Boosting Medical Visual Understanding From Multi-Granular Language Learning

• URL: http://arxiv.org/abs/2511.15943v1
• Date: Thu, 20 Nov 2025 00:24:26 GMT
• Title: Boosting Medical Visual Understanding From Multi-Granular Language Learning
• Authors: Zihan Li, Yiqing Wang, Sina Farsiu, Paul Kinahan,
• Abstract summary: Contrastive Language-Image Pretraining (CLIP) has played a pivotal role in multimodal learning.<n>We propose Multi-Granular Language Learning (MGLL), a contrastive learning framework designed to improve multi-label and cross-granularity alignment.
• Score: 13.789642522499571
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recent advances in image-text pretraining have significantly enhanced visual understanding by aligning visual and textual representations. Contrastive Language-Image Pretraining (CLIP) has played a pivotal role in multimodal learning. However, its focus on single-label, single-granularity alignment limits its effectiveness in complex domains such as medical imaging, where images often correspond to multiple high-level labels (e.g., disease categories) across different annotation granularities (e.g., diagnostic description, clinical explanation). To address this, we propose Multi-Granular Language Learning (MGLL), a contrastive learning framework designed to improve both multi-label and cross-granularity alignment. MGLL leverages structured multi-label supervision, integrates textual descriptions across granularities, and introduces soft-label supervision with point-wise constraints to enhance alignment. MGLL employs smooth Kullback-Leibler (KL) divergence to ensure cross-granularity consistency while maintaining computational efficiency as a plug-and-play module for vision-language models. Pretrained on our constructed large-scale multi-granular datasets and evaluated across multiple datasets, MGLL outperforms other state-of-the-art methods in downstream tasks. The code is available at \href{https://github.com/HUANGLIZI/MGLL}{https://github.com/HUANGLIZI/MGLL}.

Related papers

• GMAT: Grounded Multi-Agent Clinical Description Generation for Text Encoder in Vision-Language MIL for Whole Slide Image Classification [4.922864692096282]
  Multiple Instance Learning (MIL) is the leading approach for whole slide image (WSI) classification.<n>Recent work has introduced vision-language models (VLMs) into MIL pipelines to incorporate medical knowledge.<n>We propose a vision-language MIL framework with two key contributions.
  arXiv  Detail & Related papers  (2025-08-02T09:59:39Z)
• SmartCLIP: Modular Vision-language Alignment with Identification Guarantees [59.16312652369709]
  Contrastive Language-Image Pre-training (CLIP)citepradford2021learning has emerged as a pivotal model in computer vision and multimodal learning.<n>CLIP struggles with potential information misalignment in many image-text datasets and suffers from entangled representation.<n>We introduce ours, a novel approach that identifies and aligns the most relevant visual and textual representations in a modular manner.
  arXiv  Detail & Related papers  (2025-07-29T22:26:20Z)
• Semantic-guided Representation Learning for Multi-Label Recognition [13.046479112800608]
  Multi-label Recognition (MLR) involves assigning multiple labels to each data instance in an image.<n>Recent Vision and Language Pre-training methods have made significant progress in tackling zero-shot MLR tasks.<n>We introduce a Semantic-guided Representation Learning approach (SigRL) that enables the model to learn effective visual and textual representations.
  arXiv  Detail & Related papers  (2025-04-04T08:15:08Z)
• Aligning Vision to Language: Annotation-Free Multimodal Knowledge Graph Construction for Enhanced LLMs Reasoning [10.761218096540976]
  Multimodal reasoning in Large Language Models (LLMs) struggles with incomplete knowledge and hallucination artifacts.<n>We propose Vision-align-to-Language integrated Knowledge Graph (VaLiK), a novel approach for constructing Multimodal Knowledge Graphs.
  arXiv  Detail & Related papers  (2025-03-17T09:31:14Z)
• ViLa-MIL: Dual-scale Vision-Language Multiple Instance Learning for Whole Slide Image Classification [52.405499816861635]
  Multiple instance learning (MIL)-based framework has become the mainstream for processing the whole slide image (WSI)<n>We propose a dual-scale vision-language multiple instance learning (ViLa-MIL) framework for whole slide image classification.
  arXiv  Detail & Related papers  (2025-02-12T13:28:46Z)
• Context-Based Semantic-Aware Alignment for Semi-Supervised Multi-Label Learning [37.13424985128905]
  Vision-language models pre-trained on large-scale image-text pairs could alleviate the challenge of limited labeled data under SSMLL setting.<n>We propose a context-based semantic-aware alignment method to solve the SSMLL problem.
  arXiv  Detail & Related papers  (2024-12-25T09:06:54Z)
• ClawMachine: Learning to Fetch Visual Tokens for Referential Comprehension [71.03445074045092]
  We propose ClawMachine, offering a new methodology that explicitly notates each entity using token collectives groups of visual tokens.<n>Our method unifies the prompt and answer of visual referential tasks without using additional syntax.<n>ClawMachine achieves superior performance on scene-level and referential understanding tasks with higher efficiency.
  arXiv  Detail & Related papers  (2024-06-17T08:39:16Z)
• UMG-CLIP: A Unified Multi-Granularity Vision Generalist for Open-World Understanding [90.74967596080982]
  This paper extends Contrastive Language-Image Pre-training (CLIP) with multi-granularity alignment. We develop a Unified Multi-Granularity learning framework, termed UMG-CLIP, which simultaneously empowers the model with versatile perception abilities. With parameter efficient tuning, UMG-CLIP surpasses current widely used CLIP variants and achieves state-of-the-art performance on diverse image understanding benchmarks.
  arXiv  Detail & Related papers  (2024-01-12T06:35:09Z)
• Scene Graph as Pivoting: Inference-time Image-free Unsupervised Multimodal Machine Translation with Visual Scene Hallucination [88.74459704391214]
  In this work, we investigate a more realistic unsupervised multimodal machine translation (UMMT) setup. We represent the input images and texts with the visual and language scene graphs (SG), where such fine-grained vision-language features ensure a holistic understanding of the semantics. Several SG-pivoting based learning objectives are introduced for unsupervised translation training. Our method outperforms the best-performing baseline by significant BLEU scores on the task and setup.
  arXiv  Detail & Related papers  (2023-05-20T18:17:20Z)
• Dense Contrastive Visual-Linguistic Pretraining [53.61233531733243]
  Several multimodal representation learning approaches have been proposed that jointly represent image and text. These approaches achieve superior performance by capturing high-level semantic information from large-scale multimodal pretraining. We propose unbiased Dense Contrastive Visual-Linguistic Pretraining to replace the region regression and classification with cross-modality region contrastive learning.
  arXiv  Detail & Related papers  (2021-09-24T07:20:13Z)

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.