Incremental Evolving Domain Adaptation

By Adeleh Bitarafan, Mahdieh Soleymani Baghshah, Marzieh Gheisari. 2016

37 citations recorded by the source corpus.

Subfields: Artificial Intelligence

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Mingsheng Long
2. Jianmin Wang
3. Hong Liu
4. Yu Wang
5. Dina Katabi
6. Hao He
7. Hao Wang
8. Ning Xu

Citations in the corpus

• Learngene: From Open-World to Your Learning Task (2021, background): “Moreover, continual domain adaptation (Zhao and Hoi 2010; Liu et al. 2020; Bitarafan, Baghshah, and Gheisari 2016; Wang, He, and Katabi 2020; Mancini et al. 2019a) enables the learner to adapt to continually evolving target domains without forgetting.”
• Continuously Indexed Domain Adaptation (2020, methodology): “Different methods are used to perform categorical DA for each domain pair, such as optimal transport (Jimenez et al., 2019), adversarial loss (Bitarafan et al., 2016), generative adversarial networks (Wulfmeier et al., 2018), and linear transform (Hoffman et al., 2014).”
• Learning to Adapt to Evolving Domains (2020, background): “[11, 2] focus on continually shifting target domains, but they test the model online and did not address the catastrophic forgetting.”