Dense Classification and Implanting for Few-Shot Learning

Yann Lifchitz, Yannis Avrithis, Sylvaine Picard, Andrei Bursuc; The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019, pp. 9258-9267

Abstract


Few-shot learning for deep neural networks is a highly challenging and key problem in 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. Implanting enables training of multiple layers in the few-shot regime, departing from most related methods derived from metric learning that train only the final layer. Both contributions show consistent gains when used individually or jointly and we report state of the art performance on few-shot classification on miniImageNet.

Related Material


[pdf]
[bibtex]
@InProceedings{Lifchitz_2019_CVPR,
author = {Lifchitz, Yann and Avrithis, Yannis and Picard, Sylvaine and Bursuc, Andrei},
title = {Dense Classification and Implanting for Few-Shot Learning},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2019}
}