Discriminative Partial Domain Adversarial Network
| Autor: | Junchi Yan, Henry Leung, Jian Hu, Zhongliang Jing, Lingfeng Qiao, Hongya Tuo, Chao Wang, Haowen Zhong |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
Computer science
business.industry Pattern recognition 02 engineering and technology 010501 environmental sciences 01 natural sciences Weighting Domain (software engineering) Discriminative model 0202 electrical engineering electronic engineering information engineering Benchmark (computing) 020201 artificial intelligence & image processing Artificial intelligence business Divergence (statistics) Transfer of learning 0105 earth and related environmental sciences Block (data storage) |
| Zdroj: | Computer Vision – ECCV 2020 ISBN: 9783030585822 ECCV (27) |
| DOI: | 10.1007/978-3-030-58583-9_38 |
| Popis: | Domain adaptation (DA) has been a fundamental building block for Transfer Learning (TL) which assumes that source and target domain share the same label space. A more general and realistic setting is that the label space of target domain is a subset of the source domain, as termed by Partial domain adaptation (PDA). Previous methods typically match the whole source domain to target domain, which causes negative transfer due to the source-negative classes in source domain that does not exist in target domain. In this paper, a novel Discriminative Partial Domain Adversarial Network (DPDAN) is developed. We first propose to use hard binary weighting to differentiate the source-positive and source-negative samples in the source domain. The source-positive samples are those with labels shared by two domains, while the rest in the source domain are treated as source-negative samples. Based on the above binary relabeling strategy, our algorithm maximizes the distribution divergence between source-negative samples and all the others (source-positive and target samples), meanwhile minimizes domain shift between source-positive samples and target domain to obtain discriminative domain-invariant features. We empirically verify DPDAN can effectively reduce the negative transfer caused by source-negative classes, and also theoretically show it decreases negative transfer caused by domain shift. Experiments on four benchmark domain adaptation datasets show DPDAN consistently outperforms state-of-the-art methods. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|