Papers › Targeted Supervised Contrastive Learning for Long-Tailed Recognition

Targeted Supervised Contrastive Learning for Long-Tailed Recognition

27 Nov 2021CVPR 2022 1arXiv:2111.13998archive 2025-07-28

Tianhong Li, Peng Cao, Yuan Yuan, Lijie Fan, Yuzhe Yang, Rogerio Feris, Piotr Indyk, Dina Katabi

Real-world data often exhibits long tail distributions with heavy class imbalance, where the majority classes can dominate the training process and alter the decision boundaries of the minority classes. Recently, researchers have investigated the potential of supervised contrastive learning for long-tailed recognition, and demonstrated that it provides a strong performance gain. In this paper, we show that while supervised contrastive learning can help improve performance, past baselines suffer from poor uniformity brought in by imbalanced data distribution. This poor uniformity manifests in samples from the minority class having poor separability in the feature space. To address this problem, we propose targeted supervised contrastive learning (TSC), which improves the uniformity of the feature distribution on the hypersphere. TSC first generates a set of targets uniformly distributed on a hypersphere. It then makes the features of different classes converge to these distinct and uniformly distributed targets during training. This forces all classes, including minority classes, to maintain a uniform distribution in the feature space, improves class boundaries, and provides better generalization even in the presence of long-tail data. Experiments on multiple datasets show that TSC achieves state-of-the-art performance on long-tailed recognition tasks.

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="2111.13998")

Code

Syntology Ran 1 of 14 code samples harvested from 1 repository linked to this paper; 13 have no recorded run. Of those that ran: 1 ran · fixture could not drive it.

By repository: official repository: 14 samples from 1 repository, 1 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

lth14/targeted-supcon 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

14 samples harvested; 1 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.

1ran · fixture could not drive it
13unverified

Licence: 0 of the 14 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 lth14/targeted-supcon. “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 lth14/targeted-supcon/main_moco_supcon_imba.py official repository ran · fixture could not drive it MIT (permissive) · 131a82fd65128218 · report
adjust_learning_rate lth14/targeted-supcon/main_moco_supcon_imba.py official repository unverified MIT (permissive) · 75b34b1b9cfea207 · report
alexnet lth14/targeted-supcon/moco_models/alexnet.py official repository unverified MIT (permissive) · 69e2ce68b6db2411 · report
densenet121 lth14/targeted-supcon/moco_models/densenet.py official repository unverified MIT (permissive) · 9eb4b3b03ed7a1c9 · report
densenet161 lth14/targeted-supcon/moco_models/densenet.py official repository unverified MIT (permissive) · e945c7af558f65a9 · report
densenet169 lth14/targeted-supcon/moco_models/densenet.py official repository unverified MIT (permissive) · 858b62a0718acf3c · report
get_data_transform lth14/targeted-supcon/dataset/imagenet.py official repository unverified MIT (permissive) · a117231916d15cb9 · report
googlenet lth14/targeted-supcon/moco_models/googlenet.py official repository unverified MIT (permissive) · cc86d582f7c75a6d · report
init_weights lth14/targeted-supcon/imagenet_inat/utils.py official repository unverified MIT (permissive) · 4826cd3596c12660 · report
load_data_imagenet lth14/targeted-supcon/dataset/imagenet.py official repository unverified MIT (permissive) · 457c95f8c16efe85 · report
parse_option_stage1 lth14/targeted-supcon/cifar_dirty/main_supcon_imba.py official repository unverified MIT (permissive) · 215b209f49176d4e · report
shot_acc lth14/targeted-supcon/imagenet_inat/utils.py official repository unverified MIT (permissive) · 985b6559d5dbe2f7 · report
source_import lth14/targeted-supcon/imagenet_inat/utils.py official repository unverified MIT (permissive) · 07cca9631fe4f26a · report
validate lth14/targeted-supcon/main_lincls_imba.py official repository unverified MIT (permissive) · a7758cbaed64d10d · report

Tasks

Contrastive LearningLong-tail Learning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Long-tail Learning CIFAR-10-LT (ρ=10) TSC Error Rate 11.3 #33 of 50 Archive leaderboard report
Long-tail Learning CIFAR-10-LT (ρ=100) TSC(ResNet-32) Error Rate 21.3 #24 of 28 Archive leaderboard report
Long-tail Learning CIFAR-100-LT (ρ=100) TSC(ResNet-32) Error Rate 56.2 #54 of 66 Archive leaderboard report
Long-tail Learning ImageNet-LT TSC(ResNet-50) Top-1 Accuracy 52.4 #49 of 69 Archive leaderboard report
Long-tail Learning iNaturalist 2018 TSC(ResNet-50) Top-1 Accuracy 69.7% #36 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

Contrastive Learning

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