Domain adaptation based on incremental adversarial learning
| Autor: | Fatemeh Afsari, Hamideh Khadempir, Esmat Rashedi |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
Similarity (geometry)
Source data business.industry Computer science Deep learning Pattern recognition 02 engineering and technology 010501 environmental sciences Base (topology) 01 natural sciences Domain (software engineering) Discriminative model 020204 information systems 0202 electrical engineering electronic engineering information engineering Artificial intelligence business Transfer of learning Adaptation (computer science) 0105 earth and related environmental sciences |
| Zdroj: | 2020 8th Iranian Joint Congress on Fuzzy and intelligent Systems (CFIS). |
| Popis: | Domain adaptation is a method of transfer learning. Domain adaptation has a source domain and target domain with related but different distributions. Unsupervised domain adaptation could be a scenario wherever we've labeled unlabeled target data and source data. In this paper, an incremental adversarial learning method is proposed for unsupervised domain adaptation. In this work, the unknown target labels are predicted and according to these estimated labels, some target data with more similarity to the source data are added to the source data to improve the adaptation between two domains. We use the adversarial discriminative approach as the base unsupervised domain adaptation technique. We do this to handle the large domain shift between the source and target domain distributions. Experimental reports prove that our approach performs much better on several visual domain adaptation tasks. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|