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: the domain, the style (characterized in terms of low-level features variations) and the content. 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. |
Year | DOI | Venue |
---|---|---|
2021 | 10.1007/s00138-020-01164-4 | MACHINE VISION AND APPLICATIONS |
Keywords | DocType | Volume |
Unsupervised domain adaptation, Generative adversarial network, Image classification, Image-to-image translation | Journal | 32 |
Issue | ISSN | Citations |
1 | 0932-8092 | 3 |
PageRank | References | Authors |
0.38 | 0 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Subhankar Roy | 1 | 30 | 4.09 |
Aliaksandr Siarohin | 2 | 7 | 2.83 |
Enver Sangineto | 3 | 353 | 26.77 |
Nicu Sebe | 4 | 7013 | 403.03 |
Elisa Ricci 0002 | 5 | 1393 | 73.75 |