Papers › Rethinking Generalization in Few-Shot Classification

Rethinking Generalization in Few-Shot Classification

15 Jun 2022arXiv:2206.07267archive 2025-07-28

Markus Hiller, Rongkai Ma, Mehrtash Harandi, Tom Drummond

Single image-level annotations only correctly describe an often small subset of an image's content, particularly when complex real-world scenes are depicted. While this might be acceptable in many classification scenarios, it poses a significant challenge for applications where the set of classes differs significantly between training and test time. In this paper, we take a closer look at the implications in the context of few-shot learning. Splitting the input samples into patches and encoding these via the help of Vision Transformers allows us to establish semantic correspondences between local regions across images and independent of their respective class. The most informative patch embeddings for the task at hand are then determined as a function of the support set via online optimization at inference time, additionally providing visual interpretability of `what matters most' in the image. We build on recent advances in unsupervised training of networks via masked image modelling to overcome the lack of fine-grained labels and learn the more general statistical structure of the data while avoiding negative image-level annotation influence, aka supervision collapse. Experimental results show the competitiveness of our approach, achieving new state-of-the-art results on four popular few-shot classification benchmarks for $5$-shot and $1$-shot scenarios.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology 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="2206.07267")

Code

Syntology Ran 2 of 3 code samples harvested from 1 repository linked to this paper; 1 has no recorded run. Of those that ran: 1 ran · honoured contract; 1 ran · our draft was wrong.

By repository: official repository: 3 samples from 1 repository, 2 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

mrkshllr/FewTURE officialmentioned in papermentioned on GitHubpytorch 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

3 samples harvested; 2 ran; 1 honoured the contract we drafted; 1 has no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · honoured contract
1ran · our draft was wrong
1unverified

Licence: 3 of the 3 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 mrkshllr/FewTURE. “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.

compute_emb_cosine_similarity mrkshllr/FewTURE/train_metatrain_FewTURE.py official repository ran · honoured contract fingerprinted licence not identified · pointer only · 7322771f6296426b · report
get_patch_embeddings mrkshllr/FewTURE/train_metatrain_FewTURE.py official repository ran · our draft was wrong licence not identified · pointer only · 79257feee546698e · report
set_up_dataset mrkshllr/FewTURE/train_metatrain_FewTURE.py official repository unverified licence not identified · pointer only · d19384c7d90e54d8 · report

Tasks

ClassificationFew-Shot Image ClassificationFew-Shot Learning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Few-Shot Image Classification CIFAR-FS 5-way (1-shot) FewTURE Accuracy 77.76 #17 of 38 Archive leaderboard report
Few-Shot Image Classification CIFAR-FS 5-way (5-shot) FewTURE Accuracy 88.90 #18 of 39 Archive leaderboard report
Few-Shot Image Classification FC100 5-way (1-shot) FewTURE Accuracy 47.68 #11 of 22 Archive leaderboard report
Few-Shot Image Classification FC100 5-way (5-shot) FewTURE Accuracy 63.81 #12 of 22 Archive leaderboard report
Few-Shot Image Classification Mini-Imagenet 5-way (1-shot) FewTURE Accuracy 72.40 #27 of 105 Archive leaderboard report
Few-Shot Image Classification Mini-Imagenet 5-way (5-shot) FewTURE Accuracy 86.38 #21 of 95 Archive leaderboard report
Few-Shot Image Classification Tiered ImageNet 5-way (1-shot) FewTURE Accuracy 76.32 #18 of 49 Archive leaderboard report
Few-Shot Image Classification Tiered ImageNet 5-way (5-shot) FewTURE Accuracy 89.96 #7 of 51 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

AttentionLayer NormalizationLinear LayerMulti-Head AttentionResidual ConnectionSoftmaxSwin TransformerTestVision Transformer

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