Selecting Relevant Features from a Universal Representation for Few-shot Classification - Archive ouverte HAL Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2020

Selecting Relevant Features from a Universal Representation for Few-shot Classification

Résumé

Popular approaches for few-shot classification consist of first learning a generic data representation based on a large annotated dataset, before adapting the representation to new classes given only a few labeled samples. In this work, we propose a new strategy based on feature selection, which is both simpler and more effective than previous feature adaptation approaches. First, we obtain a universal representation by training a set of semantically different feature extractors. Then, given a few-shot learning task, we use our universal feature bank to automatically select the most relevant representations. We show that a simple non-parametric classifier built on top of such features produces high accuracy and generalizes to domains never seen during training, which leads to state-of-the-art results on MetaDataset and improved accuracy on mini-ImageNet.
Fichier principal
Vignette du fichier
arxiv.pdf (1.36 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-02513241 , version 1 (20-03-2020)
hal-02513241 , version 2 (22-03-2020)
hal-02513241 , version 3 (20-07-2020)

Identifiants

Citer

Nikita Dvornik, Cordelia Schmid, Julien Mairal. Selecting Relevant Features from a Universal Representation for Few-shot Classification. 2020. ⟨hal-02513241v2⟩
489 Consultations
307 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More