Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Dense Classification and Implanting for Few-Shot Learning

About

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.

Yann Lifchitz, Yannis Avrithis, Sylvaine Picard, Andrei Bursuc• 2019

Related benchmarks

TaskDatasetResultRank
Few-shot Image ClassificationMini-Imagenet (test)--
235
5-way ClassificationminiImageNet (test)--
231
5-way Few-shot ClassificationMini-Imagenet (test)
1-shot Accuracy62.53
141
Few-shot classificationminiImageNet standard (test)
5-way 1-shot Acc62.53
138
5-way Few-shot Image ClassificationFC100 (test)
1-shot Accuracy42.04
78
5-way Few-shot ClassificationminiImageNet 5-way (test)
1-shot Acc62.53
39
Few-shot Image ClassificationFC100
1-shot Acc42.04
31
5-way ClassificationFC100
Accuracy (1-shot)42.04
8
Showing 8 of 8 rows

Other info

Follow for update