Self-ensembling for visual domain adaptation
Authors:
- Geoffrey FrenchGFGeoffrey French
- Michal MackiewiczMMMichal Mackiewicz
- Mark FisherMFMark Fisher
Preprint
Abstract
This paper explores the use of self-ensembling for visual domain adaptation problems. Our technique is derived from the mean teacher variant (Tarvainen et al., 2017) of temporal ensembling (Laine et al;, 2017), a technique that achieved state of the art results in the area of semi-supervised learning. We introduce a number of modifications to their approach for challenging domain adaptation scenarios and evaluate its effectiveness. Our approach achieves state of the art results in a variety of benchmarks, including our winning entry in the VISDA-2017 visual domain adaptation challenge. In small image benchmarks, our algorithm not only outperforms prior art, but can also achieve accuracy that is close to that of a classifier trained in a supervised fashion.Keywords
All Related Versions
This publication has 10 references indexed in Scilit:
- Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised LearningIEEE Transactions on Pattern Analysis and Machine Intelligence, 2018
- From Source to Target and Back: Symmetric Bi-Directional Adaptive GAN2018
- Unpaired Image-to-Image Translation Using Cycle-Consistent Adversarial Networks2017
- Learning from Simulated and Unsupervised Images through Adversarial Training2017
- Unsupervised Pixel-Level Domain Adaptation with Generative Adversarial Networks2017
- Deep Reconstruction-Classification Networks for Unsupervised Domain Adaptation2016
- Deep Residual Learning for Image Recognition2016
- Microsoft COCO: Common Objects in Context2014
- The German Traffic Sign Recognition Benchmark: A multi-class classification competition2011
- Tri-training: exploiting unlabeled data using three classifiersIEEE Transactions on Knowledge and Data Engineering, 2005