From Source to Target and Back: Symmetric Bi-Directional Adaptive GAN
Authors:
- Paolo RussoPaolo Russo
- Fabio M. CarlucciFCFabio M. Carlucci
- Tatiana TommasiTTTatiana Tommasi
- Barbara CaputoBCBarbara Caputo
- 1 June 2018
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 8099-8108
Abstract
The effectiveness of GANs in producing images according to a specific visual domain has shown potential in unsupervised domain adaptation. Source labeled images have been modified to mimic target samples for training classifiers in the target domain, and inverse mappings from the target to the source domain have also been evaluated, without new image generation. In this paper we aim at getting the best of both worlds by introducing a symmetric mapping among domains. We jointly optimize bi-directional image transformations combining them with target self-labeling. We define a new class consistency loss that aligns the generators in the two directions, imposing to preserve the class identity of an image passing through both domain mappings. A detailed analysis of the reconstructed images, a thorough ablation study and extensive experiments on six different settings confirm the power of our approach.Keywords
All Related Versions
This publication has 16 references indexed in Scilit:
- Image Style Transfer Using Convolutional Neural Networks2016
- Simultaneous Deep Transfer Across Domains and Tasks2015
- 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
- Evaluation of Traffic Sign Recognition Methods Trained on Synthetically Generated Data2013
- 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
- Gradient-based learning applied to document recognitionProceedings of the IEEE, 1998