Saved in:
Bibliographic Details
Main Authors: Zeng, Shuang, Xie, Boxu, Zhu, Lei, Zhang, Xinliang, Hu, Jiakui, Yao, Zhengjian, Li, Yuanwei, Lu, Yuxing, Lu, Yanye
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2604.11164
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911588084088832
author Zeng, Shuang
Xie, Boxu
Zhu, Lei
Zhang, Xinliang
Hu, Jiakui
Yao, Zhengjian
Li, Yuanwei
Lu, Yuxing
Lu, Yanye
author_facet Zeng, Shuang
Xie, Boxu
Zhu, Lei
Zhang, Xinliang
Hu, Jiakui
Yao, Zhengjian
Li, Yuanwei
Lu, Yuxing
Lu, Yanye
contents Deep learning has greatly advanced medical image segmentation, but its success relies heavily on fully supervised learning, which requires dense annotations that are costly and time-consuming for 3D volumetric scans. Barely-supervised learning reduces annotation burden by using only a few labeled slices per volume. Existing methods typically propagate sparse annotations to unlabeled slices through geometric continuity to generate pseudo-labels, but this strategy lacks semantic understanding, often resulting in low-quality pseudo-labels. Furthermore, medical image segmentation is inherently a pixel-level visual understanding task, where accuracy fundamentally depends on the quality of local, fine-grained visual features. Inspired by this, we propose RADA, a novel Region-Aware Dual-encoder Auxiliary learning pipeline which introduces a dual-encoder framework pre-trained on Alpha-CLIP to extract fine-grained, region-specific visual features from the original images and limited annotations. The framework combines image-level fine-grained visual features with text-level semantic guidance, providing region-aware semantic supervision that bridges image-level semantics and pixel-level segmentation. Integrated into a triple-view training framework, RADA achieves SOTA performance under extremely sparse annotation settings on LA2018, KiTS19 and LiTS, demonstrating robust generalization across diverse datasets.
format Preprint
id arxiv_https___arxiv_org_abs_2604_11164
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle RADA: Region-Aware Dual-encoder Auxiliary learning for Barely-supervised Medical Image Segmentation
Zeng, Shuang
Xie, Boxu
Zhu, Lei
Zhang, Xinliang
Hu, Jiakui
Yao, Zhengjian
Li, Yuanwei
Lu, Yuxing
Lu, Yanye
Computer Vision and Pattern Recognition
Deep learning has greatly advanced medical image segmentation, but its success relies heavily on fully supervised learning, which requires dense annotations that are costly and time-consuming for 3D volumetric scans. Barely-supervised learning reduces annotation burden by using only a few labeled slices per volume. Existing methods typically propagate sparse annotations to unlabeled slices through geometric continuity to generate pseudo-labels, but this strategy lacks semantic understanding, often resulting in low-quality pseudo-labels. Furthermore, medical image segmentation is inherently a pixel-level visual understanding task, where accuracy fundamentally depends on the quality of local, fine-grained visual features. Inspired by this, we propose RADA, a novel Region-Aware Dual-encoder Auxiliary learning pipeline which introduces a dual-encoder framework pre-trained on Alpha-CLIP to extract fine-grained, region-specific visual features from the original images and limited annotations. The framework combines image-level fine-grained visual features with text-level semantic guidance, providing region-aware semantic supervision that bridges image-level semantics and pixel-level segmentation. Integrated into a triple-view training framework, RADA achieves SOTA performance under extremely sparse annotation settings on LA2018, KiTS19 and LiTS, demonstrating robust generalization across diverse datasets.
title RADA: Region-Aware Dual-encoder Auxiliary learning for Barely-supervised Medical Image Segmentation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2604.11164