Papers › GL-MCM: Global and Local Maximum Concept Matching for Zero-Shot Out-of-Distribution Detection

GL-MCM: Global and Local Maximum Concept Matching for Zero-Shot Out-of-Distribution Detection

10 Apr 2023arXiv:2304.04521archive 2025-07-28

Atsuyuki Miyai, Qing Yu, Go Irie, Kiyoharu Aizawa

Zero-shot out-of-distribution (OOD) detection is a task that detects OOD images during inference with only in-distribution (ID) class names. Existing methods assume ID images contain a single, centered object, and do not consider the more realistic multi-object scenarios, where both ID and OOD objects are present. To meet the needs of many users, the detection method must have the flexibility to adapt the type of ID images. To this end, we present Global-Local Maximum Concept Matching (GL-MCM), which incorporates local image scores as an auxiliary score to enhance the separability of global and local visual features. Due to the simple ensemble score function design, GL-MCM can control the type of ID images with a single weight parameter. Experiments on ImageNet and multi-object benchmarks demonstrate that GL-MCM outperforms baseline zero-shot methods and is comparable to fully supervised methods. Furthermore, GL-MCM offers strong flexibility in adjusting the target type of ID images. The code is available via https://github.com/AtsuMiyai/GL-MCM.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology: its repositories, every harvested function with whether it ran, its licence and the call to fetch it.

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="2304.04521")

Code

Syntology Ran 13 of 16 code samples harvested from 1 repository linked to this paper; 3 have no recorded run. Of those that ran: 1 ran · honoured contract; 3 ran · our draft was wrong; 1 ran · fixture could not drive it; 8 ran with no contract checked.

By repository: official repository: 16 samples from 1 repository, 13 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

atsumiyai/gl-mcm officialmentioned in paperpytorchMIT report
atsumiyai/locoop mentioned on GitHubpytorchMIT report
hoshi23/ood-x-banchmarks mentioned on GitHubpytorchMIT report
hoshi23/ood-x-benchmarks mentioned 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

16 samples harvested; 13 ran; 1 honoured the contract we drafted; 3 have no recorded run. Read from Syntology's graph 2026-09-25; that is when this build read the record, not when the samples ran.

1ran · honoured contract
3ran · our draft was wrong
1ran · fixture could not drive it
8ran
3unverified

Licence: 0 of the 16 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 atsumiyai/gl-mcm. “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.

accuracy atsumiyai/gl-mcm/utils/common.py official repository ran MIT (permissive) · 088e80bb4051265a · report
basic_clean atsumiyai/gl-mcm/clip/simple_tokenizer.py official repository ran · our draft was wrong fingerprinted MIT (permissive) · 98f385d847636a3e · report
fpr_and_fdr_at_recall atsumiyai/gl-mcm/utils/detection_util.py official repository ran · fixture could not drive it fingerprinted MIT (permissive) · 3853ecdb6fc74451 · report
get_pairs atsumiyai/gl-mcm/clip/simple_tokenizer.py official repository ran · our draft was wrong MIT (permissive) · d919ae32e5e4e616 · report
get_subset_with_len atsumiyai/gl-mcm/utils/train_eval_util.py official repository ran MIT (permissive) · 80c8dac5a9baef31 · report
get_test_labels atsumiyai/gl-mcm/utils/common.py official repository ran MIT (permissive) · 75e589009e3da37c · report
load_scores atsumiyai/gl-mcm/utils/file_ops.py official repository ran MIT (permissive) · 2358075eb310a541 · report
prepare_dataframe atsumiyai/gl-mcm/utils/file_ops.py official repository ran MIT (permissive) · 1be3e6a03938ec75 · report
read_file atsumiyai/gl-mcm/utils/common.py official repository ran MIT (permissive) · 65aed69fd9c43272 · report
set_val_loader atsumiyai/gl-mcm/utils/train_eval_util.py official repository ran MIT (permissive) · f3fda6c7f479b606 · report
setup_log atsumiyai/gl-mcm/utils/file_ops.py official repository ran MIT (permissive) · db2eed8f505e7836 · report
stable_cumsum atsumiyai/gl-mcm/utils/detection_util.py official repository ran · honoured contract fingerprinted MIT (permissive) · d4acb3120a027622 · report
whitespace_clean atsumiyai/gl-mcm/clip/simple_tokenizer.py official repository ran · our draft was wrong fingerprinted MIT (permissive) · 9542161e9640b858 · report
build_model atsumiyai/gl-mcm/clip/model.py official repository unverified MIT (permissive) · a7667e7d84eccfd8 · report
get_measures atsumiyai/gl-mcm/utils/detection_util.py official repository unverified MIT (permissive) · 24570af601666d85 · report
load atsumiyai/gl-mcm/clip/clip.py official repository unverified MIT (permissive) · c22a78c25372b59f · report

Tasks

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

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

CLIP

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