Local Propagation for Few-Shot Learning - Archive ouverte HAL Access content directly
Conference Papers Year : 2021

Local Propagation for Few-Shot Learning


Active learning typically focuses on training a model on few labeled examples alone, while unlabeled ones are only used for acquisition. In this work we depart from this setting by using both labeled and unlabeled data during model training across active learning cycles. We do so by using unsupervised feature learning at the beginning of the active learning pipeline and semi-supervised learning at every active learning cycle, on all available data. The former has not been investigated before in active learning, while the study of latter in the context of deep learning is scarce and recent findings are not conclusive with respect to its benefit. Our idea is orthogonal to acquisition strategies by using more data, much like ensemble methods use more models. By systematically evaluating on a number of popular acquisition strategies and datasets, we find that the use of unla-beled data during model training brings a surprising accuracy improvement in image classification, compared to the differences between acquisition strategies. We thus explore smaller label budgets, even one label per class.
Fichier principal
Vignette du fichier
C116.icpr20.few-local.pdf (1.03 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-03047534 , version 1 (08-12-2020)



Yann Lifchitz, Yannis Avrithis, Sylvaine Picard. Local Propagation for Few-Shot Learning. ICPR 2020 - 25th International Conference on Pattern Recognition, Jan 2021, Virtual, Italy. ⟨hal-03047534⟩
113 View
51 Download



Gmail Facebook X LinkedIn More