Papers › Global and Local Mixture Consistency Cumulative Learning for Long-tailed Visual Recognitions

Global and Local Mixture Consistency Cumulative Learning for Long-tailed Visual Recognitions

15 May 2023CVPR 2023 1arXiv:2305.08661archive 2025-07-28

Fei Du, Peng Yang, Qi Jia, Fengtao Nan, Xiaoting Chen, Yun Yang

In this paper, our goal is to design a simple learning paradigm for long-tail visual recognition, which not only improves the robustness of the feature extractor but also alleviates the bias of the classifier towards head classes while reducing the training skills and overhead. We propose an efficient one-stage training strategy for long-tailed visual recognition called Global and Local Mixture Consistency cumulative learning (GLMC). Our core ideas are twofold: (1) a global and local mixture consistency loss improves the robustness of the feature extractor. Specifically, we generate two augmented batches by the global MixUp and local CutMix from the same batch data, respectively, and then use cosine similarity to minimize the difference. (2) A cumulative head tail soft label reweighted loss mitigates the head class bias problem. We use empirical class frequencies to reweight the mixed label of the head-tail class for long-tailed data and then balance the conventional loss and the rebalanced loss with a coefficient accumulated by epochs. Our approach achieves state-of-the-art accuracy on CIFAR10-LT, CIFAR100-LT, and ImageNet-LT datasets. Additional experiments on balanced ImageNet and CIFAR demonstrate that GLMC can significantly improve the generalization of backbones. Code is made publicly available at https://github.com/ynu-yangpeng/GLMC.

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="2305.08661")

Code

Syntology Ran 7 of 10 code samples harvested from 2 repositories linked to this paper; 3 have no recorded run. Of those that ran: 4 ran · fixture could not drive it; 3 ran with no contract checked.

By repository: official repository: 4 samples from 1 repository, 2 ran; community (archive-listed): 5 samples from 1 repository, 4 ran; 1 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.

ynu-yangpeng/GLMC officialmentioned in papermentioned on GitHubpytorch report
val-iisc/saddle-longtail mentioned 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

10 samples harvested; 7 ran; 0 honoured the contract we drafted; 3 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.

4ran · fixture could not drive it
3ran
3unverified

Licence: 5 of the 10 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 2 repositories linked to this paper, official or community; each sample names its own and says which. 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.

GLMC_mixed ynu-yangpeng/GLMC/GLMC-2023/Trainer.py official repository ran · fixture could not drive it fingerprinted no licence file found · pointer only · 103036c86a31c52b · report
rand_bbox ynu-yangpeng/GLMC/GLMC-2023/Trainer.py official repository ran · fixture could not drive it fingerprinted no licence file found · pointer only · 94a1b38875494387 · report
Trainer ynu-yangpeng/GLMC/GLMC-2023/Trainer.py official repository unverified no licence file found · pointer only · 8f5d8a765e776472 · report
save_checkpoint ynu-yangpeng/GLMC/GLMC-2023/Trainer.py official repository unverified no licence file found · pointer only · c5a1cf535d31085e · report
AverageMeter val-iisc/saddle-longtail/GLMC-2023/Trainer.py community (archive-listed) ran MIT (permissive) · 8c2fbaf0a3677a09 · report
SAM val-iisc/saddle-longtail/GLMC-2023/Trainer.py community (archive-listed) ran MIT (permissive) · 5f0b6886fbdb403e · report
Trainer val-iisc/saddle-longtail/GLMC-2023/Trainer.py community (archive-listed) ran MIT (permissive) · 55445e6fa2989a18 · report
accuracy val-iisc/saddle-longtail/GLMC-2023/Trainer.py community (archive-listed) ran · fixture could not drive it MIT (permissive) · 1e369e39c90cada6 · report
save_checkpoint val-iisc/saddle-longtail/GLMC-2023/Trainer.py community (archive-listed) unverified MIT (permissive) · 909b8d6eeb4f3bb4 · report
accuracy identical code first harvested elsewhere ran · fixture could not drive it licence of this copy not recorded · fd638ce21929b00d · report

Tasks

Long-tail Learning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Long-tail Learning CIFAR-10-LT (ρ=10) GLMC+MaxNorm (ResNet-34, channel x4) Error Rate 5 #1 of 50 Archive leaderboard report
Long-tail Learning CIFAR-10-LT (ρ=10) GLMC (ResNet-34, channel x4) Error Rate 5.15 #3 of 50 Archive leaderboard report
Long-tail Learning CIFAR-10-LT (ρ=100) GLMC+MaxNorm (ResNet-34, channel x4) Error Rate 10.42 #1 of 28 Archive leaderboard report
Long-tail Learning CIFAR-10-LT (ρ=100) GLMC (ResNet-34, channel x4) Error Rate 11.50 #4 of 28 Archive leaderboard report
Long-tail Learning CIFAR-100-LT (ρ=10) GLMC+MaxNorm (ResNet-32, channel x4) Error Rate 25.72 #5 of 31 Archive leaderboard report
Long-tail Learning CIFAR-100-LT (ρ=10) GLMC (ResNet-34, channel x4) Error Rate 26.53 #6 of 31 Archive leaderboard report
Long-tail Learning CIFAR-100-LT (ρ=100) GLMC+MaxNorm (ResNet-34, channel x4) Error Rate 41.59 #7 of 66 Archive leaderboard report
Long-tail Learning CIFAR-100-LT (ρ=100) GLMC (ResNet-34, channel x4) Error Rate 42.01 #8 of 66 Archive leaderboard report
Long-tail Learning CIFAR-100-LT (ρ=50) GLMC (ResNet-34, channel x4) Error Rate 36.15 #6 of 25 Archive leaderboard report
Long-tail Learning ImageNet-LT GLMC (ResNeXt-50) Top-1 Accuracy 56.3 #34 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.

Methods

CutMixMixup

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