Papers › DisCoPatch: Taming Adversarially-driven Batch Statistics for Improved...

DisCoPatch: Taming Adversarially-driven Batch Statistics for Improved Out-of-Distribution Detection

14 Jan 2025arXiv:2501.08005archive 2025-07-28

Francisco Caetano, Christiaan Viviers, Luis A. Zavala-Mondragón, Peter H. N. de With, Fons van der Sommen

Out-of-distribution (OOD) detection holds significant importance across many applications. While semantic and domain-shift OOD problems are well-studied, this work focuses on covariate shifts - subtle variations in the data distribution that can degrade machine learning performance. We hypothesize that detecting these subtle shifts can improve our understanding of in-distribution boundaries, ultimately improving OOD detection. In adversarial discriminators trained with Batch Normalization (BN), real and adversarial samples form distinct domains with unique batch statistics - a property we exploit for OOD detection. We introduce DisCoPatch, an unsupervised Adversarial Variational Autoencoder (VAE) framework that harnesses this mechanism. During inference, batches consist of patches from the same image, ensuring a consistent data distribution that allows the model to rely on batch statistics. DisCoPatch uses the VAE's suboptimal outputs (generated and reconstructed) as negative samples to train the discriminator, thereby improving its ability to delineate the boundary between in-distribution samples and covariate shifts. By tightening this boundary, DisCoPatch achieves state-of-the-art results in public OOD detection benchmarks. The proposed model not only excels in detecting covariate shifts, achieving 95.5% AUROC on ImageNet-1K(-C) but also outperforms all prior methods on public Near-OOD (95.0%) benchmarks. With a compact model size of 25MB, it achieves high OOD detection performance at notably lower latency than existing methods, making it an efficient and practical solution for real-world OOD detection applications. The code is publicly available.

PaperPDFCode Syntology ranMethod as code

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 6 code samples harvested from 1 repository linked to this paper: 3 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified; every one of the 3 samples that ran constructed an object rather than computing a result. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: found in paper text by Syntology: 6 samples from 1 repository, 3 ran (3 with no instrument failure; 0 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written on 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

caetas/DisCoPatch found in paper text by SyntologySyntology: 6 samples, 3 ran (0 instrument-failed) · 3 unverified 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: 3 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified; every one of the 3 samples that ran constructed an object rather than computing a result. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

3ran
3unverified

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 caetas/DisCoPatch. “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. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. For 1 sample that ran, the graph records a signature this page does not show: for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (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 are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. 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 six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. 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.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

caetas/DisCoPatch found in paper text by Syntology 6 samples, 3 ran (0 instrument-failed) · 3 unverified
Discriminator in 42 papers src/discopatch/models/DisCoPatch.py ran · metamorphic tier: deterministic no licence file found · pointer only · c7c8dd4dcf04dd5f · report fixture: returned Discriminator · level recorded 2026-09-22
MSSIM src/discopatch/models/DisCoPatch.py ran · metamorphic tier: deterministic no licence file found · pointer only · e96938c177b897ed · report fixture: returned MSSIM · level recorded 2026-09-22
Patchnorm2D src/discopatch/models/DisCoPatch.py ran · metamorphic tier: deterministic no licence file found · pointer only · be451fcb6df06550 · report fixture: returned Patchnorm2D · level recorded 2026-09-22
DisCoPatch src/discopatch/models/DisCoPatch.py unverified no licence file found · pointer only · 54c49855ae7a173d · report
VanillaVAE src/discopatch/models/DisCoPatch.py unverified no licence file found · pointer only · fd69deb104cee551 · report
create_checkpoint_dir src/discopatch/models/DisCoPatch.py unverified no licence file found · pointer only · ecf6b3c0b950c09e · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for DisCoPatch (graph method: DisCoPatch). 6 bricks; individually on a fixture: 3 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified; every one of the 3 samples that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

  1. DisCoPatch entry · level 0 · unverified · 54c49855ae7a173d
  2. Discriminator model · level 1 · ran · c7c8dd4dcf04dd5f
  3. Patchnorm2D helper · level 1 · ran · be451fcb6df06550
  4. VanillaVAE model · level 0 · unverified · fd69deb104cee551
  5. create_checkpoint_dir helper · level 0 · unverified · ecf6b3c0b950c09e
  6. MSSIM metric · level 1 · ran · e96938c177b897ed

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2501.08005") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

AllOut of Distribution (OOD) DetectionOut-of-Distribution Detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Out-of-Distribution Detection ImageNet-1K vs ImageNet-C DisCoPatch AUROC 97.2 #1 of 1 Archive leaderboard report
Out-of-Distribution Detection ImageNet-1K vs ImageNet-C DisCoPatch FPR95 10.6 #1 of 1 Archive leaderboard report
Out-of-Distribution Detection ImageNet-1K vs ImageNet-C DisCoPatch Latency, ms 1.56 #1 of 1 Archive leaderboard report
Out-of-Distribution Detection ImageNet-1K vs SSB-hard DisCoPatch AUROC 95.8 #1 of 1 Archive leaderboard report
Out-of-Distribution Detection ImageNet-1K vs SSB-hard DisCoPatch FPR95 19.8 #1 of 1 Archive leaderboard report
Out-of-Distribution Detection ImageNet-1K vs SSB-hard DisCoPatch Latency, ms 1.56 #1 of 1 Archive leaderboard report
Out-of-Distribution Detection ImageNet-1k vs NINCO DisCoPatch AUROC 94.3 #3 of 5 Archive leaderboard report
Out-of-Distribution Detection ImageNet-1k vs NINCO DisCoPatch FPR@95 39.0 #3 of 5 Archive leaderboard report
Out-of-Distribution Detection ImageNet-1k vs NINCO DisCoPatch Latency, ms 1.56 #3 of 5 Archive leaderboard report
Out-of-Distribution Detection ImageNet-1k vs OpenImage-O DisCoPatch AUROC 94.4 #4 of 7 Archive leaderboard report
Out-of-Distribution Detection ImageNet-1k vs OpenImage-O DisCoPatch FPR95 29.7 #4 of 7 Archive leaderboard report
Out-of-Distribution Detection ImageNet-1k vs OpenImage-O DisCoPatch Latency, ms 1.56 #4 of 7 Archive leaderboard report
Out-of-Distribution Detection ImageNet-1k vs Textures DisCoPatch AUROC 96.4 #7 of 34 Archive leaderboard report
Out-of-Distribution Detection ImageNet-1k vs Textures DisCoPatch FPR95 18.9 #7 of 34 Archive leaderboard report
Out-of-Distribution Detection ImageNet-1k vs Textures DisCoPatch Latency, ms 1.56 #7 of 34 Archive leaderboard report
Out-of-Distribution Detection ImageNet-1k vs iNaturalist DisCoPatch AUROC 99.1 #5 of 28 Archive leaderboard report
Out-of-Distribution Detection ImageNet-1k vs iNaturalist DisCoPatch FPR95 3.6 #5 of 28 Archive leaderboard report
Out-of-Distribution Detection ImageNet-1k vs iNaturalist DisCoPatch Latency, ms 1.56 #5 of 28 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

Batch Normalization

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