Project AURIONAI Use-Cases Research & Innovation
IDEA Research (International Digital Economy Academy)
visionfamily

DINO (DETR with improved denoising anchor boxes)

IDEA Research line of DETR detectors with dynamic anchor boxes and query denoising, released in the detrex toolbox.

IDEA Research (International Digital Economy Academy)IDEA Research (International Digital Economy Academy)China
Figure from the DINO (DETR with improved denoising anchor boxes) paper: AP on COCO compared with other detection models.
Levelfamily
Classvision
Parametersnot in the notes
Contextnot in the notes
Released7 Mar 2022
Opennessopen source
Runs onnot in the notes
Statusactive

Lineage

20222023DAB-DETRDAB-DETR, Jan 2022DN-DETRDN-DETR, Mar 2022DINO detectorDINO detector, Mar 2022Mask DINOMask DINO, Jun 2022
IDEA Research (International Digital Economy Academy)Mask DINO belongs to this familyvision6 Jun 2022
IDEA Research (International Digital Economy Academy)DINO detector belongs to this familyvision7 Mar 2022
IDEA Research (International Digital Economy Academy)DN-DETR belongs to this familyvision2 Mar 2022
IDEA Research (International Digital Economy Academy)DAB-DETR belongs to this familyvision28 Jan 2022
Where this comes from
Parent and child relations from model cards, Hugging Face base_model fields and the genealogy tables of the research notes. Confidence and evidence are the notes' own.

R&D Topics

Real-time object detection (YOLO and DETR lines)produced by

Identity

Developer
IDEA Research (International Digital Economy Academy)
Family
not in the notes
Released
7 Mar 2022 sourcesannouncement page
Weights published
–
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
– sources
Active parameters
–
Checkpoint parameters
–
Note
DAB-DETR (arXiv 2201.12329), DN-DETR (arXiv 2203.01305), DINO and Mask DINO.
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 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
not in the notes
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.

Sources

  1. arxiv.org/abs/2203.03605 https://arxiv.org/abs/2203.03605
  2. github.com/IDEA-Research/detrex https://github.com/IDEA-Research/detrex
  3. modelscope.cn/models/iic/cv_swinl_image-object-detection_dino https://www.modelscope.cn/models/iic/cv_swinl_image-object-detection_dino
  4. github.com/open-mmlab/mmdetection/tree/main/configs/dab_... https://github.com/open-mmlab/mmdetection/tree/main/configs/dab_detr
  5. arxiv.org/abs/2201.12329 https://arxiv.org/abs/2201.12329
  6. github.com/open-mmlab/mmdetection/tree/main/configs/dino https://github.com/open-mmlab/mmdetection/tree/main/configs/dino
  7. arxiv.org/abs/2203.01305 https://arxiv.org/abs/2203.01305

To cite this page: Project AURION, AI Use-Cases Research & Innovation, "DINO (DETR with Improved Denoising Anchor Boxes)", https://aurion.semai.id/models/idea-research-dino-detr/, records of October 2026.