Zhang, W., Shen, L., & Foo, C.-S. (2023, October 1). Rethinking the Role of Pre-Trained Networks in Source-Free Domain Adaptation. 2023 IEEE/CVF International Conference on Computer Vision (ICCV). https://doi.org/10.1109/iccv51070.2023.01727
Abstract:
Source-free domain adaptation (SFDA) aims to adapt a source model trained on a fully-labeled source domain to an unlabeled target domain. Large-data pre-trained networks are used to initialize source models during source training, and subsequently discarded. However, source training can cause the model to overfit to source data distribution and lose applicable target domain knowledge. We propose to integrate the pre-trained network into the target adaptation process as it has diversified features important for generalization and provides an alternate view of features and classification decisions different from the source model. We propose to distil useful target domain information through a co-learning strategy to improve target pseudolabel quality for finetuning the source model. Evaluation on 4 benchmark datasets show that our proposed strategy improves adaptation performance and can be successfully integrated with existing SFDA methods. Leveraging modern pre-trained networks that have stronger representation learning ability in the co-learning strategy further boosts performance.
License type:
Publisher Copyright
Funding Info:
This research / project is supported by the A*STAR - A*STAR AME Programmatic Funds
Grant Reference no. : A20H6b0151