Papers › Diversity Helps: Unsupervised Few-shot Learning via Distribution Shift-based Data Augmentation

Diversity Helps: Unsupervised Few-shot Learning via Distribution Shift-based Data Augmentation

13 Apr 2020arXiv:2004.05805archive 2025-07-28

Tiexin Qin, Wenbin Li, Yinghuan Shi, Yang Gao

Few-shot learning aims to learn a new concept when only a few training examples are available, which has been extensively explored in recent years. However, most of the current works heavily rely on a large-scale labeled auxiliary set to train their models in an episodic-training paradigm. Such a kind of supervised setting basically limits the widespread use of few-shot learning algorithms. Instead, in this paper, we develop a novel framework called Unsupervised Few-shot Learning via Distribution Shift-based Data Augmentation (ULDA), which pays attention to the distribution diversity inside each constructed pretext few-shot task when using data augmentation. Importantly, we highlight the value and importance of the distribution diversity in the augmentation-based pretext few-shot tasks, which can effectively alleviate the overfitting problem and make the few-shot model learn more robust feature representations. In ULDA, we systemically investigate the effects of different augmentation techniques and propose to strengthen the distribution diversity (or difference) between the query set and support set in each few-shot task, by augmenting these two sets diversely (i.e., distribution shifting). In this way, even incorporated with simple augmentation techniques (e.g., random crop, color jittering, or rotation), our ULDA can produce a significant improvement. In the experiments, few-shot models learned by ULDA can achieve superior generalization performance and obtain state-of-the-art results in a variety of established few-shot learning tasks on Omniglot and miniImageNet. The source code is available in https://github.com/WonderSeven/ULDA.

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="2004.05805")

Code

Syntology Ran 0 of 13 code samples harvested from 1 repository linked to this paper; 13 have no recorded run.

By repository: official repository: 13 samples from 1 repository, 0 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

WonderSeven/ULDA 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

13 samples harvested; 0 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.

13unverified

Licence: 0 of the 13 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 WonderSeven/ULDA. “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.

Default_loader WonderSeven/ULDA/datasets/base_dataset.py official repository unverified MIT (permissive) · b7b4ce5261d43664 · report
PIL_loader WonderSeven/ULDA/datasets/base_dataset.py official repository unverified MIT (permissive) · a682370c88b559b3 · report
RGB_loader WonderSeven/ULDA/datasets/DataSets.py official repository unverified MIT (permissive) · 242d8f6ff665a8a0 · report
Rotate WonderSeven/ULDA/compare/Rotate_dataloader.py official repository unverified MIT (permissive) · b1962bd997947f9b · report
accuracy WonderSeven/ULDA/engine/fsl_baseline.py official repository unverified MIT (permissive) · e31cea644d08aaf3 · report
add_modules_for_DataParallel WonderSeven/ULDA/engine/checkpointer.py official repository unverified MIT (permissive) · a861bdb57b1efb9a · report
default_loader WonderSeven/ULDA/datasets/DataSets.py official repository unverified MIT (permissive) · f7c5285c241ce106 · report
get_function WonderSeven/ULDA/network/inits.py official repository unverified MIT (permissive) · c26bd451f1b4b267 · report
get_norm_layer WonderSeven/ULDA/network/net_tools.py official repository unverified MIT (permissive) · 7702313c16b1182f · report
load_model_directly WonderSeven/ULDA/engine/checkpointer.py official repository unverified MIT (permissive) · 75c1b60e3bf0b372 · report
one_hot WonderSeven/ULDA/network/net_tools.py official repository unverified MIT (permissive) · f1ac0078149b3155 · report
remove_modules_for_DataParallel WonderSeven/ULDA/engine/checkpointer.py official repository unverified MIT (permissive) · bb5c7b957820c064 · report
test WonderSeven/ULDA/engine/fsl_baseline.py official repository unverified MIT (permissive) · f347e7f86ec8d83d · report

Tasks

Data AugmentationDiversityFew-Shot LearningUnsupervised Few-Shot Image ClassificationUnsupervised Few-Shot Learning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Unsupervised Few-Shot Image Classification Mini-Imagenet 5-way (1-shot) ULDA Accuracy 40.71 #24 of 28 Archive leaderboard report
Unsupervised Few-Shot Image Classification Mini-Imagenet 5-way (5-shot) ULDA Accuracy 56.18 #22 of 28 Archive leaderboard report
Unsupervised Few-Shot Image Classification Tiered ImageNet 5-way (1-shot) ULDA Accuracy 41.77 #12 of 12 Archive leaderboard report
Unsupervised Few-Shot Image Classification Tiered ImageNet 5-way (5-shot) ULDA Accuracy 56.78 #12 of 12 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.

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