2023/07/21 by Jiachen Yao, Yao, Jiachen, Yikai Zhang +9 · 2 citations
Computer Science · #Advanced Neural Network Applications #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #FOS: Electrical engineering #Image and Object Detection Techniques #Image and Video Processing (eess.IV) #Machine Learning (cs.LG) #Machine Learning and Data Classification #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.2308.02498
openalex publication_date 2023/07/21 · openalex created_date 2023/08/09 · openalex updated_date 2026/08/01
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 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.