Knowledge to Sight: Reasoning over Visual Attributes via Knowledge Decomposition for Abnormality Grounding

• URL: http://arxiv.org/abs/2508.04572v1
• Date: Wed, 06 Aug 2025 15:54:44 GMT
• Title: Knowledge to Sight: Reasoning over Visual Attributes via Knowledge Decomposition for Abnormality Grounding
• Abstract summary: We propose textbfKnowledge to Sight (K2Sight), a framework that introduces structured supervision by decomposing visual attributes.<n>Unlike conventional report-level supervision, our approach explicitly bridges domain knowledge and spatial structure.<n>We train compact models with 0.23B and 2B semantic parameters using only 1.5% of the data required by state-of-the-art medical VLMs.
• Score: 14.354891415427154
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In this work, we address the problem of grounding abnormalities in medical images, where the goal is to localize clinical findings based on textual descriptions. While generalist Vision-Language Models (VLMs) excel in natural grounding tasks, they often struggle in the medical domain due to rare, compositional, and domain-specific terms that are poorly aligned with visual patterns. Specialized medical VLMs address this challenge via large-scale domain pretraining, but at the cost of substantial annotation and computational resources. To overcome these limitations, we propose \textbf{Knowledge to Sight (K2Sight)}, a framework that introduces structured semantic supervision by decomposing clinical concepts into interpretable visual attributes, such as shape, density, and anatomical location. These attributes are distilled from domain ontologies and encoded into concise instruction-style prompts, which guide region-text alignment during training. Unlike conventional report-level supervision, our approach explicitly bridges domain knowledge and spatial structure, enabling data-efficient training of compact models. We train compact models with 0.23B and 2B parameters using only 1.5\% of the data required by state-of-the-art medical VLMs. Despite their small size and limited training data, these models achieve performance on par with or better than 7B+ medical VLMs, with up to 9.82\% improvement in $mAP_{50}$. Code and models: \href{https://lijunrio.github.io/K2Sight/}{\textcolor{SOTAPink}{https://lijunrio.github.io/K2Sight/}}.

