Rethinking Regularization with Random Label Smoothing

Author(s)

dos Santos, Claudio Filipi Goncalves ; Papa, Joao Paulo

• Document type: Journal article
• Source: NEURAL PROCESSING LETTERS; v. 56, n. 3, p. 10-pg., 2024-04-27.

Abstract

Regularization helps to improve machine learning techniques by penalizing the models during training. Such approaches act in either the input, internal, or output layers. Regarding the latter, label smoothing is widely used to introduce noise in the label vector, making learning more challenging. This work proposes a new label regularization method, Random Label Smoothing, that attributes random values to the labels while preserving their semantics during training. The idea is to change the entire label into fixed arbitrary values. Results show improvements in image classification and super-resolution tasks, outperforming state-of-the-art techniques for such purposes. (AU)

• FAPESP's process: 19/07665-4 - Center for Artificial Intelligence
• Grantee: Fabio Gagliardi Cozman
• Support Opportunities: Research Grants - Research Program in eScience and Data Science - Research Centers in Engineering Program
• FAPESP's process: 13/07375-0 - CeMEAI - Center for Mathematical Sciences Applied to Industry
• Grantee: Francisco Louzada Neto
• Support Opportunities: Research Grants - Research, Innovation and Dissemination Centers - RIDC
• FAPESP's process: 14/12236-1 - AnImaLS: Annotation of Images in Large Scale: what can machines and specialists learn from interaction?
• Grantee: Alexandre Xavier Falcão
• Support Opportunities: Research Projects - Thematic Grants