Papers › Learning Imbalanced Datasets with Label-Distribution-Aware Margin Loss

Learning Imbalanced Datasets with Label-Distribution-Aware Margin Loss

18 Jun 2019NeurIPS 2019 12arXiv:1906.07413archive 2025-07-28

Kaidi Cao, Colin Wei, Adrien Gaidon, Nikos Arechiga, Tengyu Ma

Deep learning algorithms can fare poorly when the training dataset suffers from heavy class-imbalance but the testing criterion requires good generalization on less frequent classes. We design two novel methods to improve performance in such scenarios. First, we propose a theoretically-principled label-distribution-aware margin (LDAM) loss motivated by minimizing a margin-based generalization bound. This loss replaces the standard cross-entropy objective during training and can be applied with prior strategies for training with class-imbalance such as re-weighting or re-sampling. Second, we propose a simple, yet effective, training schedule that defers re-weighting until after the initial stage, allowing the model to learn an initial representation while avoiding some of the complications associated with re-weighting or re-sampling. We test our methods on several benchmark vision tasks including the real-world imbalanced dataset iNaturalist 2018. Our experiments show that either of these methods alone can already improve over existing techniques and their combination achieves even better performance gains.

PaperPDFConference PDFCodeCode Syntology ranMethod as code

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

No sample from the archive's official repository (kaidic/LDAM-DRW) is linked to this paper; the 11 samples below come from 4 community repositories. Syntology harvested code from kaidic/LDAM-DRW for another paper.

kaidic/LDAM-DRW: Syntology's graph links these samples to Decoupled Training for Long-Tailed Classification With Stochastic Representations (arXiv:2304.09426; that paper's own run record: 10 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 4 where Syntology's instrument failed) · 4 unverified); nothing checks that they implement this paper's method.

Syntology 11 code samples harvested from 4 repositories linked to this paper: 6 ran (of which 1 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified. Where Syntology's instrument failed: 2 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 11 samples from 4 repositories, 6 ran (4 with no instrument failure; 2 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

No sample is linked to this paper from 2 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 1 of the 6 samples that ran has no recorded date.

kaidic/LDAM-DRW officialmentioned in papermentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Decoupled Training for Long-Tailed Classification With Stochastic Representations (arXiv:2304.09426; that paper's own run record: 10 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 4 where Syntology's instrument failed) · 4 unverified); nothing checks that they implement this paper's method. report
feidfoe/AdjustBnd4Imbalance mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Adjusting Decision Boundary for Class Imbalanced Learning (arXiv:1912.01857; that paper's own run record: 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
ihaeyong/maximum-margin-ldam mentioned on GitHubpytorchMITSyntology: 8 samples, 5 ran (2 instrument-failed) · 3 unverified report
j3soon/arxiv-utils mentioned on GitHubMITSyntology: not harvested report
jackhck/subclass-balancing-contrastive-learning mentioned on GitHubpytorchSyntology: 1 sample, 0 ran · 1 unverified report
karurb92/ldam_str_bn mentioned on GitHubtfSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
orparask/VS-Loss mentioned on GitHubpytorchSyntology: 1 sample, 0 ran · 1 unverified 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

11 samples harvested: 6 ran (of which 1 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

2ran · our draft was wrong
4ran
5unverified

Licence: 5 of the 11 samples are pointer only, meaning Syntology does not serve that copy's text. For 2 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 4 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “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. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. For 1 sample that ran, the graph records a signature this page does not show: for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (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 are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. 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 six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. 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.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

