Enhancing Abnormality Grounding for Vision Language Models with Knowledge Descriptions

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Li, Jun, Liu, Che, Bai, Wenjia, Arcucci, Rossella, Bercea, Cosmin I., Schnabel, Julia A.
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866909525463793664
author Li, Jun
Liu, Che
Bai, Wenjia
Arcucci, Rossella
Bercea, Cosmin I.
Schnabel, Julia A.
author_facet Li, Jun
Liu, Che
Bai, Wenjia
Arcucci, Rossella
Bercea, Cosmin I.
Schnabel, Julia A.
contents Visual Language Models (VLMs) have demonstrated impressive capabilities in visual grounding tasks. However, their effectiveness in the medical domain, particularly for abnormality detection and localization within medical images, remains underexplored. A major challenge is the complex and abstract nature of medical terminology, which makes it difficult to directly associate pathological anomaly terms with their corresponding visual features. In this work, we introduce a novel approach to enhance VLM performance in medical abnormality detection and localization by leveraging decomposed medical knowledge. Instead of directly prompting models to recognize specific abnormalities, we focus on breaking down medical concepts into fundamental attributes and common visual patterns. This strategy promotes a stronger alignment between textual descriptions and visual features, improving both the recognition and localization of abnormalities in medical images.We evaluate our method on the 0.23B Florence-2 base model and demonstrate that it achieves comparable performance in abnormality grounding to significantly larger 7B LLaVA-based medical VLMs, despite being trained on only 1.5% of the data used for such models. Experimental results also demonstrate the effectiveness of our approach in both known and previously unseen abnormalities, suggesting its strong generalization capabilities.
format Preprint
id arxiv_https___arxiv_org_abs_2503_03278
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Enhancing Abnormality Grounding for Vision Language Models with Knowledge Descriptions
Li, Jun
Liu, Che
Bai, Wenjia
Arcucci, Rossella
Bercea, Cosmin I.
Schnabel, Julia A.
Computer Vision and Pattern Recognition
Computation and Language
Visual Language Models (VLMs) have demonstrated impressive capabilities in visual grounding tasks. However, their effectiveness in the medical domain, particularly for abnormality detection and localization within medical images, remains underexplored. A major challenge is the complex and abstract nature of medical terminology, which makes it difficult to directly associate pathological anomaly terms with their corresponding visual features. In this work, we introduce a novel approach to enhance VLM performance in medical abnormality detection and localization by leveraging decomposed medical knowledge. Instead of directly prompting models to recognize specific abnormalities, we focus on breaking down medical concepts into fundamental attributes and common visual patterns. This strategy promotes a stronger alignment between textual descriptions and visual features, improving both the recognition and localization of abnormalities in medical images.We evaluate our method on the 0.23B Florence-2 base model and demonstrate that it achieves comparable performance in abnormality grounding to significantly larger 7B LLaVA-based medical VLMs, despite being trained on only 1.5% of the data used for such models. Experimental results also demonstrate the effectiveness of our approach in both known and previously unseen abnormalities, suggesting its strong generalization capabilities.
title Enhancing Abnormality Grounding for Vision Language Models with Knowledge Descriptions
topic Computer Vision and Pattern Recognition
Computation and Language
url https://arxiv.org/abs/2503.03278