Papers › Using Self-Supervised Learning Can Improve Model Robustness and Uncertainty
Using Self-Supervised Learning Can Improve Model Robustness and Uncertainty
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.
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.
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.
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.
d9def42110729a85 · report
fac5364e2f53c6db · report
b16e920816efe253 · report
5b640b32a444ae38 · report
63b4423b18c974ad · report
72410f1136cc7250 · report
0c4ba7caa2964ea7 · report
ff93f9f79d2b719f · report
6f725a3000220ae9 · report
5b03b7018885e7bf · report
db245d85a98ab1e9 · report
b46a3fe2c2098a3e · report
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| 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
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