Denoised Maximum Classifier Discrepancy for Source-Free Unsupervised Domain Adaptation

Tong Chu, Yahao Liu, Jinhong Deng, Wen Li, Lixin Duan

[AAAI-22] Main Track
Abstract: Source-Free Unsupervised Domain Adaptation~(SFUDA) aims to adapt a pre-trained source model to an unlabeled target domain without access to the original labeled source domain samples. Many existing SFUDA approaches apply the self-training strategy, \ie, iteratively selecting confidently predicted target samples as pseudo-labeled samples to train the model to fit the target domain. However, the self-training strategy may also suffer from the sample selection bias and the label noise of the pseudo-labeled samples. In this work, we provide a rigorous theoretical analysis on how these two issues affect the model generalization ability when applying self-training strategy for the SFUDA problem. Benefited from the theoretical analysis, we then propose a new Denoised Maximum Classifier Discrepancy (D-MCD) for SFUDA to effectively address these two issues. In particular, we first minimize the distribution mismatch between the selected pseudo-labeled samples and the rest target domain samples to alleviate the sample selection bias. Besides, we design a strong-weak self-training paradigm to denoise the selected pseudo-labeled samples, where the strong network is used to select pseudo-labeled samples while the weak network helps the strong network to filter out hard samples to avoid incorrect labels. In this way, we are able to ensure both the quality of pseudo-label and the generalization ability of the trained model on the target domain. We achieve state-of-the-art results on three domain adaptation benchmark datasets, which clearly validates the effectiveness of our proposed approach.

Introduction Video

Sessions where this paper appears

  • Poster Session 5

    Sat, February 26 12:45 AM - 2:30 AM (+00:00)
    Blue 3
    Add to Calendar

  • Poster Session 10

    Sun, February 27 4:45 PM - 6:30 PM (+00:00)
    Blue 3
    Add to Calendar

  • Oral Session 5

    Sat, February 26 2:30 AM - 3:45 AM (+00:00)
    Blue 3
    Add to Calendar