Denoised Maximum Classifier Discrepancy for Source-Free Unsupervised Domain Adaptation

By Tong Chu, Yahao Liu, Jinhong Deng, Wen Li, Lixin Duan. 2022

50 citations recorded by the source corpus.

How researchers see this paper

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

1. Yahao Liu
2. Jiahua Dong
3. Wen Li
4. Tong Chu
5. Jinhong Deng
6. Lixu Wang
7. Zhen Fang
8. Lixin Duan

Citations in the corpus

• Federated Class-Incremental Learning (2022, background): “[34] integrates unsupervised domain adaptation [5, 9, 27, 28, 57] into federated learning framework [14, 31].”
• A Comprehensive Survey on Test-Time Adaptation Under Distribution Shifts (2023, unknown): “On the contrary, other existing methods [124], [177], [215], [217], [221], [236], [267], [274], [275], [276], [320], [321], [322] do not fix the domain partition but alternately update the domain partition and learn the target model in the adaptation step.”
• Undoing the Damage of Label Shift for Cross-domain Semantic Segmentation (2022, background): “Among them, adversarial training is the most widely adopted strategy [12, 20, 28, 39].”