Towards Category and Domain Alignment: Category-Invariant Feature Enhancement for Adversarial Domain Adaptation
| Autor: | Diana Inkpen, Yuan Wu, Ahmed El-Roby |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2021 |
| Předmět: |
FOS: Computer and information sciences
Ideal (set theory) business.industry Computer science Computer Vision and Pattern Recognition (cs.CV) media_common.quotation_subject Computer Science - Computer Vision and Pattern Recognition Pattern recognition Adaptability Domain (software engineering) Adversarial system Feature (machine learning) Artificial intelligence business Constant (mathematics) Divergence (statistics) Focus (optics) media_common |
| Popis: | Adversarial domain adaptation has made impressive advances in transferring knowledge from the source domain to the target domain by aligning feature distributions of both domains. These methods focus on minimizing domain divergence and regard the adaptability, which is measured as the expected error of the ideal joint hypothesis on these two domains, as a small constant. However, these approaches still face two issues: (1) Adversarial domain alignment distorts the original feature distributions, deteriorating the adaptability; (2) Transforming feature representations to be domain-invariant needs to sacrifice domain-specific variations, resulting in weaker discriminability. In order to alleviate these issues, we propose category-invariant feature enhancement (CIFE), a general mechanism that enhances the adversarial domain adaptation through optimizing the adaptability. Specifically, the CIFE approach introduces category-invariant features to boost the discriminability of domain-invariant features with preserving the transferability. Experiments show that the CIFE could improve upon representative adversarial domain adaptation methods to yield state-of-the-art results on five benchmarks. 10 pages, 4 figures |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|