arXiv Open Access 2025

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

Xinru Meng Han Sun Jiamei Liu Ningzhong Liu Huiyu Zhou

Lihat Sumber

Abstrak

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.

Topik & Kata Kunci

cs.CV

Penulis (5)

Xinru Meng

Han Sun

Jiamei Liu

Ningzhong Liu

Huiyu Zhou

Format Sitasi

APA MLA BibTeX

Meng, X., Sun, H., Liu, J., Liu, N., Zhou, H. (2025). Energy-Based Pseudo-Label Refining for Source-free Domain Adaptation. https://arxiv.org/abs/2504.16692

Akses Cepat

Lihat di Sumber

Informasi Jurnal

Tahun Terbit: 2025
Bahasa: en
Sumber Database: arXiv
Akses: Open Access ✓