SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2111.01004 · NeurIPS · 2021

Improving Contrastive Learning on Imbalanced Seed Data via Open-World Sampling

Ting Chen, Tianlong Chen, Zhangyang Wang, Ziyu Jiang

arXiv · PDF · Open in the Atlas

Code that ran

5 of 5 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 0 have no contract verdict; 5 failures of our instrument; 0 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/2111.01004.json · badge: /api/ran/2111.01004.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
VITA-Group/MAK canonical (classifier label)
classifier basis: classifier_2025
4 ran · 0 no recorded run
vita-group/mak community
Papers with Code archive
1 ran · 0 no recorded run
FunctionStatusWhere it lives
cal_cloest_distance_to_feature_centroid Ran
ran; our contract draft was wrong, not the code
VITA-Group/MAK/sampling.py
pointer only (licence: NONE) · get_code("69577a4f9e272824")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, VITA-Group/MAK 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.

cvt_state_dict Ran
ran; our contract draft was wrong, not the code
VITA-Group/MAK/train_imagenet.py
pointer only (licence: NONE) · get_code("08609c2e75193cba")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, VITA-Group/MAK 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.

k_core_set_greedy Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
vita-group/mak/sampling.py
pointer only (licence: NONE) · get_code("f241d92c8eef804f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, vita-group/mak 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.

reOrderData Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
VITA-Group/MAK/sampling.py
pointer only (licence: NONE) · get_code("e7f852c80b33e84f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, VITA-Group/MAK 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.

read_data_dir Ran
ran; our contract draft was wrong, not the code
VITA-Group/MAK/sampling.py
pointer only (licence: NONE) · get_code("aadbf031601ccc1d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, VITA-Group/MAK 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.

Also present in other papers' code

Of 5 samples lifted from this paper's linked repositories, 5 carry a function identity and 0 do not. Of the 5 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 5 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

Contrastive learning approaches have achieved great success in learning visual representations with few labels of the target classes. That implies a tantalizing possibility of scaling them up beyond a curated "seed" benchmark, to incorporating more unlabeled images from the internet-scale external sources to enhance its performance. However, in practice, larger amount of unlabeled data will require more computing resources due to the bigger model size and longer training needed. Moreover, open-world unlabeled data usually follows an implicit long-tail class or attribute distribution, many of which also do not belong to the target classes. Blindly leveraging all unlabeled data hence can lead to the data imbalance as well as distraction issues. This motivates us to seek a principled approach to strategically select unlabeled data from an external source, in order to learn generalizable, balanced and diverse representations for relevant classes. In this work, we present an open-world unlabeled data sampling framework called Model-Aware K-center (MAK), which follows three simple principles: (1) tailness, which encourages sampling of examples from tail classes, by sorting the empirical contrastive loss expectation (ECLE) of samples over random data augmentations; (2) proximity, which rejects the out-of-distribution outliers that may distract training; and (3) diversity, which ensures diversity in the set of sampled examples. Empirically, using ImageNet-100-LT (without labels) as the seed dataset and two "noisy" external data sources, we demonstrate that MAK can consistently improve both the overall representation quality and the class balancedness of the learned features, as evaluated via linear classifier evaluation on full-shot and few-shot settings. The code is available at: https://github.com/VITA-Group/MAK.

For agents

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

get_harvested_code_for_paper("2111.01004")
get_code_for_paper("2111.01004")
have("2111.01004")

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

curl https://syntology.ai/api/ran/2111.01004.json

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

[![Syntology run record](https://syntology.ai/api/ran/2111.01004.svg)](https://syntology.ai/paper/2111.01004)

Connect an agent — have() is free.