English

Learning to Segment from Noisy Annotations: A Spatial Correction Approach

Image and Video Processing 2023-08-08 v1 Computer Vision and Pattern Recognition Machine Learning

Abstract

Noisy labels can significantly affect the performance of deep neural networks (DNNs). In medical image segmentation tasks, annotations are error-prone due to the high demand in annotation time and in the annotators' expertise. Existing methods mostly assume noisy labels in different pixels are \textit{i.i.d}. However, segmentation label noise usually has strong spatial correlation and has prominent bias in distribution. In this paper, we propose a novel Markov model for segmentation noisy annotations that encodes both spatial correlation and bias. Further, to mitigate such label noise, we propose a label correction method to recover true label progressively. We provide theoretical guarantees of the correctness of the proposed method. Experiments show that our approach outperforms current state-of-the-art methods on both synthetic and real-world noisy annotations.

Keywords

Cite

@article{arxiv.2308.02498,
  title  = {Learning to Segment from Noisy Annotations: A Spatial Correction Approach},
  author = {Jiachen Yao and Yikai Zhang and Songzhu Zheng and Mayank Goswami and Prateek Prasanna and Chao Chen},
  journal= {arXiv preprint arXiv:2308.02498},
  year   = {2023}
}
R2 v1 2026-06-28T11:48:21.745Z