Enregistré dans:
Détails bibliographiques
Auteurs principaux: Peng, Zelin, Zhao, Yichen, Huang, Yu, Yang, Piao, Tang, Feilong, Xu, Zhengqin, Yang, Xiaokang, Shen, Wei
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:https://arxiv.org/abs/2508.04101
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866916883419103232
author Peng, Zelin
Zhao, Yichen
Huang, Yu
Yang, Piao
Tang, Feilong
Xu, Zhengqin
Yang, Xiaokang
Shen, Wei
author_facet Peng, Zelin
Zhao, Yichen
Huang, Yu
Yang, Piao
Tang, Feilong
Xu, Zhengqin
Yang, Xiaokang
Shen, Wei
contents Computer-aided medical image analysis is crucial for disease diagnosis and treatment planning, yet limited annotated datasets restrict medical-specific model development. While vision-language models (VLMs) like CLIP offer strong generalization capabilities, their direct application to medical imaging analysis is impeded by a significant domain gap. Existing approaches to bridge this gap, including prompt learning and one-way modality interaction techniques, typically focus on introducing domain knowledge to a single modality. Although this may offer performance gains, it often causes modality misalignment, thereby failing to unlock the full potential of VLMs. In this paper, we propose \textbf{NEARL-CLIP} (i\underline{N}teracted qu\underline{E}ry \underline{A}daptation with o\underline{R}thogona\underline{L} Regularization), a novel cross-modality interaction VLM-based framework that contains two contributions: (1) Unified Synergy Embedding Transformer (USEformer), which dynamically generates cross-modality queries to promote interaction between modalities, thus fostering the mutual enrichment and enhancement of multi-modal medical domain knowledge; (2) Orthogonal Cross-Attention Adapter (OCA). OCA introduces an orthogonality technique to decouple the new knowledge from USEformer into two distinct components: the truly novel information and the incremental knowledge. By isolating the learning process from the interference of incremental knowledge, OCA enables a more focused acquisition of new information, thereby further facilitating modality interaction and unleashing the capability of VLMs. Notably, NEARL-CLIP achieves these two contributions in a parameter-efficient style, which only introduces \textbf{1.46M} learnable parameters.
format Preprint
id arxiv_https___arxiv_org_abs_2508_04101
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle NEARL-CLIP: Interacted Query Adaptation with Orthogonal Regularization for Medical Vision-Language Understanding
Peng, Zelin
Zhao, Yichen
Huang, Yu
Yang, Piao
Tang, Feilong
Xu, Zhengqin
Yang, Xiaokang
Shen, Wei
Computer Vision and Pattern Recognition
Computer-aided medical image analysis is crucial for disease diagnosis and treatment planning, yet limited annotated datasets restrict medical-specific model development. While vision-language models (VLMs) like CLIP offer strong generalization capabilities, their direct application to medical imaging analysis is impeded by a significant domain gap. Existing approaches to bridge this gap, including prompt learning and one-way modality interaction techniques, typically focus on introducing domain knowledge to a single modality. Although this may offer performance gains, it often causes modality misalignment, thereby failing to unlock the full potential of VLMs. In this paper, we propose \textbf{NEARL-CLIP} (i\underline{N}teracted qu\underline{E}ry \underline{A}daptation with o\underline{R}thogona\underline{L} Regularization), a novel cross-modality interaction VLM-based framework that contains two contributions: (1) Unified Synergy Embedding Transformer (USEformer), which dynamically generates cross-modality queries to promote interaction between modalities, thus fostering the mutual enrichment and enhancement of multi-modal medical domain knowledge; (2) Orthogonal Cross-Attention Adapter (OCA). OCA introduces an orthogonality technique to decouple the new knowledge from USEformer into two distinct components: the truly novel information and the incremental knowledge. By isolating the learning process from the interference of incremental knowledge, OCA enables a more focused acquisition of new information, thereby further facilitating modality interaction and unleashing the capability of VLMs. Notably, NEARL-CLIP achieves these two contributions in a parameter-efficient style, which only introduces \textbf{1.46M} learnable parameters.
title NEARL-CLIP: Interacted Query Adaptation with Orthogonal Regularization for Medical Vision-Language Understanding
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2508.04101