Papers › CDMAD: Class-Distribution-Mismatch-Aware Debiasing for Class-Imbalanced...

CDMAD: Class-Distribution-Mismatch-Aware Debiasing for Class-Imbalanced Semi-Supervised Learning

15 Mar 2024CVPR 2024 1arXiv:2403.10391archive 2025-07-28

Hyuck Lee, Heeyoung Kim

Pseudo-label-based semi-supervised learning (SSL) algorithms trained on a class-imbalanced set face two cascading challenges: 1) Classifiers tend to be biased towards majority classes, and 2) Biased pseudo-labels are used for training. It is difficult to appropriately re-balance the classifiers in SSL because the class distribution of an unlabeled set is often unknown and could be mismatched with that of a labeled set. We propose a novel class-imbalanced SSL algorithm called class-distribution-mismatch-aware debiasing (CDMAD). For each iteration of training, CDMAD first assesses the classifier's biased degree towards each class by calculating the logits on an image without any patterns (e.g., solid color image), which can be considered irrelevant to the training set. CDMAD then refines biased pseudo-labels of the base SSL algorithm by ensuring the classifier's neutrality. CDMAD uses these refined pseudo-labels during the training of the base SSL algorithm to improve the quality of the representations. In the test phase, CDMAD similarly refines biased class predictions on test samples. CDMAD can be seen as an extension of post-hoc logit adjustment to address a challenge of incorporating the unknown class distribution of the unlabeled set for re-balancing the biased classifier under class distribution mismatch. CDMAD ensures Fisher consistency for the balanced error. Extensive experiments verify the effectiveness of CDMAD.

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="2403.10391")

Code

Syntology Ran 9 of 16 code samples harvested from 1 repository linked to this paper; 7 have no recorded run. Of those that ran: 1 ran · our draft was wrong; 8 ran with no contract checked.

By repository: official repository: 16 samples from 1 repository, 9 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

leehyuck/cdmad officialmentioned in papermentioned 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

16 samples harvested; 9 ran; 0 honoured the contract we drafted; 7 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 · our draft was wrong
8ran
7unverified

Licence: 16 of the 16 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 LeeHyuck/CDMAD. “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.

conv3x3 LeeHyuck/CDMAD/wrn.py official repository ran no licence file found · pointer only · a4917ae1314a3442 · report
f LeeHyuck/CDMAD/fixmatchcdmad.py official repository ran fingerprinted no licence file found · pointer only · 73eab42215d7c5fb · report
plot_overlap LeeHyuck/CDMAD/utils/logger.py official repository ran · our draft was wrong no licence file found · pointer only · 50afa2863ffd9fde · report
train_split LeeHyuck/CDMAD/dataset/fix_cifar10.py official repository ran no licence file found · pointer only · 75456c3bc4c21f10 · report
train_split LeeHyuck/CDMAD/dataset/fix_cifar100.py official repository ran no licence file found · pointer only · f220314765575fce · report
train_split LeeHyuck/CDMAD/dataset/fix_stl10.py official repository ran no licence file found · pointer only · b727ff665308560a · report
train_split LeeHyuck/CDMAD/dataset/remix_cifar10.py official repository ran no licence file found · pointer only · 0a6c1b33bb53dedf · report
train_split LeeHyuck/CDMAD/dataset/remix_cifar100.py official repository ran no licence file found · pointer only · 3a133f8c08b2e7a2 · report
train_split LeeHyuck/CDMAD/dataset/remix_stl10.py official repository ran no licence file found · pointer only · afe297279f65a20d · report
get_cifar10 LeeHyuck/CDMAD/dataset/fix_cifar10.py official repository unverified no licence file found · pointer only · 3d7953151d774d75 · report
get_cifar10 LeeHyuck/CDMAD/dataset/remix_cifar10.py official repository unverified no licence file found · pointer only · 5a1d3cd7b6f8dc4e · report
get_cifar100 LeeHyuck/CDMAD/dataset/fix_cifar100.py official repository unverified no licence file found · pointer only · 4ec17853aa662728 · report
get_cifar100 LeeHyuck/CDMAD/dataset/remix_cifar100.py official repository unverified no licence file found · pointer only · cb7f7654d066d3f4 · report
get_mean_and_std LeeHyuck/CDMAD/utils/misc.py official repository unverified no licence file found · pointer only · 1d6e2edb8832d7b0 · report
get_stl10 LeeHyuck/CDMAD/dataset/fix_stl10.py official repository unverified no licence file found · pointer only · 67fdfee005e736b7 · report
get_stl10 LeeHyuck/CDMAD/dataset/remix_stl10.py official repository unverified no licence file found · pointer only · b42eff56fbe2c823 · report

Tasks

Pseudo Label

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

BASESET

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