Unsupervised Pixel-Level Domain Adaptation with Generative Adversarial Networks
Top Cited Papers
- 1 July 2017
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 10636919,p. 95-104
- https://doi.org/10.1109/cvpr.2017.18
Abstract
Collecting well-annotated image datasets to train modern machine learning algorithms is prohibitively expensive for many tasks. One appealing alternative is rendering synthetic data where ground-truth annotations are generated automatically. Unfortunately, models trained purely on rendered images fail to generalize to real images. To address this shortcoming, prior work introduced unsupervised domain adaptation algorithms that have tried to either map representations between the two domains, or learn to extract features that are domain-invariant. In this work, we approach the problem in a new light by learning in an unsupervised manner a transformation in the pixel space from one domain to the other. Our generative adversarial network (GAN)-based method adapts source-domain images to appear as if drawn from the target domain. Our approach not only produces plausible samples, but also outperforms the state-of-the-art on a number of unsupervised domain adaptation scenarios by large margins. Finally, we demonstrate that the adaptation process generalizes to object classes unseen during training.Keywords
This publication has 10 references indexed in Scilit:
- Image Style Transfer Using Convolutional Neural NetworksPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2016
- Return of Frustratingly Easy Domain AdaptationProceedings of the AAAI Conference on Artificial Intelligence, 2016
- Simultaneous Deep Transfer Across Domains and TasksPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2015
- Learning descriptors for object recognition and 3D pose estimationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2015
- Beyond the shortest path: Unsupervised domain adaptation by Sampling Subspaces along the Spline FlowPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2015
- The Pascal Visual Object Classes Challenge: A RetrospectiveInternational Journal of Computer Vision, 2014
- Domain adaptation for object recognition: An unsupervised approachPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2011
- Contour Detection and Hierarchical Image SegmentationIEEE Transactions on Pattern Analysis and Machine Intelligence, 2010
- Metrics for 3D Rotations: Comparison and AnalysisJournal of Mathematical Imaging and Vision, 2009
- Gradient-based learning applied to document recognitionProceedings of the IEEE, 1998