CVMar 12, 2019

Dense Classification and Implanting for Few-Shot Learning

arXiv:1903.05050v1206 citations
Originality Incremental advance
AI Analysis

This addresses the problem of training deep neural networks with limited data for computer vision tasks, offering incremental improvements over prior methods.

The paper tackles few-shot learning by proposing dense classification over feature maps and implanting new neurons, achieving state-of-the-art results on miniImageNet with 62.5% (1-shot), 79.8% (5-shot), and 83.8% (10-shot) accuracy.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes