Learning to Segment from Noisy Annotations: A Spatial Correction Approach
Jiachen Yao, Yikai Zhang, Songzhu Zheng, Mayank Goswami, Prateek Prasanna, Chao Chen
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 tackle label noise in classification tasks. Their independent-noise assumptions do not fit label noise in segmentation task. In this paper, we propose a novel noise model for segmentation problems that encodes spatial correlation and bias, which are prominent in segmentation annotations. 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.
BibTeX
@inproceedings{
yao2023learning,
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},
booktitle={The Eleventh International Conference on Learning Representations },
year={2023},
url={https://openreview.net/forum?id=Qc_OopMEBnC}
}