QMix: Quality-aware Learning with Mixed Noise for Robust Retinal Disease Diagnosis

arXiv:2404.05169v1 Announce Type: new
Abstract: Due to the complexity of medical image acquisition and the difficulty of annotation, medical image datasets inevitably contain noise. Noisy data with wrong labels affects the robustness and generalization ability of deep neural networks. Previous noise learning methods mainly considered noise arising from images being mislabeled, i.e. label noise, assuming that all mislabeled images are of high image quality. However, medical images are prone to suffering extreme quality issues, i.e. data noise, where discriminative visual …

abstract acquisition annotation arxiv complexity cs.cv data datasets diagnosis disease disease diagnosis image image datasets images labels medical mixed networks neural networks noise quality robust robustness type