arXiv AI September 2, 2026 By Mohammed Oussama Benyahia, Marouane Tliba, Mohamed Amine Kerkouri, Taifour Yousra, Bin Wang, Max Bengtsson, Gorkem Durak, Elif Keles, Zuheng Ming, Marek Penhaker, Azeddine Beghdadi, Ulas Bagci, Aladine Chetouani

GazeRefine: Expert Gaze as a Test-Time Prompt for Training-Free Medical Image Segmentation

Read the original on arXiv AI →

GazeRefine is a training‑free framework that uses eye‑gaze data as an inference‑time prompt for zero‑shot medical image segmentation. It converts sparse, duration‑weighted fixations into foreground and background priors that initialize semantic prototypes in a frozen DINOv3 feature space, then iteratively refines these prototypes through discrimination, affinity propagation, and anchoring to the gaze guidance. The method achieves strong results on colonoscopy polyp segmentation and competitive performance on prostate MRI, demonstrating that gaze‑guided prototype refinement can enable segmentation without dense expert annotations or model fine‑tuning.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv Computer Vision

Sep 30

UniMedSeg: Unified In-Context Learning for Multi-Paradigm 2D/3D Medical Image Segmentation

arXiv:2607.12896v3 Announce Type: replace Abstract: Medical image segmentation foundation models are expected to generalize across diverse clinical scenarios, yet existing universal methods remain fr...

By Yunzhou Li, Jiesi Hu, Yanwu Yang, Hanyang Peng, Chenfei Ye, Jianfeng Cao, Yixuan Yuan, Ting Ma

llms computer-vision fine-tuning benchmarks

Hugging Face Trending Papers

Jul 7

OBBSeg: Irregular Lesion Segmentation under Oriented Bounding Box Annotations

Pixel-level annotation remains a major bottleneck in medical image segmentation, making weak supervision an attractive yet under-constrained alternative. We propose OBBSeg, an intermediate supervision paradigm guided by Oriented Bounding Boxes (OBBs) that bridges the gap between full and weak supervision.

computer-vision safety

arXiv Computer Vision

Sep 4

FoRIS: Progressive Foreground Refinement for Training-Free In-Context Segmentation

FoRIS is a training‑free in‑context segmentation framework that refines foreground masks through a coarse‑to‑fine process. It operates in three stages—Foreground Purification, Localization, and Consolidation—to suppress background noise, pinpoint target regions, and reconstruct complete foreground structures. The method achieves state‑of‑the‑art performance, improving mIoU by 4.5 and 4.8 points in 1‑shot and 5‑shot settings respectively.

By Ming Hu, Jianfu Yin, Mingyu Dou, Miaomiao Zhang, Yao Wang, Cong Hu, Bingliang Hu, Quan Wang

computer-vision benchmarks

arXiv AI

Jun 4

Enhancing MedSAM with a Lightweight Box Predictor for Medical Image Segmentation

arXiv:2606. 04705v1 Announce Type: cross Abstract: Semantic segmentation in medical imaging is a critical yet challenging task due to data scarcity and high variability across modalities.

By Amirhossein Movahedisefat, Amirreza Fateh, Mohammad Reza Mohammadi

rag computer-vision

arXiv AI

Oct 15

PR-MaGIC: Prompt Refinement Via Mask Decoder Gradient Flow For In-Context Segmentation

PR-MaGIC is a training‑free, test‑time framework that refines prompts for in‑context image segmentation by using gradient flow from the mask decoder of the Segment Anything Model (SAM). It integrates seamlessly into existing in‑context segmentation pipelines and employs a simple top‑1 selection strategy to stabilize performance. Extensive evaluations show that PR‑MaGIC consistently improves segmentation quality across multiple benchmarks without requiring additional training or architectural changes.

By Minjae Lee, Sungwoo Hur, Soojin Hwang, Won Hwa Kim

llms computer-vision benchmarks safety

arXiv Computer Vision

Sep 1

Learning To Focus: Anatomy-Guided Attention Regularization for Medical Image Classification

arXiv:2607.10851v2 Announce Type: replace Abstract: Medical image classification models are ideally expected to identify diagnostically relevant regions while making predictions, yet standard classif...

By Tonmoy Hossain, Atiqur Rahman, Farhana Hossain Swarnali, Miaomiao Zhang

computer-vision safety

One email a morning, machine-written

Related stories

UniMedSeg: Unified In-Context Learning for Multi-Paradigm 2D/3D Medical Image Segmentation

OBBSeg: Irregular Lesion Segmentation under Oriented Bounding Box Annotations

FoRIS: Progressive Foreground Refinement for Training-Free In-Context Segmentation

Enhancing MedSAM with a Lightweight Box Predictor for Medical Image Segmentation

PR-MaGIC: Prompt Refinement Via Mask Decoder Gradient Flow For In-Context Segmentation

Learning To Focus: Anatomy-Guided Attention Regularization for Medical Image Classification