Active Learning for Efficient Few-Shot Classification - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

Active Learning for Efficient Few-Shot Classification

Résumé

We introduce the problem of Active Few-Shot Classification (AFSC) where the objective is to classify a small, initially unlabeled, dataset given a very restrained labeling budget. This problem can be seen as a rival paradigm to classical Transductive Few-Shot Classification (TFSC), as both these approaches are applicable in similar conditions. We first propose a methodology that combines statistical inference, and an original two-tier active learning strategy that fits well into this framework. We then adapt several standard vision benchmarks from the field of TFSC. Our experiments show the potential benefits of AFSC can be substantial, with gains in average weighted accuracy of up to 10% compared to state-of-the-art TFSC methods for the same labeling budget. We believe this new paradigm could lead to new developments and standards in data-scarce learning settings.
Fichier non déposé

Dates et versions

hal-04173107 , version 1 (28-07-2023)

Identifiants

Citer

Aymane Abdali, Vincent Gripon, Lucas Drumetz, Bartosz Boguslawski. Active Learning for Efficient Few-Shot Classification. ICASSP 2023: IEEE International Conference on Acoustics, Speech and Signal Processing, Jun 2023, Rhodes Island, Greece. pp.1-5, ⟨10.1109/ICASSP49357.2023.10095220⟩. ⟨hal-04173107⟩
19 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More