Papers › A Closer Look at Few-shot Classification Again

A Closer Look at Few-shot Classification Again

28 Jan 2023arXiv:2301.12246archive 2025-07-28

Xu Luo, Hao Wu, Ji Zhang, Lianli Gao, Jing Xu, Jingkuan Song

Few-shot classification consists of a training phase where a model is learned on a relatively large dataset and an adaptation phase where the learned model is adapted to previously-unseen tasks with limited labeled samples. In this paper, we empirically prove that the training algorithm and the adaptation algorithm can be completely disentangled, which allows algorithm analysis and design to be done individually for each phase. Our meta-analysis for each phase reveals several interesting insights that may help better understand key aspects of few-shot classification and connections with other fields such as visual representation learning and transfer learning. We hope the insights and research challenges revealed in this paper can inspire future work in related directions. Code and pre-trained models (in PyTorch) are available at https://github.com/Frankluox/CloserLookAgainFewShot.

PaperPDFCodeCode 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="2301.12246")

Code

Syntology Ran 3 of 16 code samples harvested from 2 repositories linked to this paper; 13 have no recorded run. Of those that ran: 3 ran · fixture could not drive it.

By repository: official repository: 15 samples from 2 repositories, 2 ran; 1 identical to code first harvested elsewhere. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

frankluox/closerlookagainfewshot officialmentioned in papermentioned on GitHubpytorch report
Frankluox/Pytorch-MetaDataset officialmentioned on GitHubpytorchMIT report
raflaf/fsl-benchmark-again mentioned 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

16 samples harvested; 3 ran; 0 honoured the contract we drafted; 13 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

3ran · fixture could not drive it
13unverified

Licence: 1 of the 16 samples is 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 2 repositories linked to this paper, official or community; each sample names its own and says which. Some samples are identical code Syntology first harvested from another repository; for those, this paper's copy is not located and its licence is not recorded. “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.

accuracy Frankluox/Pytorch-MetaDataset/utils.py official repository ran · fixture could not drive it fingerprinted MIT (permissive) · b47790190bfa0514 · report
trunc_normal_ frankluox/closerlookagainfewshot/architectures/backbone/DINO_ViT.py official repository ran · fixture could not drive it MIT (permissive) · 915b71e73a54fc97 · report
auto_resume_helper Frankluox/Pytorch-MetaDataset/utils.py official repository unverified MIT (permissive) · 0c32459bef92ff8c · report
build_model Frankluox/Pytorch-MetaDataset/models/build.py official repository unverified MIT (permissive) · b60ab7da028d1057 · report
build_optimizer Frankluox/Pytorch-MetaDataset/optimizer.py official repository unverified MIT (permissive) · 42c6a0eb1009e616 · report
build_scheduler Frankluox/Pytorch-MetaDataset/optimizer.py official repository unverified MIT (permissive) · febad46f3a8e0329 · report
create_logger Frankluox/Pytorch-MetaDataset/logger.py official repository unverified MIT (permissive) · 80450600f7f09b0a · report
get_config Frankluox/Pytorch-MetaDataset/config.py official repository unverified MIT (permissive) · ae3e079034ff133b · report
get_module Frankluox/Pytorch-MetaDataset/models/build.py official repository unverified MIT (permissive) · 2685107849023379 · report
load_checkpoint Frankluox/Pytorch-MetaDataset/utils.py official repository unverified MIT (permissive) · dce200bb0559f13b · report
process_cifar frankluox/closerlookagainfewshot/prepare_datasets.py official repository unverified MIT (permissive) · fcffd6777f074244 · report
process_mnist frankluox/closerlookagainfewshot/prepare_datasets.py official repository unverified MIT (permissive) · 33a2d0092101477f · report
process_quickdraw frankluox/closerlookagainfewshot/prepare_datasets.py official repository unverified MIT (permissive) · 2dc8ad16af4aad88 · report
update_config Frankluox/Pytorch-MetaDataset/config.py official repository unverified MIT (permissive) · ef39da1ccfb41dbb · report
vit_tiny frankluox/closerlookagainfewshot/architectures/backbone/DINO_ViT.py official repository unverified MIT (permissive) · 0a55ce5c7c8fd9fd · report
drop_path identical code first harvested elsewhere ran · fixture could not drive it fingerprinted licence of this copy not recorded · 55120f2026b56aa2 · report

Tasks

ClassificationRepresentation LearningTransfer Learning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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