Hard Sample Aware Noise Robust Learning for Histopathology Image Classification

5 Dec 2021  ·  Chuang Zhu, Wenkai Chen, Ting Peng, Ying Wang, Mulan Jin ·

Deep learning-based histopathology image classification is a key technique to help physicians in improving the accuracy and promptness of cancer diagnosis. However, the noisy labels are often inevitable in the complex manual annotation process, and thus mislead the training of the classification model. In this work, we introduce a novel hard sample aware noise robust learning method for histopathology image classification. To distinguish the informative hard samples from the harmful noisy ones, we build an easy/hard/noisy (EHN) detection model by using the sample training history. Then we integrate the EHN into a self-training architecture to lower the noise rate through gradually label correction. With the obtained almost clean dataset, we further propose a noise suppressing and hard enhancing (NSHE) scheme to train the noise robust model. Compared with the previous works, our method can save more clean samples and can be directly applied to the real-world noisy dataset scenario without using a clean subset. Experimental results demonstrate that the proposed scheme outperforms the current state-of-the-art methods in both the synthetic and real-world noisy datasets. The source code and data are available at https://github.com/bupt-ai-cz/HSA-NRL/.

PDF Abstract

Datasets


Introduced in the Paper:

Chaoyang

Used in the Paper:

CIFAR-10 WebVision DigestPath
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Learning with noisy labels Chaoyang HSANR ACCURACY 83.4 # 1
Image Classification Chaoyang HSANR Accuracy 83.4 # 1
Image Classification mini WebVision 1.0 HSA-NRL(Inception-ResNet-v2) Top-1 Accuracy 77.52 # 27

Methods