Sliced Wasserstein Discrepancy for Unsupervised Domain Adaptation

2019/03/10 by Lee, Chen-Yu, Batra, Tanmay, Baig, Mohammad Haris +1 · 2 citations
#Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML)

paper · doi:10.48550/arxiv.1903.04064

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

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