Domain Prompt Learning with Quaternion Networks (Extended Abstract)

Qinglong Cao, Zhengqin Xu, Yuntian Chen, Chao Ma, Xiaokang Yang

IJCAI 2025 pp. 10881-10884

doi:10.24963/IJCAI.2025/1209 /ijcai/2025/cao2025ijcai-domain/

Abstract

Foundational vision-language models (VLMs) like CLIP have revolutionized image recognition, but adapting them to specialized domains with limited data remains challenging. We propose Domain Prompt Learning with Quaternion Networks (DPLQ), which leverages domain-specific foundation models and quaternion-based prompt tuning to effectively transfer recognition capabilities. Our method achieves state-of-the-art results in remote sensing and medical imaging tasks. This extended abstract highlights the key contributions and performance of DPLQ.

PDF IJCAI Semantic Scholar

Cite

Text

Cao et al. "Domain Prompt Learning with Quaternion Networks (Extended Abstract)." International Joint Conference on Artificial Intelligence, 2025. doi:10.24963/IJCAI.2025/1209

Markdown

[Cao et al. "Domain Prompt Learning with Quaternion Networks (Extended Abstract)." International Joint Conference on Artificial Intelligence, 2025.](https://mlanthology.org/ijcai/2025/cao2025ijcai-domain/) doi:10.24963/IJCAI.2025/1209

BibTeX

@inproceedings{cao2025ijcai-domain,
  title     = {{Domain Prompt Learning with Quaternion Networks (Extended Abstract)}},
  author    = {Cao, Qinglong and Xu, Zhengqin and Chen, Yuntian and Ma, Chao and Yang, Xiaokang},
  booktitle = {International Joint Conference on Artificial Intelligence},
  year      = {2025},
  pages     = {10881-10884},
  doi       = {10.24963/IJCAI.2025/1209},
  url       = {https://mlanthology.org/ijcai/2025/cao2025ijcai-domain/}
}