vision
DEIM
Real-time DETR training scheme; the paper compares DEIM-D-FINE-L against D-FINE-L.
Levelmodel
Classvision
Parametersnot in the notes
Contextnot in the notes
Released5 Dec 2024
Opennessopen source
Runs onsingle datacentre GPU
Statusactive
Lineage
successor
D-FINE is the parent (successor)medium confidencenotesWhere this comes from
Parent and child relations from model cards, Hugging Face base_model fields and the genealogy tables of the research notes. The tree shows two generations each way, 3 models. Confidence and evidence are the notes' own.
Identity
- Developer
- Intellindust AI Lab, City University of Hong Kong, Great Bay University, Hefei Normal University
- Family
- not in the notes
- Released
- 5 Dec 2024 sourcesannouncement page
- Weights published
- –
- Record checked
- 10 Oct 2026
Where this comes from
Developer and dates from the research notes. Release date is the vendor's public announcement; weights date is when open weights were published.
Architecture and Size
- Architecture
- dense transformer DETR with Improved Matching for Fast Convergence; a training scheme applied on top of D-FINE
- Total parameters
- – sources
- Active parameters
- –
- Checkpoint parameters
- –
- Context length
- not in the notes
- Input
- image
- Output
- not in the notes
Where this comes from
Parameter counts as the developer states them. Where the checkpoint holds a different total, both are shown (register A16).
Openness and Access
- Openness
- open source
- Licence
- Apache License 2.0 sources
- Access routes
- open weights download
Where this comes from
The licence file governs over registry tags and aggregator labels.
Deployment
- Runs on
- single datacentre GPU
- Footprint
- not in the notes
- Runtimes
- not in the notes
Where this comes from
Deployment tiers and runtimes as named in the notes. Footprint is the notes' figure, not a measurement by AURION.
Indonesia
- Indonesian support
- not stated
- Regional languages
- not in the notes
- Jakarta hosting
- unknown
- Languages
- not in the notes
Where this comes from
Indonesia fields are carried on every model; unknown is an allowed value.
Benchmark Results
The notes record no benchmark result for this model.
Industry Use Cases
No industry use case links this model.
Links
DevelopersIntellindust AI Labcompany, China
City University of Hong Konguniversity, China
Great Bay Universityuniversity, China
Hefei Normal Universityuniversity, China
Intellindust AI Labcompany, ChinaCity University of Hong Konguniversity, ChinaGreat Bay Universityuniversity, ChinaHefei Normal Universityuniversity, ChinaModelDEIMIntellindust AI Lab, vision
DEIMIntellindust AI Lab, visionUse CasesSafety (PPE, Hazards, Fatigue)IndustrialVisual Quality Inspection and Defect DetectionIndustrialUse cases of models in the same R&D topic; none is recorded for this model itself.
Who Runs It
PT Bukit Asam TbkIn production, 9 Sep 2026
PT Aneka Tambang Tbk (ANTAM), ferronickelIn production, 9 Sep 2026PLN Indonesia Power with Huawei (PLTU Banten 3 Lontar)Research, 26 Nov 2025
PT Kilang Pertamina Internasional (Pertamina refineries)In production, 17 Oct 2025+5 moreDeployments of these use cases; none names this model.
PT Bukit Asam TbkIn production, 9 Sep 2026PT Aneka Tambang Tbk (ANTAM), ferronickelIn production, 9 Sep 2026PLN Indonesia Power with Huawei (PLTU Banten 3 Lontar)Research, 26 Nov 2025PT Kilang Pertamina Internasional (Pertamina refineries)In production, 17 Oct 2025+5 moreDeployments of these use cases; none names this model.Organisations 4
Sources
- DEIM: DETR with Improved Matching for Fast Convergence arxiv.org https://arxiv.org/abs/2412.04234
- GitHub - Intellindust-AI-Lab/DEIM: [CVPR 2025] DEIM: DETR with Improved Matching for Fast Convergence github.com https://github.com/ShihuaHuang95/DEIM
- playground.roboflow.com/models/compare/deim-vs-rf-detr https://playground.roboflow.com/models/compare/deim-vs-rf-detr
To cite this page: Project AURION, AI Use-Cases Research & Innovation, "DEIM", https://aurion.semai.id/models/intellindust-deim/, records of October 2026.