Noisy Label Classification using Label Noise Selection with Test-Time Augmentation Cross-Entropy and NoiseMix Learning

TL;DR

This paper introduces a novel approach for training deep learning models with noisy labels by using test-time augmentation-based cross-entropy for noise detection and a NoiseMix data augmentation method to improve robustness and accuracy.

Contribution

It proposes TTA cross-entropy for effective noisy label detection and NoiseMix for robust classifier training, advancing noisy label learning techniques.

Findings

TTA cross-entropy outperforms conventional methods in noise detection.

NoiseMix improves classification accuracy and robustness against label noise.

Method demonstrates superior performance on skin lesion diagnosis dataset.

Abstract

As the size of the dataset used in deep learning tasks increases, the noisy label problem, which is a task of making deep learning robust to the incorrectly labeled data, has become an important task. In this paper, we propose a method of learning noisy label data using the label noise selection with test-time augmentation (TTA) cross-entropy and classifier learning with the NoiseMix method. In the label noise selection, we propose TTA cross-entropy by measuring the cross-entropy to predict the test-time augmented training data. In the classifier learning, we propose the NoiseMix method based on MixUp and BalancedMix methods by mixing the samples from the noisy and the clean label data. In experiments on the ISIC-18 public skin lesion diagnosis dataset, the proposed TTA cross-entropy outperformed the conventional cross-entropy and the TTA uncertainty in detecting label noise data in the label noise selection process. Moreover, the proposed NoiseMix not only outperformed the state-of-the-art methods in the classification performance but also showed the most robustness to the label noise in the classifier learning.