From source to target and back: symmetric bi-directional adaptive GAN
Preprint
Abstract
The effectiveness of generative adversarial approaches in producing images according to a specific style or visual domain has recently opened new directions to solve the unsupervised domain adaptation problem. It has been shown that source labeled images can be modified to mimic target samples making it possible to train directly a classifier in the target domain, despite the original lack of annotated data. Inverse mappings from the target to the source domain have also been evaluated but only passing through adapted feature spaces, thus without new image generation. In this paper we propose to better exploit the potential of generative adversarial networks for adaptation by introducing a novel symmetric mapping among domains. We jointly optimize bi-directional image transformations combining them with target self-labeling. Moreover we define a new class consistency loss that aligns the generators in the two directions imposing to conserve the class identity of an image passing through both domain mappings. A detailed qualitative and quantitative analysis of the reconstructed images confirm the power of our approach. By integrating the two domain specific classifiers obtained with our bi-directional network we exceed previous state-of-the-art unsupervised adaptation results on four different benchmark datasets.Keywords
All Related Versions
This publication has 8 references indexed in Scilit:
- Generate to Adapt: Aligning Domains Using Generative Adversarial Networks2018
- Unpaired Image-to-Image Translation Using Cycle-Consistent Adversarial Networks2017
- Domain adaptation of weighted majority votes via perturbed variation-based self-labelingPattern Recognition Letters, 2015
- ITERATIVE SELF-LABELING DOMAIN ADAPTATION FOR LINEAR STRUCTURED IMAGE CLASSIFICATIONInternational Journal on Artificial Intelligence Tools, 2013
- The German Traffic Sign Recognition Benchmark: A multi-class classification competition2011
- Contour Detection and Hierarchical Image SegmentationIEEE Transactions on Pattern Analysis and Machine Intelligence, 2010
- Domain Adaptation Problems: A DASVM Classification Technique and a Circular Validation StrategyIEEE Transactions on Pattern Analysis and Machine Intelligence, 2009
- Image quality assessment: from error visibility to structural similarityIEEE Transactions on Image Processing, 2004