Papers › SIO: Synthetic In-Distribution Data Benefits Out-of-Distribution Detection

SIO: Synthetic In-Distribution Data Benefits Out-of-Distribution Detection

25 Mar 2023arXiv:2303.14531archive 2025-07-28

Jingyang Zhang, Nathan Inkawhich, Randolph Linderman, Ryan Luley, Yiran Chen, Hai Li

Building up reliable Out-of-Distribution (OOD) detectors is challenging, often requiring the use of OOD data during training. In this work, we develop a data-driven approach which is distinct and complementary to existing works: Instead of using external OOD data, we fully exploit the internal in-distribution (ID) training set by utilizing generative models to produce additional synthetic ID images. The classifier is then trained using a novel objective that computes weighted loss on real and synthetic ID samples together. Our training framework, which is termed SIO, serves as a "plug-and-play" technique that is designed to be compatible with existing and future OOD detection algorithms, including the ones that leverage available OOD training data. Our experiments on CIFAR-10, CIFAR-100, and ImageNet variants demonstrate that SIO consistently improves the performance of nearly all state-of-the-art (SOTA) OOD detection algorithms. For instance, on the challenging CIFAR-10 v.s. CIFAR-100 detection problem, SIO improves the average OOD detection AUROC of 18 existing methods from 86.25\% to 89.04\% and achieves a new SOTA of 92.94\% according to the OpenOOD benchmark. Code is available at https://github.com/zjysteven/SIO.

PaperPDFCodeCode 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="2303.14531")

Code

Syntology Ran 6 of 15 code samples harvested from 1 repository linked to this paper; 9 have no recorded run. Of those that ran: 3 ran · violated contract; 3 ran · our draft was wrong.

By repository: official repository: 15 samples from 1 repository, 6 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

zjysteven/sio officialmentioned in papermentioned 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

15 samples harvested; 6 ran; 0 honoured the contract we drafted; 9 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.

3ran · violated contract
3ran · our draft was wrong
9unverified

Licence: 0 of the 15 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 zjysteven/sio. “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.

cosine_annealing zjysteven/sio/imagenet_train_subclasses.py official repository ran · violated contract fingerprinted MIT (permissive) · 05eda95f9800a1e9 · report
conv1x1 zjysteven/sio/openood/networks/bit.py official repository ran · our draft was wrong MIT (permissive) · ee80cf467065076b · report
conv3x3 zjysteven/sio/openood/networks/bit.py official repository ran · our draft was wrong MIT (permissive) · f01b8d3901f0b289 · report
rew_ce zjysteven/sio/openood/losses/reweight.py official repository ran · violated contract MIT (permissive) · d8339d591bbd7f52 · report
soft_cross_entropy zjysteven/sio/openood/losses/sce.py official repository ran · our draft was wrong MIT (permissive) · 61492b343324d2ea · report
tf2th zjysteven/sio/openood/networks/bit.py official repository ran · violated contract fingerprinted MIT (permissive) · 7023eb86801bb3a3 · report
Discriminator32 zjysteven/sio/openood/networks/arpl_net.py official repository unverified MIT (permissive) · 3cce4936256bdc33 · report
Generator zjysteven/sio/openood/networks/arpl_net.py official repository unverified MIT (permissive) · 797cd0913159403b · report
Generator32 zjysteven/sio/openood/networks/arpl_net.py official repository unverified MIT (permissive) · 893f424fd19a9b6c · report
create_window zjysteven/sio/openood/losses/ssim.py official repository unverified MIT (permissive) · 45b6edb2cf78cda2 · report
gaussian zjysteven/sio/openood/losses/ssim.py official repository unverified MIT (permissive) · e2424ce033ba3a0f · report
loss_function zjysteven/sio/openood/losses/rd4ad_loss.py official repository unverified MIT (permissive) · 4c1d0e3674921db5 · report
rew_sce zjysteven/sio/openood/losses/reweight.py official repository unverified MIT (permissive) · e1014da2309b3946 · report
ssim zjysteven/sio/openood/losses/ssim.py official repository unverified MIT (permissive) · d1619ad1bb7ea0f7 · report
validate zjysteven/sio/imagenet_train_subclasses.py official repository unverified MIT (permissive) · 02f1e9718544189d · report

Tasks

Out-of-Distribution Detection

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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