Papers › Few-shot Learning as Cluster-induced Voronoi Diagrams: A Geometric Approach

Few-shot Learning as Cluster-induced Voronoi Diagrams: A Geometric Approach

5 Feb 2022arXiv:2202.02471archive 2025-07-28

Chunwei Ma, Ziyun Huang, Mingchen Gao, Jinhui Xu

Few-shot learning (FSL) is the process of rapid generalization from abundant base samples to inadequate novel samples. Despite extensive research in recent years, FSL is still not yet able to generate satisfactory solutions for a wide range of real-world applications. To confront this challenge, we study the FSL problem from a geometric point of view in this paper. One observation is that the widely embraced ProtoNet model is essentially a Voronoi Diagram (VD) in the feature space. We retrofit it by making use of a recent advance in computational geometry called Cluster-induced Voronoi Diagram (CIVD). Starting from the simplest nearest neighbor model, CIVD gradually incorporates cluster-to-point and then cluster-to-cluster relationships for space subdivision, which is used to improve the accuracy and robustness at multiple stages of FSL. Specifically, we use CIVD (1) to integrate parametric and nonparametric few-shot classifiers; (2) to combine feature representation and surrogate representation; (3) and to leverage feature-level, transformation-level, and geometry-level heterogeneities for a better ensemble. Our CIVD-based workflow enables us to achieve new state-of-the-art results on mini-ImageNet, CUB, and tiered-ImagenNet datasets, with ∼2%-5% improvements upon the next best. To summarize, CIVD provides a mathematically elegant and geometrically interpretable framework that compensates for extreme data insufficiency, prevents overfitting, and allows for fast geometric ensemble for thousands of individual VD. These together make FSL stronger.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology: its repositories, every harvested function with whether it ran, its licence and the call to fetch it.

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

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2202.02471")

Code

Syntology Ran 4 of 12 code samples harvested from 1 repository linked to this paper; 8 have no recorded run. Of those that ran: 1 ran · our draft was wrong; 1 ran · fixture could not drive it; 2 ran with no contract checked.

By repository: official repository: 12 samples from 1 repository, 4 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

horsepurve/deepvoro officialmentioned in papermentioned on GitHubpytorchMIT 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

12 samples harvested; 4 ran; 0 honoured the contract we drafted; 8 have no recorded run. Read from Syntology's graph 2026-09-25; that is when this build read the record, not when the samples ran.

1ran · our draft was wrong
1ran · fixture could not drive it
2ran
8unverified

Licence: 0 of the 12 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from horsepurve/deepvoro. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

distribution_calibration horsepurve/deepvoro/evaluate_DC.py official repository ran · fixture could not drive it MIT (permissive) · 356115ab6aa3719e · report
euclidean_dist horsepurve/deepvoro/methods/protonet.py official repository ran · our draft was wrong fingerprinted MIT (permissive) · 4dd319c45d372246 · report
get_assigned_file horsepurve/deepvoro/io_utils.py official repository ran fingerprinted MIT (permissive) · 400a8db2fb9b1633 · report
get_resume_file horsepurve/deepvoro/io_utils.py official repository ran fingerprinted MIT (permissive) · 3f1d37e1fff407e2 · report
ClassesInRun horsepurve/deepvoro/FSLTask.py official repository unverified MIT (permissive) · 9ae865b05537face · report
GenerateRun horsepurve/deepvoro/FSLTask.py official repository unverified MIT (permissive) · 1905389d29839bd7 · report
ResNet10 horsepurve/deepvoro/backbone.py official repository unverified MIT (permissive) · 2582452f5ccbebc2 · report
ResNet18 horsepurve/deepvoro/backbone.py official repository unverified MIT (permissive) · d58f228480b8a193 · report
loadDataSet horsepurve/deepvoro/FSLTask.py official repository unverified MIT (permissive) · 0220810ba040f3d7 · report
mixup_data horsepurve/deepvoro/wrn_mixup_model.py official repository unverified MIT (permissive) · b53e6443d8a7fbf3 · report
parse_args horsepurve/deepvoro/io_utils.py official repository unverified MIT (permissive) · e12bb8a4ee28a833 · report
to_one_hot horsepurve/deepvoro/wrn_mixup_model.py official repository unverified MIT (permissive) · 61ea85418a6324dc · report

Tasks

Few-Shot Learning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

BASE

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