Skip to Main content Skip to Navigation
Conference papers

Selecting Relevant Features from a Multi-domain Representation for Few-shot Classification

Nikita Dvornik 1 Cordelia Schmid 2 Julien Mairal 1
1 Thoth - Apprentissage de modèles à partir de données massives
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann
2 WILLOW - Models of visual object recognition and scene understanding
DI-ENS - Département d'informatique - ENS Paris, Inria de Paris
Abstract : 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 multi-domain representation by training a set of semantically different feature extractors. Then, given a few-shot learning task, we use our multi-domain 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.
Complete list of metadata

Cited literature [54 references]  Display  Hide  Download
Contributor : Nikita Dvornik Connect in order to contact the contributor
Submitted on : Monday, July 20, 2020 - 2:57:26 PM
Last modification on : Thursday, March 17, 2022 - 10:08:54 AM


Files produced by the author(s)




Nikita Dvornik, Cordelia Schmid, Julien Mairal. Selecting Relevant Features from a Multi-domain Representation for Few-shot Classification. ECCV 2020 - European Conference on Computer Vision, Aug 2020, Glasgow / Virtual, United Kingdom. pp.769-786, ⟨10.1007/978-3-030-58607-2_45⟩. ⟨hal-02513241v3⟩



Record views


Files downloads