DOI | Trouver le DOI : https://doi.org/10.1007/978-3-030-86520-7_12 |
---|
Auteur | Rechercher : Guo, Hongyu1 |
---|
Affiliation | - Conseil national de recherches du Canada. Technologies numériques
|
---|
Format | Texte, Chapitre de livre |
---|
Conférence | European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD 2021), Sept. 13-17, 2021, Bilbao, Spain [Held Online] |
---|
Sujet | label smoothing; model regularization; mixup |
---|
Résumé | Label Smoothing (LS) improves model generalization through penalizing models from generating overconfident output distributions. For each training sample the LS strategy smooths the one-hot encoded training signal by distributing its distribution mass over the non-ground truth classes. We extend this technique by considering example pairs, coined PLS. PLS first creates midpoint samples by averaging random sample pairs and then learns a smoothing distribution during training for each of these midpoint samples, resulting in midpoints with high uncertainty labels for training. We empirically show that PLS significantly outperforms LS, achieving up to 30% of relative classification error reduction. We also visualize that PLS produces very low winning softmax scores for both in and out of distribution samples. |
---|
Date de publication | 2021-09-10 |
---|
Maison d’édition | Springer |
---|
Dans | |
---|
Série | |
---|
Langue | anglais |
---|
Publications évaluées par des pairs | Oui |
---|
Exporter la notice | Exporter en format RIS |
---|
Signaler une correction | Signaler une correction (s'ouvre dans un nouvel onglet) |
---|
Identificateur de l’enregistrement | 626d0ead-4e83-43b5-aede-66bbaed53047 |
---|
Enregistrement créé | 2021-10-25 |
---|
Enregistrement modifié | 2021-10-25 |
---|