Papers › The Majority Can Help The Minority: Context-rich Minority Oversampling for Long-tailed...

The Majority Can Help The Minority: Context-rich Minority Oversampling for Long-tailed Classification

1 Dec 2021CVPR 2022 1arXiv:2112.00412archive 2025-07-28

Seulki Park, Youngkyu Hong, Byeongho Heo, Sangdoo Yun, Jin Young Choi

The problem of class imbalanced data is that the generalization performance of the classifier deteriorates due to the lack of data from minority classes. In this paper, we propose a novel minority over-sampling method to augment diversified minority samples by leveraging the rich context of the majority classes as background images. To diversify the minority samples, our key idea is to paste an image from a minority class onto rich-context images from a majority class, using them as background images. Our method is simple and can be easily combined with the existing long-tailed recognition methods. We empirically prove the effectiveness of the proposed oversampling method through extensive experiments and ablation studies. Without any architectural changes or complex algorithms, our method achieves state-of-the-art performance on various long-tailed classification benchmarks. Our code is made available at https://github.com/naver-ai/cmo.

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="2112.00412")

Code

Syntology Ran 3 of 5 code samples harvested from 1 repository linked to this paper; 2 have no recorded run. Of those that ran: 3 ran · our draft was wrong.

By repository: official repository: 3 samples from 1 repository, 1 ran; 2 identical to code first harvested elsewhere. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

naver-ai/cmo 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

5 samples harvested; 3 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.

3ran · our draft was wrong
2unverified

Licence: 2 of the 5 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 naver-ai/cmo. Some samples are identical code Syntology first harvested from another repository; for those, this paper's copy is not located and its licence is not recorded. “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.

rand_bbox_withcenter naver-ai/cmo/imagenet_train.py official repository ran · our draft was wrong fingerprinted MIT (permissive) · c2961e85b58555de · report
rand_bbox naver-ai/cmo/cifar_train.py official repository unverified MIT (permissive) · dc38cf45af8c7880 · report
rand_bbox_withcenter naver-ai/cmo/cifar_train.py official repository unverified MIT (permissive) · 32afcb4e4479037f · report
hms_string identical code first harvested elsewhere ran · our draft was wrong fingerprinted licence of this copy not recorded · a0e3d9c713be829a · report
rand_bbox identical code first harvested elsewhere ran · our draft was wrong fingerprinted licence of this copy not recorded · 0756a99508caf42c · report

Tasks

Image ClassificationLong-tail Learning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Classification iNaturalist 2018 BS-CMO (ResNet-50) Top-1 Accuracy 74.0% #30 of 60 Archive leaderboard report
Long-tail Learning CIFAR-100-LT (ρ=100) RIDE 3 experts + CMO Error Rate 50 #28 of 66 Archive leaderboard report
Long-tail Learning CIFAR-100-LT (ρ=100) LDAM-DRW + CMO Error Rate 52.8 #38 of 66 Archive leaderboard report
Long-tail Learning CIFAR-100-LT (ρ=100) Balanced Softmax + CMO Error Rate 53.4 #40 of 66 Archive leaderboard report
Long-tail Learning CIFAR-100-LT (ρ=100) CE-DRW Error Rate 58.9 #62 of 66 Archive leaderboard report
Long-tail Learning ImageNet-LT BS-CMO (ResNet-50) Top-1 Accuracy 58.0 #23 of 69 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