Skip to Main content Skip to Navigation
Conference papers

Un Mixup Local pour empêcher les intrusions de variétés

Raphael Baena 1, 2 Lucas Drumetz 3, 1 Vincent Gripon 1, 2 
2 Lab-STICC_2AI - Equipe Algorithm Architecture Interactions
Lab-STICC - Laboratoire des sciences et techniques de l'information, de la communication et de la connaissance : UMR6285
3 Lab-STICC_OSE - Equipe Observations Signal & Environnement
Lab-STICC - Laboratoire des sciences et techniques de l'information, de la communication et de la connaissance : UMR6285
Abstract : Deployed in the context of supervised learning, Mixup is a data-dependent regularization technique that consists in linearly interpolating input samples and associated outputs. It has been shown to improve accuracy when used to train on standard machine learning datasets. However, authors have pointed out that Mixup can produce out-of-distribution virtual samples and even contradictions in the augmented training set, potentially resulting in adversarial effects. In this paper, we introduce Local Mixup in which distant input samples are weighted down when computing the loss. In constrained settings we demonstrate that Local Mixup can create a trade-off between bias and variance, with the extreme cases reducing to vanilla training and classical Mixup. Using standardized computer vision benchmarks, we also show that Local Mixup can improve accuracy.
Complete list of metadata

https://hal-imt-atlantique.archives-ouvertes.fr/hal-03693098
Contributor : Raphael Baena Connect in order to contact the contributor
Submitted on : Friday, June 10, 2022 - 11:17:06 AM
Last modification on : Wednesday, June 29, 2022 - 3:50:21 AM

File

baena717 (1).pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-03693098, version 1

Citation

Raphael Baena, Lucas Drumetz, Vincent Gripon. Un Mixup Local pour empêcher les intrusions de variétés. GRESTI 2022, Sep 2022, Nancy, France. ⟨hal-03693098⟩

Share

Metrics

Record views

0

Files downloads

0