Fake it till you make it: Learning(s) from a synthetic ImageNet clone - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2022

Fake it till you make it: Learning(s) from a synthetic ImageNet clone

Résumé

Recent large-scale image generation models such as Stable Diffusion have exhibited an impressive ability to generate fairly realistic images starting from a very simple text prompt. Could such models render real images obsolete for training image prediction models? In this paper, we answer part of this provocative question by questioning the need for real images when training models for ImageNet classification. More precisely, provided only with the class names that have been used to build the dataset, we explore the ability of Stable Diffusion to generate synthetic clones of ImageNet and measure how useful they are for training classification models from scratch. We show that with minimal and class-agnostic prompt engineering those ImageNet clones we denote as ImageNet-SD are able to close a large part of the gap between models produced by synthetic images and models trained with real images for the several standard classification benchmarks that we consider in this study. More importantly, we show that models trained on synthetic images exhibit strong generalization properties and perform on par with models trained on real data.
Fichier principal
Vignette du fichier
ImageNet_SD_v1_1.pdf (36.25 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03916262 , version 1 (30-12-2022)
hal-03916262 , version 2 (03-04-2023)

Identifiants

Citer

Mert Bulent Sariyildiz, Karteek Alahari, Diane Larlus, Yannis Kalantidis. Fake it till you make it: Learning(s) from a synthetic ImageNet clone. 2022. ⟨hal-03916262v1⟩
780 Consultations
289 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More