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

Atsuyuki Miyai; Go Irie; Kiyoharu Aizawa; Qing Yu

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

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2304.04521 v4 pith:HP2RI6YE submitted 2023-04-10 cs.CV

Atsuyuki Miyai , Qing Yu , Go Irie , Kiyoharu Aizawa This is my paper · ORCID

classification cs.CV

keywords gl-mcmimagesdetectionlocalmethodstypezero-shotconcept

verification ladder T0 review T1 audit T2 compute T3 formal

0 comments

read the original abstract

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.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 2 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

$\Delta \mathrm{Energy}$: Optimizing Energy Change During Vision-Language Alignment Improves both OOD Detection and OOD Generalization
cs.CV 2025-10 reject novelty 5.0 of 10

ΔEnergy, an energy-change OOD score for CLIP, and its EBM fine-tuning loss simultaneously improve OOD detection and covariate-shift generalization.
Reliable Few-shot Learning under Dual Noises
cs.CV 2025-06 conditional novelty 5.0 of 10

DETA++ combines region-weighting, noise-entropy maximization, memory-bank prototypes, and intra-class region swapping to handle both in-distribution and out-of-distribution noise in few-shot learning.

Pith tools