Papers › Distribution-Aware Robust Learning from Long-Tailed Data with Noisy Labels

Distribution-Aware Robust Learning from Long-Tailed Data with Noisy Labels

23 Jul 2024arXiv:2407.16802archive 2025-07-28

Jae Soon Baik, In Young Yoon, Kun Hoon Kim, Jun Won Choi

Deep neural networks have demonstrated remarkable advancements in various fields using large, well-annotated datasets. However, real-world data often exhibit long-tailed distributions and label noise, significantly degrading generalization performance. Recent studies addressing these issues have focused on noisy sample selection methods that estimate the centroid of each class based on high-confidence samples within each target class. The performance of these methods is limited because they use only the training samples within each class for class centroid estimation, making the quality of centroids susceptible to long-tailed distributions and noisy labels. In this study, we present a robust training framework called Distribution-aware Sample Selection and Contrastive Learning (DaSC). Specifically, DaSC introduces a Distribution-aware Class Centroid Estimation (DaCC) to generate enhanced class centroids. DaCC performs weighted averaging of the features from all samples, with weights determined based on model predictions. Additionally, we propose a confidence-aware contrastive learning strategy to obtain balanced and robust representations. The training samples are categorized into high-confidence and low-confidence samples. Our method then applies Semi-supervised Balanced Contrastive Loss (SBCL) using high-confidence samples, leveraging reliable label information to mitigate class bias. For the low-confidence samples, our method computes Mixup-enhanced Instance Discrimination Loss (MIDL) to improve their representations in a self-supervised manner. Our experimental results on CIFAR and real-world noisy-label datasets demonstrate the superior performance of the proposed DaSC compared to previous approaches.

PaperPDFCodeCode Syntology ran

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

Syntology 17 code samples harvested from 1 repository linked to this paper: 14 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 2 honoured, 0 violated, 6 with no contract checked; 6 where Syntology's instrument failed) · 3 unverified. Where Syntology's instrument failed: 6 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 17 samples from 1 repository, 14 ran (8 with no instrument failure; 6 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.

Levels written between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

jaesoonbaik1213/dasc officialmentioned in paperpytorchMITSyntology: 17 samples, 14 ran (6 instrument-failed) · 3 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.

Code Syntology ran Syntology

17 samples harvested: 14 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 2 honoured, 0 violated, 6 with no contract checked; 6 where Syntology's instrument failed) · 3 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 · honoured contract
6ran · our draft was wrong
6ran
3unverified

Licence: 1 of the 17 samples is pointer only, meaning Syntology does not serve that copy's text. For that sample, 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 jaesoonbaik1213/dasc. “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”. “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.

jaesoonbaik1213/dasc official repository 17 samples, 14 ran (6 instrument-failed) · 3 unverified
Preact_ResNet18 models/PreResNet.py ran · our draft was wrong MIT (permissive) · edb2f37e016d955a · report fixture: signature num_classes:int/0/int, args:Args/0/? · returned ResNet · level recorded 2026-09-24
ResNet18 in 174 papers models/PreResNet.py ran · our draft was wrong MIT (permissive) · 621298c338df1815 · report fixture: signature num_classes:int/0/int, args:ArgsStandIn/0/? · returned ResNet · level recorded 2026-09-24
conv3x3 in 1,376 papers models/PreResNet.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · 583f9780bdd00a45 · report fixture: signature in_planes:int/0/int, out_planes:int/0/int, stride:int/0/int · returned Conv2d · level recorded 2026-09-22
get_imbalance_ratios datas/dataloader_red_mini_imagenet.py ran · honoured contract MIT (permissive) · d6b493f24b80f8d3 · report fixture: signature imb_factor:float/0/float, cls_num:int/0/int · returned list · level recorded 2026-09-24
get_imbalance_ratios_1 datas/data_utils_N.py ran · honoured contract MIT (permissive) · 23afa08e1cbdacce · report fixture: signature imb_factor:float/0/float, cls_num:int/0/int · returned list · level recorded 2026-09-24
get_img_num_per_cls datas/dataloader_red_mini_imagenet.py ran MIT (permissive) · b419771b07d6b313 · report fixture: signature img_num:int/0/int, cls_num:int/0/int, imb_factor:float/0/float, num_meta:NoneType/0/? · returned list · level recorded 2026-09-24
sample_dataset in 20 papers datas/dataloader_red_mini_imagenet.py ran MIT (permissive) · 04303b0f4abc9b27 · report fixture: signature train_data:list/1/int, train_label:list/1/int, img_num_list:list/1/int, num_classes:int/0/int, kind:str/0/str · returned list · level recorded 2026-09-24
sample_dataset_1 datas/data_utils.py ran MIT (permissive) · a399ccf88d7166c6 · report fixture: signature train_data:ndarray/2/float, train_label:ndarray/1/int, noise_label:ndarray/1/int, img_num_list:list/1/int, num_classes:int/0/int, kind:str/0/str · returned tuple · level recorded 2026-09-24
sample_dataset_1 datas/data_utils_N.py ran MIT (permissive) · 082b83cd93beed20 · report fixture: signature train_data:ndarray/2/float, train_label:ndarray/1/int, img_num_list:ndarray/1/int, num_classes:int/0/int, kind:str/0/str, human_label:NoneType/0/? · returned tuple · level recorded 2026-09-24
set_device in 16 papers settings/configs.py ran · our draft was wrong MIT (permissive) · 1edaa58918fd8481 · report fixture: signature args:Args/0/? · returned device · level recorded 2026-09-24
set_tensor utils/util.py ran MIT (permissive) · 56df0904ca7bc6a3 · report fixture: signature tensor_var:Tensor/2/float, boolen:bool/0/bool, device:str/0/str · returned Tensor · level recorded 2026-09-24
to_var in 51 papers
census: 12 implementations from 21 papers, 1 distinct output on one shared input
models/resnet.py ran fingerprinted MIT (permissive) · 0d26b5abf61353f9 · report fixture: signature x:Tensor/2/float, requires_grad:bool/0/bool · returned Tensor · level recorded 2026-09-24
unpickle in 45 papers datas/data_utils.py ran · our draft was wrong MIT (permissive) · 5543609031c0e900 · report fixture: signature file:str/0/str · returned dict · level recorded 2026-09-24
unpickle in 45 papers datas/data_utils_N.py ran · our draft was wrong MIT (permissive) · ef49e82a7403eee1 · report fixture: signature file:str/0/str · returned dict · level recorded 2026-09-24
balanced_softmax_loss in 9 papers experiment/train_cifar_ssl.py unverified MIT (permissive) · fd714bbda15c3c95 · report
balanced_softmax_loss_semi experiment/train_cifar_ssl.py unverified MIT (permissive) · 15a4b28e19a85a2a · report

Tasks

Contrastive Learning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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