Papers › SURE: SUrvey REcipes for building reliable and robust deep networks

SURE: SUrvey REcipes for building reliable and robust deep networks

1 Mar 2024CVPR 2024 1arXiv:2403.00543archive 2025-07-28

Yuting Li, Yingyi Chen, Xuanlong Yu, Dexiong Chen, Xi Shen

In this paper, we revisit techniques for uncertainty estimation within deep neural networks and consolidate a suite of techniques to enhance their reliability. Our investigation reveals that an integrated application of diverse techniques--spanning model regularization, classifier and optimization--substantially improves the accuracy of uncertainty predictions in image classification tasks. The synergistic effect of these techniques culminates in our novel SURE approach. We rigorously evaluate SURE against the benchmark of failure prediction, a critical testbed for uncertainty estimation efficacy. Our results showcase a consistently better performance than models that individually deploy each technique, across various datasets and model architectures. When applied to real-world challenges, such as data corruption, label noise, and long-tailed class distribution, SURE exhibits remarkable robustness, delivering results that are superior or on par with current state-of-the-art specialized methods. Particularly on Animal-10N and Food-101N for learning with noisy labels, SURE achieves state-of-the-art performance without any task-specific adjustments. This work not only sets a new benchmark for robust uncertainty estimation but also paves the way for its application in diverse, real-world scenarios where reliability is paramount. Our code is available at \url{https://yutingli0606.github.io/SURE/}.

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="2403.00543")

Code

Syntology Ran 5 of 6 code samples harvested from 1 repository linked to this paper; 1 has no recorded run. Of those that ran: 5 ran with no contract checked.

By repository: official repository: 6 samples from 1 repository, 5 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

YutingLi0606/SURE officialmentioned 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

6 samples harvested; 5 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.

5ran
1unverified

Licence: 6 of the 6 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 YutingLi0606/SURE. “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.

calc_aurc_eaurc YutingLi0606/SURE/utils/metrics.py official repository ran no licence file found · pointer only · 4a20e753857545ed · report
calc_ece YutingLi0606/SURE/utils/metrics.py official repository ran no licence file found · pointer only · 6328797fa973a062 · report
calc_fpr_aupr YutingLi0606/SURE/utils/metrics.py official repository ran no licence file found · pointer only · 8f790e315b526f80 · report
compute_confidence_scores YutingLi0606/SURE/train_finetune.py official repository ran no licence file found · pointer only · f71e6609d7f54a29 · report
make_layers YutingLi0606/SURE/model/vgg.py official repository ran no licence file found · pointer only · ac62432dc5134b0d · report
compute_loss YutingLi0606/SURE/train_finetune.py official repository unverified no licence file found · pointer only · d577c874c4871163 · report

Tasks

Image ClassificationLearning with noisy labelsLong-tail LearningSurveyimage-classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Classification Food-101N SURE(ResNet-50) Accuracy 88.0 #3 of 4 Archive leaderboard report
Learning with noisy labels ANIMAL SURE Accuracy 89.0 #2 of 19 Archive leaderboard report
Learning with noisy labels ANIMAL SURE ImageNet Pretrained NO #2 of 19 Archive leaderboard report
Learning with noisy labels ANIMAL SURE Network Vgg19-BN #2 of 19 Archive leaderboard report
Long-tail Learning CIFAR-10-LT (ρ=10) SURE(ResNet-32) Error Rate 5.04 #2 of 50 Archive leaderboard report
Long-tail Learning CIFAR-10-LT (ρ=100) SURE(ResNet-32) Error Rate 13.07 #6 of 28 Archive leaderboard report
Long-tail Learning CIFAR-10-LT (ρ=50) SURE(ResNet-32) Error Rate 9.78 #2 of 8 Archive leaderboard report
Long-tail Learning CIFAR-100-LT (ρ=10) SURE(ResNet-32) Error Rate 26.76 #7 of 31 Archive leaderboard report
Long-tail Learning CIFAR-100-LT (ρ=100) SURE(ResNet-32) Error Rate 43.66 #9 of 66 Archive leaderboard report
Long-tail Learning CIFAR-100-LT (ρ=50) SURE(ResNet-32) Error Rate 36.87 #7 of 25 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