papers AI Learner
The Github is limit! Click to go to the new site.

Dense Classification and Implanting for Few-Shot Learning

2019-03-12
Yann Lifchitz, Yannis Avrithis, Sylvaine Picard, Andrei Bursuc

Abstract

Training deep neural networks from few examples is a highly challenging and key problem for many computer vision tasks. In this context, we are targeting knowledge transfer from a set with abundant data to other sets with few available examples. We propose two simple and effective solutions: (i) dense classification over feature maps, which for the first time studies local activations in the domain of few-shot learning, and (ii) implanting, that is, attaching new neurons to a previously trained network to learn new, task-specific features. On miniImageNet, we improve the prior state-of-the-art on few-shot classification, i.e., we achieve 62.5%, 79.8% and 83.8% on 5-way 1-shot, 5-shot and 10-shot settings respectively.

Abstract (translated by Google)
URL

http://arxiv.org/abs/1903.05050

PDF

http://arxiv.org/pdf/1903.05050


Similar Posts

Comments