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

HyperShot: Few-Shot Learning by Kernel HyperNetworks

About

Few-shot models aim at making predictions using a minimal number of labeled examples from a given task. The main challenge in this area is the one-shot setting where only one element represents each class. We propose HyperShot - the fusion of kernels and hypernetwork paradigm. Compared to reference approaches that apply a gradient-based adjustment of the parameters, our model aims to switch the classification module parameters depending on the task's embedding. In practice, we utilize a hypernetwork, which takes the aggregated information from support data and returns the classifier's parameters handcrafted for the considered problem. Moreover, we introduce the kernel-based representation of the support examples delivered to hypernetwork to create the parameters of the classification module. Consequently, we rely on relations between embeddings of the support examples instead of direct feature values provided by the backbone models. Thanks to this approach, our model can adapt to highly different tasks.

Marcin Sendera, Marcin Przewi\k{e}\'zlikowski, Konrad Karanowski, Maciej Zi\k{e}ba, Jacek Tabor, Przemys{\l}aw Spurek• 2022

Related benchmarks

TaskDatasetResultRank
Few-shot Image ClassificationMini-Imagenet (test)
Accuracy53.18
235
Few-shot classificationCUB (test)
Accuracy66.13
145
ClassificationOmniglot to EMNIST (test)
Accuracy90.81
51
5-way Cross-domain Classificationmini-ImageNet -> CUB cross-domain (test)
Accuracy58.86
42
Classificationmini-ImageNet 5-shot (test)
Accuracy69.62
25
ClassificationCaltech-UCSD Birds (CUB) 5-shot (test)
Accuracy80.07
15
Showing 6 of 6 rows

Other info

Follow for update