Few-Shot Image Classification Benchmarks are Too Far From Reality: Build Back Better with Semantic Task Sampling - Archive ouverte HAL
Communication Dans Un Congrès Année : 2022

Few-Shot Image Classification Benchmarks are Too Far From Reality: Build Back Better with Semantic Task Sampling

Domaines

Intelligence artificielle [cs.AI]

Céline Hudelot  : Connectez-vous pour contacter le contributeur

https://hal.science/hal-04574156

Soumis le : lundi 13 mai 2024-23:42:56

Dernière modification le : lundi 21 octobre 2024-15:09:06

Consulter le texte intégral

Dates et versions

hal-04574156 , version 1 (13-05-2024)

Identifiants

Citer

Etienne Bennequin, Myriam Tami, Antoine Toubhans, Céline Hudelot. Few-Shot Image Classification Benchmarks are Too Far From Reality: Build Back Better with Semantic Task Sampling. 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Jun 2022, New Orleans, United States. pp.4766-4775, ⟨10.1109/CVPRW56347.2022.00523⟩. ⟨hal-04574156⟩

Exporter

BibTeX XML-TEI Dublin Core DC Terms EndNote DataCite

Collections

UGA CNRS LIG CENTRALESUPELEC MICS UNIV-PARIS-SACLAY GS-COMPUTER-SCIENCE HUB-IA LIG_SIDCH
23 Consultations
0 Téléchargements

Altmetric

Partager

More