SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2207.01573 · ECCV · 2022

Embedding contrastive unsupervised features to cluster in-and out-of-distribution noise in corrupted image datasets

Kevin Mcguinness, Noel O'connor, Paul Albert, Eric Arazo

arXiv · PDF · Open in the Atlas

Code that ran

3 of 4 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 1 has no contract verdict; 2 failures of our instrument; 1 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2207.01573.json · badge: /api/ran/2207.01573.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
PaulAlbert31/SNCF community
Papers with Code archive
3 ran · 1 no recorded run
FunctionStatusWhere it lives
Path Ran
ran on a synthesized input
PaulAlbert31/SNCF/main_unsup.py
pointer only (licence: NONE) · get_code("324fbf3bfb96b604")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, PaulAlbert31/SNCF when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

make_data_loader Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
PaulAlbert31/SNCF/main_unsup.py
pointer only (licence: NONE) · get_code("0cb6c4fb7dcd4ceb")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, PaulAlbert31/SNCF when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

multi_class_loss Ran
ran; our contract draft was wrong, not the code
PaulAlbert31/SNCF/main_unsup.py
pointer only (licence: NONE) · get_code("932ae04bd6a4d4a5")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, PaulAlbert31/SNCF when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

Trainer Not yet run
unverified (harvested, no recorded run)
PaulAlbert31/SNCF/main_unsup.py
pointer only (licence: NONE) · get_code("1849e34db38e6f9c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, PaulAlbert31/SNCF when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 4 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Using search engines for web image retrieval is a tempting alternative to manual curation when creating an image dataset, but their main drawback remains the proportion of incorrect (noisy) samples retrieved. These noisy samples have been evidenced by previous works to be a mixture of in-distribution (ID) samples, assigned to the incorrect category but presenting similar visual semantics to other classes in the dataset, and out-of-distribution (OOD) images, which share no semantic correlation with any category from the dataset. The latter are, in practice, the dominant type of noisy images retrieved. To tackle this noise duality, we propose a two stage algorithm starting with a detection step where we use unsupervised contrastive feature learning to represent images in a feature space. We find that the alignment and uniformity principles of contrastive learning allow OOD samples to be linearly separated from ID samples on the unit hypersphere. We then spectrally embed the unsupervised representations using a fixed neighborhood size and apply an outlier sensitive clustering at the class level to detect the clean and OOD clusters as well as ID noisy outliers. We finally train a noise robust neural network that corrects ID noise to the correct category and utilizes OOD samples in a guided contrastive objective, clustering them to improve low-level features. Our algorithm improves the state-of-the-art results on synthetic noise image datasets as well as real-world web-crawled data. Our work is fully reproducible github.com/PaulAlbert31/SNCF.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2207.01573")
get_code_for_paper("2207.01573")
have("2207.01573")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2207.01573.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2207.01573.svg)](https://syntology.ai/paper/2207.01573)

Connect an agent — have() is free.