Energy-Based Pseudo-Label Refining for Source-free Domain Adaptation

Source-free domain adaptation (SFDA), which involves adapting models without access to source data, is both demanding and challenging. Existing SFDA techniques typically rely on pseudo-labels generated from confidence levels, leading to negative transfer due to significant noise. To tackle this problem, Energy-Based Pseudo-Label Refining (EBPR) is proposed for SFDA. Pseudo-labels are created for all sample clusters according to their energy scores. Global and class energy thresholds are computed to selectively filter pseudo-labels. Furthermore, a contrastive learning strategy is introduced to filter difficult samples, aligning them with their augmented versions to learn more discriminative features. Our method is validated on the Office-31, Office-Home, and VisDA-C datasets, consistently finding that our model outperformed state-of-the-art methods.

@article{meng2025_2504.16692,
  title={ Energy-Based Pseudo-Label Refining for Source-free Domain Adaptation },
  author={ Xinru Meng and Han Sun and Jiamei Liu and Ningzhong Liu and Huiyu Zhou },
  journal={arXiv preprint arXiv:2504.16692},
  year={ 2025 }
}