Learning with Noisy Labels through Learnable Weighting and Centroid Similarity
This addresses a critical issue in domains like medical diagnosis and autonomous driving where label noise is common, though it appears incremental as it builds on existing insights about overfitting to noise.
The paper tackles the problem of training machine learning models with noisy labels, which degrade generalization, by proposing a method that uses class centroid distances and a discounting mechanism to reduce the influence of noisy samples, resulting in consistent outperformance of state-of-the-art techniques with significant accuracy improvements.
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