Nasty-SFDA: Source Free Domain Adaptation from a Nasty Model

Jiajiong Cao; Yufan Liu; Weiming Bai; Jingting Ding; Liang Li

ICASSP 2023accepted0 citations

Nasty-SFDA: Source Free Domain Adaptation from a Nasty Model

Jiajiong Cao, Yufan Liu, Weiming Bai, Jingting Ding, Liang Li

Abstract

A challenging problem called Nasty Source Free Domain Adaptation (Nasty-SFDA) is proposed in this work, where only a nasty source model and unlabeled target samples are available for DA. Further, after DA, the target model is expected to be a nasty model. In order to deal with Nasty-SFDA, Nasty HypOthesis Transfer (NHOT) with an improved version of Information Maximization (IM) loss called Multi-Peak Constraints (MPC) and several Label Generation (LG) techniques is proposed. Experiments on four popular datasets show the superiority of NHOT for both Nasty-SFDA and SFDA. In addition, the target model obtained via NHOT is proven to be a nasty model.

BibTeX

@inproceedings{icassp2023_nastysfdasourcef,
  title = {Nasty-SFDA: Source Free Domain Adaptation from a Nasty Model},
  author = {Jiajiong Cao and Yufan Liu and Weiming Bai and Jingting Ding and Liang Li},
  booktitle = {ICASSP 2023},
  year = {2023}
}