# Dense Classification and Implanting for Few-Shot Learning

## TL;DR

This paper introduces dense classification over feature maps and a novel implanting method to enhance few-shot learning, significantly improving performance on miniImageNet benchmarks.

## Contribution

It presents two new techniques—dense classification and implanting—that effectively transfer knowledge from abundant data to few-shot tasks in deep neural networks.

## Key findings

- Achieved state-of-the-art results on miniImageNet
- Improved 5-way 1-shot accuracy to 62.5%
- Enhanced 5-shot and 10-shot classification performance

## 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.