Unsupervised domain adaptation in the wild via disentangling representation learning

• المؤلفون الرئيسيون: Li, Haoliang, Wan, Renjie, Wang, Shiqi, Kot, Alex Chichung
• مؤلفون آخرون: School of Electrical and Electronic Engineering
• التنسيق: مقال
• اللغة: English
• منشور في: 2022
• الموضوعات: Engineering::Electrical and electronic engineering; In the Wild; Cross-Domain
• الوصول للمادة أونلاين: https://hdl.handle.net/10356/160950

Most recently proposed unsupervised domain adaptation algorithms attempt to learn domain invariant features by confusing a domain classifier through adversarial training. In this paper, we argue that this may not be an optimal solution in the real-world setting (a.k.a. in the wild) as the difference...