Learning with Noisy Labels through Learnable Weighting and Centroid Similarity

TL;DR

This paper presents a new method for training models with noisy labels by using class centroid distances and a discounting mechanism to reduce the influence of potentially noisy samples, improving accuracy.

Contribution

The authors introduce a novel approach that leverages learnable weighting based on centroid similarity to mitigate the effects of noisy labels during training.

Findings

Outperforms existing state-of-the-art methods on benchmark datasets.

Effectively reduces the impact of noisy labels in training.

Achieves significant accuracy improvements in noisy label scenarios.

Abstract

We introduce a novel method for training machine learning models in the presence of noisy labels, which are prevalent in domains such as medical diagnosis and autonomous driving and have the potential to degrade a model's generalization performance. Inspired by established literature that highlights how deep learning models are prone to overfitting to noisy samples in the later epochs of training, we propose a strategic approach. This strategy leverages the distance to class centroids in the latent space and incorporates a discounting mechanism, aiming to diminish the influence of samples that lie distant from all class centroids. By doing so, we effectively counteract the adverse effects of noisy labels. The foundational premise of our approach is the assumption that samples situated further from their respective class centroid in the initial stages of training are more likely to be associated with noise. Our methodology is grounded in robust theoretical principles and has been validated empirically through extensive experiments on several benchmark datasets. Our results show that our method consistently outperforms the existing state-of-the-art techniques, achieving significant improvements in classification accuracy in the presence of noisy labels. The code for our proposed loss function and supplementary materials is available at https://github.com/wanifarooq/NCOD