Self-ensembling for visual domain adaptation


Nov 03, 2017 (modified: Nov 03, 2017) ICLR 2018 Conference Blind Submission readers: everyone Show Bibtex
  • 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.
  • TL;DR: Self-ensembling based label propagation algorithm for visual domain adaptation, won VisDA-2017 image classification domain adaptation challenge.
  • Keywords: deep learning, neural networks, domain adaptation, images, visual, computer vision