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
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Few-shot Image Classification | Mini-Imagenet (test) | -- | 235 | |
| 5-way Classification | miniImageNet (test) | -- | 231 | |
| 5-way Few-shot Classification | Mini-Imagenet (test) | 1-shot Accuracy62.53 | 141 | |
| Few-shot classification | miniImageNet standard (test) | 5-way 1-shot Acc62.53 | 138 | |
| 5-way Few-shot Image Classification | FC100 (test) | 1-shot Accuracy42.04 | 78 | |
| 5-way Few-shot Classification | miniImageNet 5-way (test) | 1-shot Acc62.53 | 39 | |
| Few-shot Image Classification | FC100 | 1-shot Acc42.04 | 31 | |
| 5-way Classification | FC100 | Accuracy (1-shot)42.04 | 8 |
Showing 8 of 8 rows