Generative Models from the perspective of Continual Learning - Archive ouverte HAL Access content directly
Conference Papers Year : 2019

Generative Models from the perspective of Continual Learning

Abstract

Which generative model is the most suitable for Continual Learning? This paper aims at evaluating and comparing generative models on disjoint sequential image generation tasks. We investigate how several models learn and forget, considering various strategies: rehearsal, regularization, generative replay and fine-tuning. We used two quantitative metrics to estimate the generation quality and memory ability. We experiment with sequential tasks on three commonly used benchmarks for Continual Learning (MNIST, Fashion MNIST). We found that among all models, the original GAN performs best and among Continual Learning strategies, gener-ative replay outperforms all other methods.
Fichier principal
Vignette du fichier
_NIPS_CL_Workshop__Continual_learning_for_generative_models.pdf (6.53 Mo) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01951954 , version 1 (21-12-2018)

Identifiers

  • HAL Id : hal-01951954 , version 1

Cite

Timothée Lesort, Hugo Caselles-Dupré, Michael Garcia-Ortiz, Jean-François Goudou, David Filliat. Generative Models from the perspective of Continual Learning. IJCNN - International Joint Conference on Neural Networks, Jul 2019, Budapest, Hungary. ⟨hal-01951954⟩
256 View
111 Download

Share

Gmail Facebook X LinkedIn More