</> Code with Papers by Syntology

Papers › HyperShot: Few-Shot Learning by Kernel HyperNetworks

HyperShot: Few-Shot Learning by Kernel HyperNetworks

21 Mar 2022arXiv:2203.11378archive 2025-07-28

Marcin Sendera, Marcin Przewięźlikowski, Konrad Karanowski, Maciej Zięba, Jacek Tabor, Przemysław Spurek

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.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

gmum/few-shot-hypernets-public officialmentioned on GitHubpytorchNOASSERTION report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Few-Shot Image ClassificationFew-Shot Learning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Few-Shot Image Classification CUB 200 5-way 1-shot HyperShot Accuracy 66.13 #32 of 36 Archive leaderboard report
Few-Shot Image Classification CUB 200 5-way 5-shot HyperShot Accuracy 80.07 #30 of 32 Archive leaderboard report
Few-Shot Image Classification Mini-ImageNet - 1-Shot Learning HyperShot Accuracy 53.18% #15 of 16 Archive leaderboard report
Few-Shot Image Classification Mini-ImageNet-CUB 5-way (1-shot) HyperShot Accuracy 40.03 #10 of 12 Archive leaderboard report
Few-Shot Image Classification Mini-ImageNet-CUB 5-way (5-shot) HyperShot Accuracy 58.86 #7 of 8 Archive leaderboard report
Few-Shot Image Classification Mini-Imagenet 5-way (5-shot) HyperShot Accuracy 69.62% #85 of 95 Archive leaderboard report
Few-Shot Image Classification OMNIGLOT-EMNIST 5-way (1-shot) HyperShot Accuracy 80.65 #1 of 2 Archive leaderboard report
Few-Shot Image Classification OMNIGLOT-EMNIST 5-way (5-shot) HyperShot Accuracy 90.81 #1 of 2 Archive leaderboard report
Few-Shot Learning Mini-Imagenet 5-way (1-shot) HyperShot Accuracy 53.18 #2 of 3 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

HyperNetwork

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections