Sliced Wasserstein Discrepancy for Unsupervised Domain Adaptation
Authors:
Top Cited Papers
- 1 June 2019
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 10277-10287
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.Keywords
All Related Versions
This publication has 37 references indexed in Scilit:
- Sliced and Radon Wasserstein Barycenters of MeasuresJournal of Mathematical Imaging and Vision, 2014
- Evaluation of Traffic Sign Recognition Methods Trained on Synthetically Generated Data2013
- The German Traffic Sign Recognition Benchmark: A multi-class classification competition2011
- A theory of learning from different domainsMachine Learning, 2009
- A Survey on Transfer LearningIEEE Transactions on Knowledge and Data Engineering, 2009
- Optimal Mass Transport for Registration and WarpingInternational Journal of Computer Vision, 2004
- Improving predictive inference under covariate shift by weighting the log-likelihood functionJournal of Statistical Planning and Inference, 2000
- Gradient-based learning applied to document recognitionProceedings of the IEEE, 1998
- A database for handwritten text recognition researchIEEE Transactions on Pattern Analysis and Machine Intelligence, 1994
- On the Translocation of MassesManagement Science, 1958