all AI news
Understanding Why Label Smoothing Degrades Selective Classification and How to Fix It
March 25, 2024, 4:41 a.m. | Guoxuan Xia, Olivier Laurent, Gianni Franchi, Christos-Savvas Bouganis
cs.LG updates on arXiv.org arxiv.org
Abstract: Label smoothing (LS) is a popular regularisation method for training deep neural network classifiers due to its effectiveness in improving test accuracy and its simplicity in implementation. "Hard" one-hot labels are "smoothed" by uniformly distributing probability mass to other classes, reducing overfitting. In this work, we reveal that LS negatively affects selective classification (SC) - where the aim is to reject misclassifications using a model's predictive uncertainty. We first demonstrate empirically across a range of …
abstract accuracy arxiv classification classifiers cs.ai cs.cv cs.lg deep neural network hot implementation improving labels network neural network overfitting popular probability simplicity test training type understanding
More from arxiv.org / cs.LG updates on arXiv.org
Jobs in AI, ML, Big Data
Founding AI Engineer, Agents
@ Occam AI | New York
AI Engineer Intern, Agents
@ Occam AI | US
AI Research Scientist
@ Vara | Berlin, Germany and Remote
Data Architect
@ University of Texas at Austin | Austin, TX
Data ETL Engineer
@ University of Texas at Austin | Austin, TX
Codec Avatars Research Engineer
@ Meta | Pittsburgh, PA