Prompt-Based Distribution Alignment for Unsupervised Domain Adaptation
Proceedings of the AAAI Conference on Artificial Intelligence · 24.03.2024 · 38 (2) · 729-737
DOI: 10.1609/aaai.v38i2.27830 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 24.03.2024. Verfasst von Shuanghao Bai und 6 weiteren Autor:innen. Die Arbeit wurde bisher 84-mal zitiert (Crossref).
Abstract (Originalsprache)
Recently, despite the unprecedented success of large pre-trained visual-language models (VLMs) on a wide range of downstream tasks, the real-world unsupervised domain adaptation (UDA) problem is still not well explored. Therefore, in this paper, we first experimentally demonstrate that the unsupervised-trained VLMs can significantly reduce the distribution discrepancy between source and target domains, thereby improving the performance of UDA. However, a major challenge for directly deploying such models on downstream UDA tasks is prompt engineering, which requires aligning the domain knowledge of source and target domains, since the performance of UDA is severely influenced by a good domain-invariant representation. We further propose a Prompt-based Distribution Alignment (PDA) method to incorporate the domain knowledge into prompt learning. Specifically, PDA employs a two-branch prompt-tuning paradigm, namely base branch and alignment branch. The base branch focuses on integrating class-related representation into prompts, ensuring discrimination among different classes. To further minimize domain discrepancy, for the alignment branch, we construct feature banks for both the source and target domains and propose image-guided feature tuning (IFT) to make the input attend to feature banks, which effectively integrates self-enhanced and cross-domain features into the model. In this way, these two branches can be mutually promoted to enhance the adaptation of VLMs for UDA. We conduct extensive experiments on three benchmarks to demonstrate that our proposed PDA achieves state-of-the-art performance. The code is available at https://github.com/BaiShuanghao/Prompt-based-Distribution-Alignment.
Zitieren
APA
Bai, S., Zhang, M., Zhou, W., Huang, S., Luan, Z., Wang, D., & Chen, B. (2024). Prompt-Based Distribution Alignment for Unsupervised Domain Adaptation. Proceedings of the AAAI Conference on Artificial Intelligence, 38(2), 729-737. https://doi.org/10.1609/aaai.v38i2.27830
Vancouver
Bai S, Zhang M, Zhou W, Huang S, Luan Z, Wang D, et al. Prompt-Based Distribution Alignment for Unsupervised Domain Adaptation. Proceedings of the AAAI Conference on Artificial Intelligence. 2024;38(2):729-737. doi:10.1609/aaai.v38i2.27830
BibTeX
@article{Bai2024,
author = {Bai, Shuanghao and Zhang, Min and Zhou, Wanqi and Huang, Siteng and Luan, Zhirong and Wang, Donglin and Chen, Badong},
title = {Prompt-Based Distribution Alignment for Unsupervised Domain Adaptation},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2024},
volume = {38},
number = {2},
pages = {729--737},
doi = {10.1609/aaai.v38i2.27830}
}
EUVIMED