Saved in:
Bibliographic Details
Main Authors: Liu, Kuanghong, Wang, Jin, He, Kangjian, Xu, Dan, Zhang, Xuejie
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2503.06106
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910865136025600
author Liu, Kuanghong
Wang, Jin
He, Kangjian
Xu, Dan
Zhang, Xuejie
author_facet Liu, Kuanghong
Wang, Jin
He, Kangjian
Xu, Dan
Zhang, Xuejie
contents Conventional multi-source domain few-shot adaptation (MFDA) faces the challenge of further reducing the load on edge-side devices in low-resource scenarios. Considering the native language-supervised advantage of CLIP and the plug-and-play nature of prompt to transfer CLIP efficiently, this paper introduces an uploadable multi-source few-shot domain adaptation (UMFDA) schema. It belongs to a decentralized edge collaborative learning in the edge-side models that must maintain a low computational load. And only a limited amount of annotations in source domain data is provided, with most of the data being unannotated. Further, this paper proposes a vision-aware multimodal prompt tuning framework (VAMP) under the decentralized schema, where the vision-aware prompt guides the text domain-specific prompt to maintain semantic discriminability and perceive the domain information. The cross-modal semantic and domain distribution alignment losses optimize each edge-side model, while text classifier consistency and semantic diversity losses promote collaborative learning among edge-side models. Extensive experiments were conducted on OfficeHome and DomainNet datasets to demonstrate the effectiveness of the proposed VAMP in the UMFDA, which outperformed the previous prompt tuning methods.
format Preprint
id arxiv_https___arxiv_org_abs_2503_06106
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Vision-aware Multimodal Prompt Tuning for Uploadable Multi-source Few-shot Domain Adaptation
Liu, Kuanghong
Wang, Jin
He, Kangjian
Xu, Dan
Zhang, Xuejie
Computer Vision and Pattern Recognition
Conventional multi-source domain few-shot adaptation (MFDA) faces the challenge of further reducing the load on edge-side devices in low-resource scenarios. Considering the native language-supervised advantage of CLIP and the plug-and-play nature of prompt to transfer CLIP efficiently, this paper introduces an uploadable multi-source few-shot domain adaptation (UMFDA) schema. It belongs to a decentralized edge collaborative learning in the edge-side models that must maintain a low computational load. And only a limited amount of annotations in source domain data is provided, with most of the data being unannotated. Further, this paper proposes a vision-aware multimodal prompt tuning framework (VAMP) under the decentralized schema, where the vision-aware prompt guides the text domain-specific prompt to maintain semantic discriminability and perceive the domain information. The cross-modal semantic and domain distribution alignment losses optimize each edge-side model, while text classifier consistency and semantic diversity losses promote collaborative learning among edge-side models. Extensive experiments were conducted on OfficeHome and DomainNet datasets to demonstrate the effectiveness of the proposed VAMP in the UMFDA, which outperformed the previous prompt tuning methods.
title Vision-aware Multimodal Prompt Tuning for Uploadable Multi-source Few-shot Domain Adaptation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2503.06106