Learning Confident Classifiers in the Presence of Label Noise

TL;DR

This paper introduces a probabilistic model for training confident classifiers and segmenters that effectively handle label noise, improving accuracy in noisy and real-world annotation scenarios.

Contribution

It presents a novel probabilistic framework with an information-based regularization and confidence-aware loss adjustment for noisy label learning in classification and segmentation.

Findings

Outperforms state-of-the-art methods on noisy MNIST, CIFAR-10, and Fashion-MNIST datasets.

Achieves superior results on medical image segmentation datasets like LIDC and RIGA.

Effectively filters out label noise and recovers ground-truth labels.

Abstract

The success of Deep Neural Network (DNN) models significantly depends on the quality of provided annotations. In medical image segmentation, for example, having multiple expert annotations for each data point is common to minimize subjective annotation bias. Then, the goal of estimation is to filter out the label noise and recover the ground-truth masks, which are not explicitly given. This paper proposes a probabilistic model for noisy observations that allows us to build a confident classification and segmentation models. To accomplish it, we explicitly model label noise and introduce a new information-based regularization that pushes the network to recover the ground-truth labels. In addition, for segmentation task we adjust the loss function by prioritizing learning in high-confidence regions where all the annotators agree on labeling. We evaluate the proposed method on a series of classification tasks such as noisy versions of MNIST, CIFAR-10, Fashion-MNIST datasets as well as CIFAR-10N, which is real-world dataset with noisy human annotations. Additionally, for segmentation task, we consider several medical imaging datasets, such as, LIDC and RIGA that reflect real-world inter-variability among multiple annotators. Our experiments show that our algorithm outperforms state-of-the-art solutions for the considered classification and segmentation problems.