Enregistré dans:
Détails bibliographiques
Auteurs principaux: Gao, Qiang, Wang, Yi, Zhang, Yong, Li, Yong, Deng, Yongbing, Du, Lan, Chen, Cunjian
Format: Preprint
Publié: 2026
Sujets:
Accès en ligne:https://arxiv.org/abs/2604.10912
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866915933913612288
author Gao, Qiang
Wang, Yi
Zhang, Yong
Li, Yong
Deng, Yongbing
Du, Lan
Chen, Cunjian
author_facet Gao, Qiang
Wang, Yi
Zhang, Yong
Li, Yong
Deng, Yongbing
Du, Lan
Chen, Cunjian
contents Medical image segmentation remains challenging due to limited fine-grained annotations, complex anatomical structures, and image degradation from noise, low contrast, or illumination variation. We propose TAMISeg, a text-guided segmentation framework that incorporates clinical language prompts and semantic distillation as auxiliary semantic cues to enhance visual understanding and reduce reliance on pixel-level fine-grained annotations. TAMISeg integrates three core components: a consistency-aware encoder pretrained with strong perturbations for robust feature extraction, a semantic encoder distillation module with supervision from a frozen DINOv3 teacher to enhance semantic discriminability, and a scale-adaptive decoder that segments anatomical structures across different spatial scales. Experiments on the Kvasir-SEG, MosMedData+, and QaTa-COV19 datasets demonstrate that TAMISeg consistently outperforms existing uni-modal and multi-modal methods in both qualitative and quantitative evaluations. Code will be made publicly available at https://github.com/qczggaoqiang/TAMISeg.
format Preprint
id arxiv_https___arxiv_org_abs_2604_10912
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle TAMISeg: Text-Aligned Multi-scale Medical Image Segmentation with Semantic Encoder Distillation
Gao, Qiang
Wang, Yi
Zhang, Yong
Li, Yong
Deng, Yongbing
Du, Lan
Chen, Cunjian
Computer Vision and Pattern Recognition
Medical image segmentation remains challenging due to limited fine-grained annotations, complex anatomical structures, and image degradation from noise, low contrast, or illumination variation. We propose TAMISeg, a text-guided segmentation framework that incorporates clinical language prompts and semantic distillation as auxiliary semantic cues to enhance visual understanding and reduce reliance on pixel-level fine-grained annotations. TAMISeg integrates three core components: a consistency-aware encoder pretrained with strong perturbations for robust feature extraction, a semantic encoder distillation module with supervision from a frozen DINOv3 teacher to enhance semantic discriminability, and a scale-adaptive decoder that segments anatomical structures across different spatial scales. Experiments on the Kvasir-SEG, MosMedData+, and QaTa-COV19 datasets demonstrate that TAMISeg consistently outperforms existing uni-modal and multi-modal methods in both qualitative and quantitative evaluations. Code will be made publicly available at https://github.com/qczggaoqiang/TAMISeg.
title TAMISeg: Text-Aligned Multi-scale Medical Image Segmentation with Semantic Encoder Distillation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2604.10912