NEARL-CLIP: Interacted Query Adaptation with Orthogonal Regularization for Medical Vision-Language Understanding

• URL: http://arxiv.org/abs/2508.04101v1
• Date: Wed, 06 Aug 2025 05:44:01 GMT
• Title: NEARL-CLIP: Interacted Query Adaptation with Orthogonal Regularization for Medical Vision-Language Understanding
• Authors: Zelin Peng, Yichen Zhao, Yu Huang, Piao Yang, Feilong Tang, Zhengqin Xu, Xiaokang Yang, Wei Shen,
• Abstract summary: textbfNEARL-CLIP (iunderlineNteracted quunderlineEry underlineAdaptation with ounderlineRthogonaunderlineL Regularization) is a novel cross-modality interaction VLM-based framework.
• Score: 51.63264715941068
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: 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.

Related papers

• DART: Dual Adaptive Refinement Transfer for Open-Vocabulary Multi-Label Recognition [59.203152078315235]
  Open-Vocabulary Multi-Label Recognition (OV-MLR) aims to identify multiple seen and unseen object categories within an image.<n> Vision-Language Pre-training models offer a strong open-vocabulary foundation, but struggle with fine-grained localization under weak supervision.<n>We propose the Dual Adaptive Refinement Transfer (DART) framework to overcome these limitations.
  arXiv  Detail & Related papers  (2025-08-07T17:22:33Z)
• Multimodal Causal-Driven Representation Learning for Generalizable Medical Image Segmentation [56.52520416420957]
  We propose Multimodal Causal-Driven Representation Learning (MCDRL) to tackle domain generalization in medical image segmentation.<n>MCDRL consistently outperforms competing methods, yielding superior segmentation accuracy and exhibiting robust generalizability.
  arXiv  Detail & Related papers  (2025-08-07T03:41:41Z)
• Co-AttenDWG: Co-Attentive Dimension-Wise Gating and Expert Fusion for Multi-Modal Offensive Content Detection [0.0]
  Multi-modal learning has emerged as a crucial research direction.<n>Existing approaches often suffer from insufficient cross-modal interactions and rigid fusion strategies.<n>We propose Co-AttenDWG, co-attention with dimension-wise gating, and expert fusion.<n>We show that Co-AttenDWG achieves state-of-the-art performance and superior cross-modal alignment.
  arXiv  Detail & Related papers  (2025-05-25T07:26:00Z)
• Zeus: Zero-shot LLM Instruction for Union Segmentation in Multimodal Medical Imaging [4.341503087761129]
  Conducting multimodal learning involves visual and text modalities shown as a solution, but collecting paired vision-language datasets is expensive and time-consuming.<n>Inspired by the superior ability in numerous cross-modal tasks for Large Language Models (LLMs), we proposed a novel Vision-LLM union framework to address the issues.
  arXiv  Detail & Related papers  (2025-04-09T23:33:35Z)
• Measuring Cross-Modal Interactions in Multimodal Models [9.862551438475666]
  Existing AI methods fail to capture cross-modal interactions crucial for understanding the combined impact of multiple data sources.<n>This paper introduces InterSHAP, a cross-modal interaction score that addresses the limitations of existing approaches.<n>We show that InterSHAP accurately measures the presence of cross-modal interactions, can handle multiple modalities, and provides detailed explanations at a local level for individual samples.
  arXiv  Detail & Related papers  (2024-12-20T12:11:20Z)
• MoRE: Multi-Modal Contrastive Pre-training with Transformers on X-Rays, ECGs, and Diagnostic Report [4.340464264725625]
  We introduce a novel Multi-Modal Contrastive Pre-training Framework that synergistically combines X-rays, electrocardiograms (ECGs) and radiology/cardiology reports. We utilize LoRA-Peft to significantly reduce trainable parameters in the LLM and incorporate recent linear attention dropping strategy in the Vision Transformer(ViT) for smoother attention. To the best of our knowledge, we are the first to propose an integrated model that combines X-ray, ECG, and Radiology/Cardiology Report with this approach.
  arXiv  Detail & Related papers  (2024-10-21T17:42:41Z)
• MedualTime: A Dual-Adapter Language Model for Medical Time Series-Text Multimodal Learning [27.22751020503897]
  MedualTime is a language model composed of dual adapters to implement temporal-primary and textual-primary modeling simultaneously.<n>MedualTime demonstrates superior performance on medical data, achieving notable improvements of 8% accuracy and 12% F1 in supervised settings.
  arXiv  Detail & Related papers  (2024-06-07T14:34:28Z)
• Dr-LLaVA: Visual Instruction Tuning with Symbolic Clinical Grounding [53.629132242389716]
  Vision-Language Models (VLM) can support clinicians by analyzing medical images and engaging in natural language interactions. VLMs often exhibit "hallucinogenic" behavior, generating textual outputs not grounded in contextual multimodal information. We propose a new alignment algorithm that uses symbolic representations of clinical reasoning to ground VLMs in medical knowledge.
  arXiv  Detail & Related papers  (2024-05-29T23:19:28Z)
• Masked Contrastive Reconstruction for Cross-modal Medical Image-Report Retrieval [3.5314225883644945]
  Cross-modal medical image-report retrieval task plays a significant role in clinical diagnosis and various medical generative tasks. We propose an efficient framework named Masked Contrastive and Reconstruction (MCR), which takes masked data as the sole input for both tasks. This enhances task connections, reducing information interference and competition between them, while also substantially decreasing the required GPU memory and training time.
  arXiv  Detail & Related papers  (2023-12-26T01:14:10Z)
• Multi-task Paired Masking with Alignment Modeling for Medical Vision-Language Pre-training [55.56609500764344]
  We propose a unified framework based on Multi-task Paired Masking with Alignment (MPMA) to integrate the cross-modal alignment task into the joint image-text reconstruction framework. We also introduce a Memory-Augmented Cross-Modal Fusion (MA-CMF) module to fully integrate visual information to assist report reconstruction.
  arXiv  Detail & Related papers  (2023-05-13T13:53:48Z)
• Towards Cross-modality Medical Image Segmentation with Online Mutual Knowledge Distillation [71.89867233426597]
  In this paper, we aim to exploit the prior knowledge learned from one modality to improve the segmentation performance on another modality. We propose a novel Mutual Knowledge Distillation scheme to thoroughly exploit the modality-shared knowledge. Experimental results on the public multi-class cardiac segmentation data, i.e., MMWHS 2017, show that our method achieves large improvements on CT segmentation.
  arXiv  Detail & Related papers  (2020-10-04T10:25:13Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.