Papers › Using Self-Supervised Learning Can Improve Model Robustness and Uncertainty

Using Self-Supervised Learning Can Improve Model Robustness and Uncertainty

28 Jun 2019NeurIPS 2019 12arXiv:1906.12340archive 2025-07-28

Dan Hendrycks, Mantas Mazeika, Saurav Kadavath, Dawn Song

Self-supervision provides effective representations for downstream tasks without requiring labels. However, existing approaches lag behind fully supervised training and are often not thought beneficial beyond obviating or reducing the need for annotations. We find that self-supervision can benefit robustness in a variety of ways, including robustness to adversarial examples, label corruption, and common input corruptions. Additionally, self-supervision greatly benefits out-of-distribution detection on difficult, near-distribution outliers, so much so that it exceeds the performance of fully supervised methods. These results demonstrate the promise of self-supervision for improving robustness and uncertainty estimation and establish these tasks as new axes of evaluation for future self-supervised learning research.

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="1906.12340")

Code

Syntology Ran 5 of 12 code samples harvested from 1 repository linked to this paper; 7 have no recorded run. Of those that ran: 5 ran · our draft was wrong.

By repository: official repository: 12 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.

hendrycks/ss-ood officialmentioned in papermentioned on GitHubpytorchMIT report
drumpt/RotNet-OOD mentioned on GitHubpytorch report
feedbackward/addro mentioned on GitHubpytorch report
sooonwoo/RotNet-OOD mentioned 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

12 samples harvested; 5 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.

5ran · our draft was wrong
7unverified

Licence: 0 of the 12 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 hendrycks/ss-ood. “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.

conv1x1 hendrycks/ss-ood/models/resnet.py official repository ran · our draft was wrong MIT (permissive) · d9def42110729a85 · report
conv3x3 hendrycks/ss-ood/models/resnet.py official repository ran · our draft was wrong MIT (permissive) · fac5364e2f53c6db · report
normalize_l2 hendrycks/ss-ood/adversarial/attacks.py official repository ran · our draft was wrong fingerprinted MIT (permissive) · b16e920816efe253 · report
tensor_clamp hendrycks/ss-ood/adversarial/attacks.py official repository ran · our draft was wrong fingerprinted MIT (permissive) · 5b640b32a444ae38 · report
tensor_clamp_l2 hendrycks/ss-ood/adversarial/attacks.py official repository ran · our draft was wrong fingerprinted MIT (permissive) · 63b4423b18c974ad · report
make_layers hendrycks/ss-ood/multiclass_ood/models/allconv.py official repository unverified MIT (permissive) · 72410f1136cc7250 · report
normalize hendrycks/ss-ood/multiclass_ood/opencv_functional.py official repository unverified MIT (permissive) · 0c4ba7caa2964ea7 · report
possible_downsample hendrycks/ss-ood/models/revnet.py official repository unverified MIT (permissive) · ff93f9f79d2b719f · report
resize hendrycks/ss-ood/multiclass_ood/opencv_functional.py official repository unverified MIT (permissive) · 6f725a3000220ae9 · report
resnet18 hendrycks/ss-ood/models/resnet.py official repository unverified MIT (permissive) · 5b03b7018885e7bf · report
size_after_residual hendrycks/ss-ood/models/revnet.py official repository unverified MIT (permissive) · db245d85a98ab1e9 · report
to_tensor hendrycks/ss-ood/multiclass_ood/opencv_functional.py official repository unverified MIT (permissive) · b46a3fe2c2098a3e · report

Tasks

Anomaly DetectionOut-of-Distribution DetectionOutlier DetectionSelf-Supervised LearningUnsupervised Anomaly Detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Anomaly Detection Anomaly Detection on Anomaly Detection on Unlabeled ImageNet-30 vs Flowers-102 ROT+Trans Network ResNet-18 #5 of 5 Archive leaderboard report
Anomaly Detection Anomaly Detection on Anomaly Detection on Unlabeled ImageNet-30 vs Flowers-102 ROT+Trans ROC-AUC 86.3 #5 of 5 Archive leaderboard report
Anomaly Detection Anomaly Detection on Unlabeled ImageNet-30 vs CUB-200 ROT+Trans Network ResNet-18 #4 of 5 Archive leaderboard report
Anomaly Detection Anomaly Detection on Unlabeled ImageNet-30 vs CUB-200 ROT+Trans ROC-AUC 74.5 #4 of 5 Archive leaderboard report
Anomaly Detection One-class CIFAR-10 SSOOD AUROC 90.1 #19 of 36 Archive leaderboard report
Anomaly Detection One-class ImageNet-30 RotNet + Translation + Self-Attention + Resize AUROC 85.7 #6 of 11 Archive leaderboard report
Anomaly Detection One-class ImageNet-30 RotNet + Translation + Self-Attention AUROC 84.8 #7 of 11 Archive leaderboard report
Anomaly Detection One-class ImageNet-30 RotNet + Self-Attention AUROC 81.6 #8 of 11 Archive leaderboard report
Anomaly Detection One-class ImageNet-30 RotNet + Translation AUROC 77.9 #9 of 11 Archive leaderboard report
Anomaly Detection One-class ImageNet-30 RotNet AUROC 65.3 #10 of 11 Archive leaderboard report
Anomaly Detection One-class ImageNet-30 Supervised (OE) AUROC 56.1 #11 of 11 Archive leaderboard report
Out-of-Distribution Detection CIFAR-10 WRN 40-2 + Rotation Prediction AUROC 96.2 #10 of 10 Archive leaderboard report
Out-of-Distribution Detection CIFAR-10 WRN 40-2 + Rotation Prediction FPR95 16.0 #10 of 10 Archive leaderboard report
Out-of-Distribution Detection CIFAR-10 vs CIFAR-100 WRN 40-2 + Rotation Prediction AUPR 67.7 #12 of 14 Archive leaderboard report
Out-of-Distribution Detection CIFAR-10 vs CIFAR-100 WRN 40-2 + Rotation Prediction AUROC 90.9 #12 of 14 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

1x1 ConvolutionAverage PoolingBatch NormalizationBottleneck Residual BlockConvolutionGlobal Average PoolingKaiming InitializationMax PoolingReLUResidual BlockResidual Connection

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