Contrastive Learning for Online Semi-Supervised General Continual Learning - Archive ouverte HAL Access content directly
Conference Papers Year : 2022

Contrastive Learning for Online Semi-Supervised General Continual Learning

Abstract

We study Online Continual Learning with missing labels and propose SemiCon, a new contrastive loss designed for partly labeled data. We demonstrate its efficiency by devising a memory-based method trained on an unlabeled data stream, where every data added to memory is labeled using an oracle. Our approach outperforms existing semi-supervised methods when few labels are available, and obtain similar results to state-of-the-art supervised methods while using only 2.6% of labels on Split-CIFAR10 and 10% of labels on Split-CIFAR100.
Fichier principal
Vignette du fichier
ICIP_paper.pdf (517.26 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-03866436 , version 1 (22-11-2022)

Identifiers

Cite

Nicolas Michel, Romain Negrel, Giovanni Chierchia, Jean-François Bercher. Contrastive Learning for Online Semi-Supervised General Continual Learning. 2022 IEEE International Conference on Image Processing (ICIP), Oct 2022, Bordeaux, France. pp.1896-1900, ⟨10.1109/ICIP46576.2022.9897290⟩. ⟨hal-03866436⟩
59 View
54 Download

Altmetric

Share

Gmail Facebook X LinkedIn More