Papers › MDCS: More Diverse Experts with Consistency Self-distillation for Long-tailed Recognition

MDCS: More Diverse Experts with Consistency Self-distillation for Long-tailed Recognition

19 Aug 2023ICCV 2023 1arXiv:2308.09922archive 2025-07-28

QiHao Zhao, Chen Jiang, Wei Hu, Fan Zhang, Jun Liu

Recently, multi-expert methods have led to significant improvements in long-tail recognition (LTR). We summarize two aspects that need further enhancement to contribute to LTR boosting: (1) More diverse experts; (2) Lower model variance. However, the previous methods didn't handle them well. To this end, we propose More Diverse experts with Consistency Self-distillation (MDCS) to bridge the gap left by earlier methods. Our MDCS approach consists of two core components: Diversity Loss (DL) and Consistency Self-distillation (CS). In detail, DL promotes diversity among experts by controlling their focus on different categories. To reduce the model variance, we employ KL divergence to distill the richer knowledge of weakly augmented instances for the experts' self-distillation. In particular, we design Confident Instance Sampling (CIS) to select the correctly classified instances for CS to avoid biased/noisy knowledge. In the analysis and ablation study, we demonstrate that our method compared with previous work can effectively increase the diversity of experts, significantly reduce the variance of the model, and improve recognition accuracy. Moreover, the roles of our DL and CS are mutually reinforcing and coupled: the diversity of experts benefits from the CS, and the CS cannot achieve remarkable results without the DL. Experiments show our MDCS outperforms the state-of-the-art by 1% ∼ 2% on five popular long-tailed benchmarks, including CIFAR10-LT, CIFAR100-LT, ImageNet-LT, Places-LT, and iNaturalist 2018. The code is available at https://github.com/fistyee/MDCS.

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="2308.09922")

Code

Syntology Ran 7 of 8 code samples harvested from 1 repository linked to this paper; 1 has no recorded run. Of those that ran: 1 ran · our draft was wrong; 6 ran with no contract checked.

By repository: official repository: 8 samples from 1 repository, 7 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

fistyee/mdcs 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

8 samples harvested; 7 ran; 0 honoured the contract we drafted; 1 has 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
6ran
1unverified

Licence: 8 of the 8 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 fistyee/MDCS. “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.

MDCSLoss fistyee/MDCS/model/loss.py official repository ran no licence file found · pointer only · dc8b3c5ea5f84173 · report
accuracy fistyee/mdcs/model/metric.py official repository ran no licence file found · pointer only · 1c1fdcd838303a0d · report
cat_mask fistyee/mdcs/model/loss.py official repository ran fingerprinted no licence file found · pointer only · 09b93518f9edc2dc · report
dkd_loss fistyee/mdcs/model/loss.py official repository ran no licence file found · pointer only · 5f5ee5e8c168b306 · report
focal_loss fistyee/mdcs/model/loss.py official repository ran · our draft was wrong fingerprinted no licence file found · pointer only · 4dcf06ba28983266 · report
learing_rate_scheduler fistyee/mdcs/train_places.py official repository ran no licence file found · pointer only · 23198d10b9f73030 · report
top_k_acc fistyee/mdcs/model/metric.py official repository ran no licence file found · pointer only · c642158604bebe8a · report
init_weights fistyee/mdcs/model/model.py official repository unverified no licence file found · pointer only · 0933d643f92c12aa · report

Tasks

DiversityLong-tail Learning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Long-tail Learning CIFAR-10-LT (ρ=50) MDCS Error Rate 11.7 #5 of 8 Archive leaderboard report
Long-tail Learning CIFAR-100-LT (ρ=100) MDCS Error Rate 43.9 #10 of 66 Archive leaderboard report
Long-tail Learning CIFAR-100-LT (ρ=50) MDCS Error Rate 39.9 #9 of 25 Archive leaderboard report
Long-tail Learning ImageNet-LT MDCS (ResNeXt-50) Top-1 Accuracy 61.8 #12 of 69 Archive leaderboard report
Long-tail Learning iNaturalist 2018 MDCS(Resnet50) Top-1 Accuracy 75.6% #11 of 43 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

Focus

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