
vision
Deformable DETR
DETR with deformable attention for faster convergence and small objects.
Levelmodel
Classvision
Parameters40.18M
Contextnot in the notes
Released8 Oct 2020
Opennessopen weights permissive
Runs onmobile or NPU
Statusactive
Identity
- Developer
- SenseTime, University of Science and Technology of China (USTC)
- Family
- not in the notes
- Released
- 8 Oct 2020 sourcesannouncement page
- Weights published
- 2 Mar 2022
- Record checked
- 12 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
- Total parameters
- 40.18M sources
- Active parameters
- –
- Checkpoint parameters
- –
- Context length
- not in the notes
- Input
- image
- Output
- labels and boxes
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 weights permissive
- Licence
- Apache License 2.0 sources
- Access routes
- open weights download, cloud marketplace
Where this comes from
The licence file governs over registry tags and aggregator labels.
Deployment
- Runs on
- mobile or NPU
- Footprint
- Edge or toolkit builds listed in: Qualcomm AI Hub.
- 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.
Lineage
The notes record no lineage for this model.
Industry Use Cases
No industry use case links this model.
Links
Developers
SenseTimecompany, China
University of Science and Technology of China (USTC)university, China
SenseTimecompany, China
University of Science and Technology of China (USTC)university, ChinaModel
Deformable DETRSenseTime, vision
Deformable DETRSenseTime, 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 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.Organisations 2
Sources
- arxiv.org/abs/2010.04159 https://arxiv.org/abs/2010.04159
- huggingface.co/SenseTime/deformable-detr https://huggingface.co/SenseTime/deformable-detr
- ai.azure.com/catalog/models?task=object-detection https://ai.azure.com/catalog/models?task=object-detection
- aihub.qualcomm.com/models/deformable_detr https://aihub.qualcomm.com/models/deformable_detr
- github.com/fundamentalvision/Deformable-DETR https://github.com/fundamentalvision/Deformable-DETR
- paperswithcode.com/method/deformable-detr https://paperswithcode.com/method/deformable-detr
- huggingface.co/datasets/pwc-archive/methods https://huggingface.co/datasets/pwc-archive/methods
- arxiv.org/html/2010.04159 https://arxiv.org/html/2010.04159
To cite this page: Project AURION, AI Use-Cases Research & Innovation, "Deformable DETR", https://aurion.semai.id/models/deformable-detr/, records of October 2026.