction module by exploiting both information maximization and self-supervised pseudo-labeling to implicitly align representations from the target domains to the source hypothesis. To verify its versatility, we evaluate SHOT in a variety of adaptation cases including closed-set, partial-set, and open-set domain adaptation. Experiments indicate that SHOT yields state-of-the-art results among multiple domain adaptation benchmarks.

arXiv commentICML2020. Fix the typos for Digits. Code is available at https://github.com/tim-learn/SHOT

References in corpus (21)

• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• How transferable are features in deep neural networks?
• Learning Transferable Features with Deep Adaptation Networks
• ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentation
• Conditional Adversarial Domain Adaptation
• Towards Federated Learning at Scale: System Design
• Learning Differentially Private Recurrent Language Models
• Domain Separation Networks
• VisDA: The Visual Domain Adaptation Challenge
• Curriculum Domain Adaptation for Semantic Segmentation of Urban Scenes
• Adversarial Discriminative Domain Adaptation
• A DIRT-T Approach to Unsupervised Domain Adaptation
• Learning Discrete Representations via Information Maximizing Self-Augmented Training
• A Kernel Method for the Two-Sample Problem
• Federated Adversarial Domain Adaptation
• Domain Agnostic Learning with Disentangled Representations
• Information-Theoretical Learning of Discriminative Clusters for Unsupervised Domain Adaptation
• Pseudo-Labeling Curriculum for Unsupervised Domain Adaptation
• Deep Reconstruction-Classification Networks for Unsupervised Domain Adaptation
• Deep Cocktail Network: Multi-source Unsupervised Domain Adaptation with Category Shift
• Learning to Transfer Examples for Partial Domain Adaptation

Cited by in corpus (18)

• A Comprehensive Survey on Test-Time Adaptation under Distribution Shifts
• Robust Multi-Task Learning and Online Refinement for Spacecraft Pose Estimation across Domain Gap
• Exploiting the Intrinsic Neighborhood Structure for Source-free Domain Adaptation
• Unsupervised Domain Adaptation of Black-Box Source Models
• Test-time Batch Statistics Calibration for Covariate Shift
• RAIN: RegulArization on Input and Network for Black-Box Domain Adaptation
• Improving Domain Adaptation Through Class Aware Frequency Transformation
• Generation, augmentation, and alignment: A pseudo-source domain based method for source-free domain adaptation
• Cross-Domain Gradient Discrepancy Minimization for Unsupervised Domain Adaptation
• On Universal Black-Box Domain Adaptation
• BiPC: Bidirectional Probability Calibration for Unsupervised Domain Adaption
• Hypothesis Disparity Regularized Mutual Information Maximization
• Transfer Learning with Pre-trained Conditional Generative Models
• Uncover and Unlearn Nuisances: Agnostic Fully Test-Time Adaptation
• NI-UDA: Graph Adversarial Domain Adaptation from Non-shared-and-Imbalanced Big Data to Small Imbalanced Applications
• Task Guided Compositional Representation Learning for ZDA
• Mutual-Information Based Few-Shot Classification
• Domain Adaptive Semantic Segmentation without Source Data