Sliced Wasserstein Discrepancy for Unsupervised Domain Adaptation

2019/03/10 by Chen-Yu Lee, Tanmay Batra, Lee, Chen-Yu +5 · 12 citations
Computer Science · Mathematics · #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #cs.CV #cs.LG #stat.ML

paper · pdf · doi:10.48550/arxiv.1903.04064

Accepted at CVPR 2019

arxiv created 2019/03/10 · arxiv updated 2019/03/12

Abstract

In this work, we connect two distinct concepts for unsupervised domain adaptation: feature distribution alignment between domains by utilizing the task-specific decision boundary and the Wasserstein metric. Our proposed sliced Wasserstein discrepancy (SWD) is designed to capture the natural notion of dissimilarity between the outputs of task-specific classifiers. It provides a geometrically meaningful guidance to detect target samples that are far from the support of the source and enables efficient distribution alignment in an end-to-end trainable fashion. In the experiments, we validate the effectiveness and genericness of our method on digit and sign recognition, image classification, semantic segmentation, and object detection.

Cited by

• On the Information Processing of One-Dimensional Wasserstein Distances with Finite Samples
• Mitigating Negative Transfer via Reducing Environmental Disagreement
• Unsupervised Pairwise Learning Optimization Framework for Cross-Corpus EEG-Based Emotion Recognition Based on Prototype Representation
• AFRDA: Attentive Feature Refinement for Domain Adaptive Semantic Segmentation
• Sparse Causal Discovery with Generative Intervention for Unsupervised Graph Domain Adaptation
• CLOT: Closed Loop Optimal Transport for Unsupervised Action Segmentation
• Global Variational Inference Enhanced Robust Domain Adaptation
• IDAL: Improved Domain Adaptive Learning for Natural Images Dataset
• Preserving Clusters in Prompt Learning for Unsupervised Domain Adaptation
• Shuffle PatchMix Augmentation with Confidence-Margin Weighted Pseudo-Labels for Enhanced Source-Free Domain Adaptation
• Cross-Domain Diffusion with Progressive Alignment for Efficient Adaptive Retrieval
• Semantic-Space-Intervened Diffusive Alignment for Visual Classification

Related

• Sliced Wasserstein Discrepancy in Disentangling Representation and Adaptation Networks for Unsupervised Domain Adaptation
• Maximum Classifier Discrepancy for Unsupervised Domain Adaptation
• Wasserstein Distance Based Domain Adaptation for Object Detection
• Task-Discriminative Domain Alignment for Unsupervised Domain Adaptation
• On the Transferability and Discriminability of Repersentation Learning in Unsupervised Domain Adaptation