Deep multi-Wasserstein unsupervised domain adaptation
| Autor: | Tien-Nam Le, Marc Sebban, Amaury Habrard |
|---|---|
| Rok vydání: | 2019 |
| Předmět: |
Generalization
business.industry Computer science Feature vector Deep learning 02 engineering and technology 01 natural sciences Term (time) Artificial Intelligence Wasserstein metric 0103 physical sciences Signal Processing Softmax function 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Computer Vision and Pattern Recognition Artificial intelligence 010306 general physics business Divergence (statistics) Algorithm Software |
| Zdroj: | Pattern Recognition Letters. 125:249-255 |
| ISSN: | 0167-8655 |
| DOI: | 10.1016/j.patrec.2019.04.025 |
| Popis: | In unsupervised domain adaptation (DA), 1 aims at learning from labeled source data and fully unlabeled target examples a model with a low error on the target domain. In this setting, standard generalization bounds prompt us to minimize the sum of three terms: (a) the source true risk, (b) the divergence between the source and target domains, and (c) the combined error of the ideal joint hypothesis over the two domains. Many DA methods – especially those using deep neural networks – have focused on the first two terms by using different divergence measures to align the source and target distributions on a shared latent feature space, while ignoring the third term, assuming it is negligible to perform the adaptation. However, it has been shown that purely aligning the two distributions while minimizing the source error may lead to so-called negative transfer. In this paper, we address this issue with a new deep unsupervised DA method – called MCDA – minimizing the first two terms while controlling the third one. MCDA benefits from highly-confident target samples (using softmax predictions) to minimize class-wise Wasserstein distances and efficiently approximate the ideal joint hypothesis. Empirical results show that our approach outperforms state of the art methods. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full Text from ScienceDirect