Abstract | ||
---|---|---|
Deep Learning for Computer Vision depends mainly on the source of supervision.Photo-realistic simulators can generate large-scale automatically labeled syntheticdata, but introduce a domain gap negatively impacting performance. We propose anew unsupervised domain adaptation algorithm, called SPIGAN, relying on Sim-ulator Privileged Information (PI) and Generative Adversarial Networks (GAN).We use internal data from the simulator as PI during the training of a target tasknetwork. We experimentally evaluate our approach on semantic segmentation. Wetrain the networks on real-world Cityscapes and Vistas datasets, using only unla-beled real-world images and synthetic labeled data with z-buffer (depth) PI fromthe SYNTHIA dataset. Our method improves over no adaptation and state-of-the-art unsupervised domain adaptation techniques. |
Year | Venue | Field |
---|---|---|
2018 | international conference on learning representations | Domain adaptation,Computer science,Segmentation,Artificial intelligence,Generative grammar,Deep learning,Labeled data,Machine learning,Adversarial system |
DocType | Volume | Citations |
Journal | abs/1810.03756 | 5 |
PageRank | References | Authors |
0.42 | 26 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Kuan-Hui Lee | 1 | 83 | 10.04 |
Germán Ros | 2 | 223 | 11.13 |
J.X. Li | 3 | 403 | 113.63 |
Adrien Gaidon | 4 | 284 | 24.17 |