TriGAN: image-to-image translation for multi-source domain adaptation
Open Access
- 19 January 2021
- journal article
- research article
- Published by Springer Nature in Machine Vision and Applications
- Vol. 32 (1) , 1-12
Abstract
Most domain adaptation methods consider the problem of transferring knowledge to the target domain from a single-source dataset. However, in practical applications, we typically have access to multiple sources. In this paper we propose the first approach for multi-source domain adaptation (MSDA) based on generative adversarial networks. Our method is inspired by the observation that the appearance of a given image depends on three factors: thedomain, thestyle(characterized in terms of low-level features variations) and thecontent. For this reason, we propose to project the source image features onto a space where only the dependence from the content is kept, and then re-project this invariant representation onto the pixel space using the target domain and style. In this way, new labeled images can be generated which are used to train a final target classifier. We test our approach using common MSDA benchmarks, showing that it outperforms state-of-the-art methods.Keywords
All Related Versions
Funding Information
- Università degli Studi di Trento
This publication has 32 references indexed in Scilit:
- Domain-Adversarial Training of Neural Networks2017
- Adversarial Discriminative Domain Adaptation2017
- Image-to-Image Translation with Conditional Adversarial Networks2017
- Image Style Transfer Using Convolutional Neural Networks2016
- Deep Residual Learning for Image Recognition2016
- ImageNet Large Scale Visual Recognition ChallengeInternational Journal of Computer Vision, 2015
- Unbiased look at dataset bias2011
- Cholesky Factorization of Matrices in Parallel and Ranking of Graphs2004
- Introduction2001
- Gradient-based learning applied to document recognitionProceedings of the IEEE, 1998