Skip to Main content Skip to Navigation
Conference papers

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.
Document type :
Conference papers
Complete list of metadata

Cited literature [14 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01951954
Contributor : Timothéee Lesort <>
Submitted on : Friday, December 21, 2018 - 11:27:29 AM
Last modification on : Thursday, January 21, 2021 - 9:26:01 AM
Long-term archiving on: : Friday, March 22, 2019 - 2:08:17 PM

File

_NIPS_CL_Workshop__Continual_l...
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01951954, version 1

Collections

Citation

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⟩

Share

Metrics

Record views

238

Files downloads

225