Papers › Parametric Contrastive Learning

Parametric Contrastive Learning

26 Jul 2021ICCV 2021 10arXiv:2107.12028archive 2025-07-28

Jiequan Cui, Zhisheng Zhong, Shu Liu, Bei Yu, Jiaya Jia

In this paper, we propose Parametric Contrastive Learning (PaCo) to tackle long-tailed recognition. Based on theoretical analysis, we observe supervised contrastive loss tends to bias on high-frequency classes and thus increases the difficulty of imbalanced learning. We introduce a set of parametric class-wise learnable centers to rebalance from an optimization perspective. Further, we analyze our PaCo loss under a balanced setting. Our analysis demonstrates that PaCo can adaptively enhance the intensity of pushing samples of the same class close as more samples are pulled together with their corresponding centers and benefit hard example learning. Experiments on long-tailed CIFAR, ImageNet, Places, and iNaturalist 2018 manifest the new state-of-the-art for long-tailed recognition. On full ImageNet, models trained with PaCo loss surpass supervised contrastive learning across various ResNet backbones, e.g., our ResNet-200 achieves 81.8% top-1 accuracy. Our code is available at https://github.com/dvlab-research/Parametric-Contrastive-Learning.

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="2107.12028")

Code

Syntology Ran 1 of 3 code samples harvested from 3 repositories linked to this paper; 2 have no recorded run. Of those that ran: 1 ran with no contract checked.

By repository: official repository: 1 sample from 1 repository, 1 ran; community (archive-listed): 2 samples from 2 repositories, 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.

dvlab-research/parametric-contrastive-learning officialmentioned in papermentioned on GitHubpytorchMIT report
jiequancui/Parametric-Contrastive-Learning officialmentioned in papermentioned on GitHubpytorch report
dvlab-research/imbalanced-learning mentioned on GitHubpytorch report
dvlab-research/rescom mentioned on GitHubpytorch report
silicx/dlsa mentioned 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; 1 ran; 0 honoured the contract we drafted; 2 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.

1ran
2unverified

Licence: 1 of the 3 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 3 repositories linked to this paper, official or community; each sample names its own and says which. “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.

PaCoLoss jiequancui/Parametric-Contrastive-Learning/GPaCo/LT/losses.py official repository ran MIT (permissive) · 0e220d6ffd020ea0 · report
GmmContrastLoss silicx/dlsa/models/losses.py community (archive-listed) unverified Apache-2.0 (permissive) · 3eaa045101420da2 · report
SiamBS_SPM dvlab-research/rescom/ResCom/losses.py community (archive-listed) unverified no licence file found · pointer only · 67c48f79aac74f2d · report

Tasks

Contrastive LearningImage ClassificationLong-tail Learning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Classification ImageNet ResNet-200 Top 1 Accuracy 81.8% #605 of 1060 Archive leaderboard report
Image Classification ImageNet ResNet-152 Top 1 Accuracy 81.3% #649 of 1060 Archive leaderboard report
Image Classification ImageNet ResNet-101 Top 1 Accuracy 80.9% #673 of 1060 Archive leaderboard report
Image Classification iNaturalist 2018 PaCo(ResNet-152) Top-1 Accuracy 75.2% #28 of 60 Archive leaderboard report
Long-tail Learning CIFAR-10-LT (ρ=10) PCL Error Rate 9.14 #14 of 50 Archive leaderboard report
Long-tail Learning CIFAR-100-LT (ρ=100) PCL Error Rate 49.10 #26 of 66 Archive leaderboard report
Long-tail Learning ImageNet-LT PaCo(ResNeXt101-32x4d) Top-1 Accuracy 60.0 #15 of 69 Archive leaderboard report
Long-tail Learning ImageNet-LT PaCo(ResNeXt-50) Top-1 Accuracy 58.2 #22 of 69 Archive leaderboard report
Long-tail Learning Places-LT PaCo Top-1 Accuracy 41.2 #16 of 29 Archive leaderboard report
Long-tail Learning iNaturalist 2018 PaCo(ResNet-152) Top-1 Accuracy 75.2% #14 of 43 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

1x1 ConvolutionAverage PoolingBatch NormalizationBottleneck Residual BlockContrastive LearningConvolutionGlobal Average PoolingKaiming InitializationMax PoolingReLUResidual BlockResidual ConnectionSupervised Contrastive Loss

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