Home » Publication » 27907

Dettaglio pubblicazione

2023, , Pages -

Combining Distance to Class Centroids and Outlier Discounting for Improved Learning with Noisy Labels (13b Working paper)

Wani FAROOQ AHMAD, Bucarelli MARIA SOFIA, Silvestri Fabrizio

In this paper, we propose a new approach for addressing the challenge of training machine learning models in the presence of noisy labels. By combining a clever usage of distance to class centroids in the items' latent space with a discounting strategy to reduce the importance of samples far away from all the class centroids (i.e., outliers), our method effectively addresses the issue of noisy labels. Our approach is based on the idea that samples farther away from their respective class centroid in the early stages of training are more likely to be noisy. We demonstrate the effectiveness of our method through extensive experiments on several popular benchmark datasets. Our results show that our approach outperforms the state-of-the-art in this area, achieving significant improvements in classification accuracy when the dataset contains noisy labels.
Gruppo di ricerca: Theory of Deep Learning
© Università degli Studi di Roma "La Sapienza" - Piazzale Aldo Moro 5, 00185 Roma