Attenuating Catastrophic Forgetting by Joint Contrastive and Incremental Learning - Equipe Robot interaction, Ambient system, Machine learning, Behaviour, Optimization Access content directly
Conference Papers Year :

Attenuating Catastrophic Forgetting by Joint Contrastive and Incremental Learning

Abstract

In class incremental learning, discriminative models are trained to classify images while adapting to new instances and classes incrementally. Training a model to adapt to new classes without total access to previous class data, however, leads to the known problem of catastrophic forgetting of the previously learnt classes. To alleviate this problem, we show how we can build upon recent progress on contrastive learning methods. In particular, we develop an incremental learning approach for deep neural networks operating both at classification and representation level which alleviates forgetting and learns more general features for data classification. Experiments performed on several datasets demonstrate the superiority of the proposed method with respect to well known state-of-the-art methods.

Domains

Automatic
Fichier principal
Vignette du fichier
Ferdinand_Attenuating_Catastrophic_Forgetting_by_Joint_Contrastive_and_Incremental_Learning_CVPRW_2022_paper.pdf (1.11 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-03784379 , version 1 (23-09-2022)

Identifiers

Cite

Quentin Ferdinand, Benoit Clement, Quentin Oliveau, Gilles Le Chenadec, Panagiotis Papadakis. Attenuating Catastrophic Forgetting by Joint Contrastive and Incremental Learning. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Jun 2022, New-Orleans, United States. ⟨10.1109/CVPRW56347.2022.00423⟩. ⟨hal-03784379⟩
51 View
29 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More