Related papers

• MedGround: Bridging the Evidence Gap in Medical Vision-Language Models with Verified Grounding Data [32.65971100171597]
  We introduce MedGround, an automated pipeline that transforms segmentation resources into high-quality medical referring grounding data.<n>We also present MedGround-35K, a novel multimodal medical dataset.
  arXiv  Detail & Related papers  (2026-01-11T10:34:18Z)
• XBench: A Comprehensive Benchmark for Visual-Language Explanations in Chest Radiography [6.447908430647854]
  We present the first systematic benchmark for evaluating cross-modal interpretability in chest X-rays.<n>We generate visual explanations using cross-attention and similarity-based localization maps.<n>We quantitatively assess their alignment with radiologist-annotated regions across multiple pathologies.
  arXiv  Detail & Related papers  (2025-10-22T13:52:19Z)
• Self-Supervised Anatomical Consistency Learning for Vision-Grounded Medical Report Generation [61.350584471060756]
  Vision-grounded medical report generation aims to produce clinically accurate descriptions of medical images.<n>We propose Self-Supervised Anatomical Consistency Learning (SS-ACL) to align generated reports with corresponding anatomical regions.<n>SS-ACL constructs a hierarchical anatomical graph inspired by the invariant top-down inclusion structure of human anatomy.
  arXiv  Detail & Related papers  (2025-09-30T08:59:06Z)
• RAU: Reference-based Anatomical Understanding with Vision Language Models [26.06602931463068]
  We introduce RAU, a framework for reference-based anatomical understanding with vision-language models (VLMs)<n>We first show that a VLM learns to identify anatomical regions through relative spatial reasoning between reference and target images.<n>Next, we demonstrate that the VLM-derived spatial cues can be seamlessly integrated with the fine-grained segmentation capability of SAM2.
  arXiv  Detail & Related papers  (2025-09-26T14:32:03Z)
• MedGround-R1: Advancing Medical Image Grounding via Spatial-Semantic Rewarded Group Relative Policy Optimization [19.70803794316208]
  Medical Image Grounding (MIG) involves localizing specific regions in medical images based on textual descriptions.<n>Existing Vision-Language Models (VLMs) for MIG often rely on Supervised Fine-Tuning (SFT) with large amounts of Chain-of-Thought (CoT) reasoning annotations.<n>We propose the Spatial-Semantic Rewarded Group Relative Policy Optimization to train the model without CoT reasoning annotations.
  arXiv  Detail & Related papers  (2025-07-01T21:51:42Z)
• Leveraging the Structure of Medical Data for Improved Representation Learning [12.175375511821352]
  Building generalizable medical AI systems requires pretraining strategies that are data-efficient and domain-aware.<n>We propose a self-supervised framework that leverages the inherent structure of medical datasets.<n>We show strong performance compared to supervised objectives and baselines being trained without leveraging structure.
  arXiv  Detail & Related papers  (2025-07-01T11:14:45Z)
• Seeing the Trees for the Forest: Rethinking Weakly-Supervised Medical Visual Grounding [50.483761005446]
  Current models struggle to associate textual descriptions with disease regions due to inefficient attention mechanisms and a lack of fine-grained token representations.<n>We introduce Disease-Aware Prompting (DAP), which uses the explainability map of a VLM to identify the appropriate image features.<n>DAP improves visual grounding accuracy by 20.74% compared to state-of-the-art methods across three major chest X-ray datasets.
  arXiv  Detail & Related papers  (2025-05-21T05:16:45Z)
• From Gaze to Insight: Bridging Human Visual Attention and Vision Language Model Explanation for Weakly-Supervised Medical Image Segmentation [46.99748372216857]
  Vision-language models (VLMs) provide semantic context through textual descriptions but lack explanation precision required.<n>We propose a teacher-student framework that integrates both gaze and language supervision, leveraging their complementary strengths.<n>Our method achieves Dice scores of 80.78%, 80.53%, and 84.22%, respectively, improving 3-5% over gaze baselines without increasing the annotation burden.
  arXiv  Detail & Related papers  (2025-04-15T16:32:15Z)
• EXGRA-MED: Extended Context Graph Alignment for Medical Vision- Language Models [69.40730368630003]
  We introduce EXGRA-MED, a novel framework for vision-language integration in medical AI.<n>It jointly aligns images, instruction responses, and extended captions in the latent space, advancing semantic grounding and cross-modal coherence.<n>It matches LLAVA-MED's performance using just 10% of pre-training data, achieving a 20.13% gain on VQA-RAD and approaching full-data performance.
  arXiv  Detail & Related papers  (2024-10-03T15:52:03Z)
• A Textbook Remedy for Domain Shifts: Knowledge Priors for Medical Image Analysis [48.84443450990355]
  Deep networks have achieved broad success in analyzing natural images, when applied to medical scans, they often fail in unexcepted situations. We investigate this challenge and focus on model sensitivity to domain shifts, such as data sampled from different hospitals or data confounded by demographic variables such as sex, race, etc, in the context of chest X-rays and skin lesion images. Taking inspiration from medical training, we propose giving deep networks a prior grounded in explicit medical knowledge communicated in natural language.
  arXiv  Detail & Related papers  (2024-05-23T17:55:02Z)
• Medical Vision-Language Pre-Training for Brain Abnormalities [96.1408455065347]
  We show how to automatically collect medical image-text aligned data for pretraining from public resources such as PubMed. In particular, we present a pipeline that streamlines the pre-training process by initially collecting a large brain image-text dataset. We also investigate the unique challenge of mapping subfigures to subcaptions in the medical domain.
  arXiv  Detail & Related papers  (2024-04-27T05:03:42Z)
• MedContext: Learning Contextual Cues for Efficient Volumetric Medical Segmentation [25.74088298769155]
  We propose a universal training framework called MedContext for 3D medical segmentation. Our approach effectively learns self supervised contextual cues jointly with the supervised voxel segmentation task. The effectiveness of MedContext is validated across multiple 3D medical datasets and four state-of-the-art model architectures.
  arXiv  Detail & Related papers  (2024-02-27T17:58:05Z)
• Class Attention to Regions of Lesion for Imbalanced Medical Image Recognition [59.28732531600606]
  We propose a framework named textbfClass textbfAttention to textbfREgions of the lesion (CARE) to handle data imbalance issues. The CARE framework needs bounding boxes to represent the lesion regions of rare diseases. Results show that the CARE variants with automated bounding box generation are comparable to the original CARE framework.
  arXiv  Detail & Related papers  (2023-07-19T15:19:02Z)
• LVM-Med: Learning Large-Scale Self-Supervised Vision Models for Medical Imaging via Second-order Graph Matching [59.01894976615714]
  We introduce LVM-Med, the first family of deep networks trained on large-scale medical datasets. We have collected approximately 1.3 million medical images from 55 publicly available datasets. LVM-Med empirically outperforms a number of state-of-the-art supervised, self-supervised, and foundation models.
  arXiv  Detail & Related papers  (2023-06-20T22:21:34Z)
• Learnable Weight Initialization for Volumetric Medical Image Segmentation [66.3030435676252]
  We propose a learnable weight-based hybrid medical image segmentation approach. Our approach is easy to integrate into any hybrid model and requires no external training data. Experiments on multi-organ and lung cancer segmentation tasks demonstrate the effectiveness of our approach.
  arXiv  Detail & Related papers  (2023-06-15T17:55:05Z)
• Vision-Language Modelling For Radiological Imaging and Reports In The Low Data Regime [70.04389979779195]
  This paper explores training medical vision-language models (VLMs) where the visual and language inputs are embedded into a common space. We explore several candidate methods to improve low-data performance, including adapting generic pre-trained models to novel image and text domains. Using text-to-image retrieval as a benchmark, we evaluate the performance of these methods with variable sized training datasets of paired chest X-rays and radiological reports.
  arXiv  Detail & Related papers  (2023-03-30T18:20:00Z)
• medXGAN: Visual Explanations for Medical Classifiers through a Generative Latent Space [38.57696431713717]
  We propose a novel medical imaging generative framework, medXGAN, to explain what a medical adversarial focuses on in its binary predictions. By encoding domain knowledge of medical images, we are able to disentangle anatomical structure and pathology, leading to fine-grained visualization. Our method outperforms baselines such as Gradient-Weighted Class Activation Mapping (Grad-CAM) and Integrated Gradients in localization and explanatory ability.
  arXiv  Detail & Related papers  (2022-04-11T19:27:15Z)

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.