ihaeyong/maximum-margin-ldam community (archive-listed) 8 samples, 5 ran (2 instrument-failed) · 3 unverified
focal_loss in 65 papers
census: 6 implementations from 13 papers, 4 distinct outputs across 3 buckets, one shared input per bucket this sample: bucket 2 of 3, arg 1: rank 2, kind float, dtype float32
losses.py ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only · 4dcf06ba28983266 · report fixture: signature input_values:Tensor/2/float, gamma:float/0/float · returned Tensor · level recorded, date not recorded
obj_margins cifar_train.py ran MIT (permissive) · 26d27ecdc945d123 · report fixture: signature rm_obj_dists:Tensor/2/float, labels:Tensor/1/int, index_float:Tensor/2/float, max_m:Tensor/0/float, gamma:float/0/float · returned Tensor · level recorded 2026-09-24
plot_confusion_matrix in 11 papers utils.py ran MIT (permissive) · e5ce72a1e8d9bc22 · report fixture: signature y_true:ndarray/1/int, y_pred:ndarray/1/int, classes:ndarray/1/<U7, normalize:bool/0/bool, title:str/0/str, cmap:callable/0/? · returned Axes · level recorded 2026-09-25
resnet32 in 47 papers models/resnet_cifar.py ran · our draft was wrong MIT (permissive) · 11d038f53d77a8d2 · report fixture: signature num_classes:int/0/int, use_norm:bool/0/bool · returned ResNet_s · level recorded 2026-09-25
to_onehot in 9 papers utils.py ran fingerprinted MIT (permissive) · 83b8128b16e83cfc · report fixture: signature vec:Tensor/1/int, num_classes:int/0/int, fill:int/0/int · returned Tensor · level recorded 2026-09-24
accuracy in 872 papers
census: 8 implementations from 7 papers, 7 distinct outputs across 6 buckets, one shared input per bucket
utils.py unverified MIT (permissive) here; the stored copy is pointer only · 688c38ac8517471a · report
ldam_loss cifar_train.py unverified MIT (permissive) · 6feb1ddb1872cd29 · report
weight in 6 papers cifar_train.py unverified MIT (permissive) · 75d3d8bc39a6d61b · report
jackhck/subclass-balancing-contrastive-learning community (archive-listed) 1 sample, 0 ran · 1 unverified
LDAMLoss SimCLR/loss.py unverified no licence file found · pointer only · a3ce423c36d71133 · report
karurb92/ldam_str_bn community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
LDAMLoss losses.py ran no licence file found · pointer only · 62c8aa90e3fb2973 · report fixture: returned LDAMLoss · level recorded 2026-09-22
orparask/VS-Loss community (archive-listed) 1 sample, 0 ran · 1 unverified
LDAMLoss class_imbalance/losses.py unverified no licence file found · pointer only · 6683ac6a76084b68 · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it. Siblings are assemblies lifted from this paper in the same batch for the same method: alternative readings kept side by side; none replaces or supersedes another.

3 assemblies on this paper: 3 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).

3 sibling assemblies for Label-Distribution-Aware Margin (LDAM) loss (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.

harvested Assembly for Label-Distribution-Aware Margin (LDAM) loss (graph method: Label-Distribution-Aware Margin (LDAM) loss). 1 brick; individually on a fixture: 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 3 siblings

  1. LDAMLoss entry · level 1 · ran · 62c8aa90e3fb2973

harvested Assembly for Label-Distribution-Aware Margin (LDAM) loss (graph method: Label-Distribution-Aware Margin (LDAM) loss). 1 brick; individually on a fixture: 0 ran · 1 unverified. The assembly has not been run end-to-end.

one of 3 siblings

  1. LDAMLoss entry · level 0 · unverified · 6683ac6a76084b68

harvested Assembly for Label-Distribution-Aware Margin (LDAM) loss (graph method: Label-Distribution-Aware Margin (LDAM) loss). 1 brick; individually on a fixture: 0 ran · 1 unverified. The assembly has not been run end-to-end.

one of 3 siblings

  1. LDAMLoss entry · level 0 · unverified · a3ce423c36d71133

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="1906.07413") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Long-tail LearningLong-tail learning with class descriptors

Datasets

Introduced by this paper, per the archive.

CIFAR100-LT

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Long-tail Learning CIFAR-10-LT (ρ=10) LDAM-DRW Error Rate 11.84 #39 of 50 Archive leaderboard report
Long-tail Learning CIFAR-10-LT (ρ=10) Class-balanced Resampling Error Rate 13.21 #47 of 50 Archive leaderboard report
Long-tail Learning CIFAR-10-LT (ρ=10) Empirical Risk Minimization (ERM, CE) Error Rate 13.61 #49 of 50 Archive leaderboard report
Long-tail Learning CIFAR-10-LT (ρ=100) LDAM-DRW Error Rate 22.97 #27 of 28 Archive leaderboard report
Long-tail Learning CIFAR-100-LT (ρ=10) LDAM-DRW Error Rate 41.29 #30 of 31 Archive leaderboard report
Long-tail Learning CIFAR-100-LT (ρ=100) LDAM-DRW Error Rate 57.96 #61 of 66 Archive leaderboard report
Long-tail Learning COCO-MLT LDAM(ResNet-50) Average mAP 40.53 #13 of 13 Archive leaderboard report
Long-tail Learning VOC-MLT LDAM(ResNet-50) Average mAP 70.73 #12 of 13 Archive leaderboard report
Long-tail learning with class descriptors AWA-LT LDAM Long-Tailed Accuracy 93.5 #5 of 5 Archive leaderboard report
Long-tail learning with class descriptors AWA-LT LDAM Per-Class Accuracy 69.1 #5 of 5 Archive leaderboard report
Long-tail learning with class descriptors CUB-LT LDAM Long-Tailed Accuracy 64.1 #4 of 5 Archive leaderboard report
Long-tail learning with class descriptors CUB-LT LDAM Per-Class Accuracy 50.1 #4 of 5 Archive leaderboard report
Long-tail learning with class descriptors SUN-LT LDAM Long-Tailed Accuracy 36.4 #5 of 5 Archive leaderboard report
Long-tail learning with class descriptors SUN-LT LDAM Per-Class Accuracy 29.8 #5 of 5 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