Papers › MOS: Towards Scaling Out-of-distribution Detection for Large Semantic Space

MOS: Towards Scaling Out-of-distribution Detection for Large Semantic Space

5 May 2021CVPR 2021 1arXiv:2105.01879archive 2025-07-28

Rui Huang, Yixuan Li

Detecting out-of-distribution (OOD) inputs is a central challenge for safely deploying machine learning models in the real world. Existing solutions are mainly driven by small datasets, with low resolution and very few class labels (e.g., CIFAR). As a result, OOD detection for large-scale image classification tasks remains largely unexplored. In this paper, we bridge this critical gap by proposing a group-based OOD detection framework, along with a novel OOD scoring function termed MOS. Our key idea is to decompose the large semantic space into smaller groups with similar concepts, which allows simplifying the decision boundaries between in- vs. out-of-distribution data for effective OOD detection. Our method scales substantially better for high-dimensional class space than previous approaches. We evaluate models trained on ImageNet against four carefully curated OOD datasets, spanning diverse semantics. MOS establishes state-of-the-art performance, reducing the average FPR95 by 14.33% while achieving 6x speedup in inference compared to the previous best method.

PaperPDFConference PDFCodeCode 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 4 code samples harvested from 4 repositories linked to this paper: 3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified. Where Syntology's instrument failed: 2 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code. Every run on this page is a failure of Syntology's instrument, not of the code.

By repository: official repository: 1 sample from 1 repository, 1 ran (0 with no instrument failure; 1 where Syntology's instrument failed); community (archive-listed): 3 samples from 3 repositories, 2 ran (0 with no instrument failure; 2 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.

No sample is linked to this paper from 1 of its repositories that Syntology harvested for other papers:

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

deeplearning-wisc/large_scale_ood officialmentioned in papermentioned on GitHubpytorchSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
deeplearning-wisc/gradnorm_ood mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
ma-kjh/CMA-OoDD mentioned on GitHubpytorchSyntology: 1 sample, 0 ran · 1 unverified report
tmlr-group/class_prior mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
tmlr-group/neglabel mentioned on GitHubpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Negative Label Guided OOD Detection with Pretrained Vision-Language Models (arXiv:2403.20078; that paper's own run record: 9 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

4 samples harvested: 3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Every run on this page is a failure 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.

2ran · our draft was wrong
1ran; the contract check could not run
1unverified

Licence: 1 of the 4 samples is 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 4 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “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”. “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.

deeplearning-wisc/large_scale_ood official repository 1 sample, 1 ran (1 instrument-failed) · 0 unverified
calc_group_softmax_loss finetune.py ran · our draft was wrong Apache-2.0 (permissive) · 1caff2f8b8fc899d · report fixture: signature criterion:callable/0/?, logits:Tensor/2/float, labels:Tensor/2/int, group_slices:Tensor/2/int · returned Tensor · level recorded 2026-09-22
deeplearning-wisc/gradnorm_ood community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
get_Mahalanobis_score in 8 papers utils/mahalanobis_lib.py ran · our draft was wrong Apache-2.0 (permissive) · ae64ecb508b5b2bb · report fixture: returned ndarray · level recorded 2026-09-22
ma-kjh/CMA-OoDD community (archive-listed) 1 sample, 0 ran · 1 unverified
CLIP in 25 papers clip/model.py unverified no licence file found · pointer only · ef2d645ece6b584c · report
tmlr-group/class_prior community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
iterate_data_mahalanobis funcs.py ran; the contract check could not run (RAISES) MIT (permissive) · 12fc2270fe050752 · report fixture: returned tuple · level recorded 2026-09-22

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. Siblings are assemblies lifted from this paper in the same batch for the same method: alternative readings kept side by side; none replaces or supersedes another.

4 assemblies on this paper: 4 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).

4 sibling assemblies for MOS (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.

harvested Assembly for MOS (graph method: MOS). 1 brick; individually on a fixture: 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 4 siblings

  1. get_Mahalanobis_score entry · level 1 · ran · our draft was wrong · ae64ecb508b5b2bb

harvested Assembly for MOS (graph method: MOS). 2 bricks; individually on a fixture: 2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 4 siblings

  1. iterate_data_mahalanobis entry · level 1 · ran; the contract check could not run (RAISES) · 12fc2270fe050752
  2. get_Mahalanobis_score helper · level 1 · ran · our draft was wrong · ae64ecb508b5b2bb

harvested Assembly for MOS (graph method: MOS). 9 bricks; individually on a fixture: 8 ran (of which 7 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.

one of 4 siblings

  1. CLIP entry · level 0 · unverified · ef2d645ece6b584c
  2. LayerNorm helper · level 1 · ran · e296840ad4106ad9
  3. ModifiedResNet model · level 1 · ran · aedc8261aa63cda3
  4. Transformer model · level 1 · ran · 46053fd5fb7a6576
  5. VisionTransformer model · level 1 · ran · dee6bfa940b2b6a4
  6. AttentionPool2d model · level 1 · ran · 733f63bc89b6c510
  7. Bottleneck helper · level 1 · ran · 50b240334bdc6bc6
  8. ResidualAttentionBlock model · level 1 · ran · 6088793f94190d8d
  9. QuickGELU helper · level 1 · ran · 8c5c4de012c0aab9

harvested Assembly for MOS (graph method: MOS). 1 brick; individually on a fixture: 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 4 siblings

  1. calc_group_softmax_loss entry · level 1 · ran · our draft was wrong · 1caff2f8b8fc899d

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="2105.01879") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Image ClassificationOut-of-Distribution Detectionimage-classification

Datasets

Introduced by this paper, per the archive.

ImageNet-1k vs PlacesImageNet-1k vs SUNImageNet-1k vs TexturesImageNet-1k vs iNaturalist

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Out-of-Distribution Detection ImageNet-1k vs Curated OODs (avg.) MOS (BiT-S-R101x1) AUROC 90.11 #11 of 16 Archive leaderboard report
Out-of-Distribution Detection ImageNet-1k vs Curated OODs (avg.) MOS (BiT-S-R101x1) FPR95 39.97 #11 of 16 Archive leaderboard report
Out-of-Distribution Detection ImageNet-1k vs Places MOS (BiT-S-R101x1) AUROC 89.06 #14 of 25 Archive leaderboard report
Out-of-Distribution Detection ImageNet-1k vs Places MOS (BiT-S-R101x1) FPR95 49.54 #14 of 25 Archive leaderboard report
Out-of-Distribution Detection ImageNet-1k vs SUN MOS (BiT-S-R101x1) AUROC 92.01 #11 of 22 Archive leaderboard report
Out-of-Distribution Detection ImageNet-1k vs SUN MOS (BiT-S-R101x1) FPR95 40.63 #11 of 22 Archive leaderboard report
Out-of-Distribution Detection ImageNet-1k vs Textures MOS (BiT-S-R101x1) AUROC 81.23 #27 of 34 Archive leaderboard report
Out-of-Distribution Detection ImageNet-1k vs Textures MOS (BiT-S-R101x1) FPR95 60.43 #27 of 34 Archive leaderboard report
Out-of-Distribution Detection ImageNet-1k vs iNaturalist MOS (BiT-S-R101x1) AUROC 98.15 #7 of 28 Archive leaderboard report
Out-of-Distribution Detection ImageNet-1k vs iNaturalist MOS (BiT-S-R101x1) FPR95 9.28 #7 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.

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