English

Relation U-Net

Image and Video Processing 2025-01-17 v1 Computer Vision and Pattern Recognition

Abstract

Towards clinical interpretations, this paper presents a new ''output-with-confidence'' segmentation neural network with multiple input images and multiple output segmentation maps and their pairwise relations. A confidence score of the test image without ground-truth can be estimated from the difference among the estimated relation maps. We evaluate the method based on the widely used vanilla U-Net for segmentation and our new model is named Relation U-Net which can output segmentation maps of the input images as well as an estimated confidence score of the test image without ground-truth. Experimental results on four public datasets show that Relation U-Net can not only provide better accuracy than vanilla U-Net but also estimate a confidence score which is linearly correlated to the segmentation accuracy on test images.

Keywords

Cite

@article{arxiv.2501.09101,
  title  = {Relation U-Net},
  author = {Sheng He and Rina Bao and P. Ellen Grant and Yangming Ou},
  journal= {arXiv preprint arXiv:2501.09101},
  year   = {2025}
}

Comments

ISIB 2025

R2 v1 2026-06-28T21:07:40.114Z