# DEIM

[DEIMv2] Real Time Object Detection Meets DINOv3

Repository: https://github.com/Intellindust-AI-Lab/DEIMv2
Canonical: https://ross.abutalabs.com/products/deim
Homepage: https://intellindust-ai-lab.github.io/projects/DEIMv2/
Language: Jupyter Notebook
License: NOASSERTION
License Family: other
Topics: detection-transformer, dinov3, object-detection, real-time, real-time-detection
Last push: 2026-08-24T06:10:00+00:00
Link (homepage): https://intellindust-ai-lab.github.io/projects/DEIMv2/

## Health v2 (maintenance only)
Score: 62/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 99, release rhythm 35, longevity 24
- inputs: {"age_days": 349, "days_push": 9, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1999, forks 212 (observed 2026-08-28T04:06:03.677450+00:00)

## What it is
DEIMv2 is a real-time object detection framework that extends the DEIM DETR family with DINOv3-pretrained and distilled backbones plus a Spatial Tuning Adapter. It ships eight model sizes from X down to Atto with pretrained weights, achieving state-of-the-art accuracy-efficiency trade-offs on COCO for GPU, edge, and mobile deployment.

## Use cases
- train a real-time object detection model on custom data
- run state-of-the-art object detection on edge devices
- fine-tune DINOv3-backed detectors on COCO
- deploy lightweight object detection on mobile
- benchmark detection models against YOLO variants
- convert a single-scale foundation model backbone into multi-scale detection features

## When to choose
- you need top accuracy-per-parameter real-time detection with pretrained weights
- you want DETR-style detection that converges fast
- you need model sizes spanning from mobile (Atto) to server (X)

## When to avoid
- you need a permissively licensed model (custom DEIMv2 license)
- you need segmentation or pose estimation out of the box (see EdgeCrafter)
- you require a non-PyTorch deployment stack without conversion effort

## Facets
- artifact type: library
- maturity: active
- function: machine-learning, computer-vision, image-processing, deep-learning
- domain: computer-vision, deep-learning, machine-learning
- platform: python, cross-platform
- tags: object-detection, detr, dinov3, real-time-detection, detection-transformer, model-zoo, pretrained-weights, coco, gpu

## Member repositories
- Intellindust-AI-Lab/DEIMv2 (main) score 62
- Intellindust-AI-Lab/DEIM (main) score 54

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:03.677450+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T03:02:08.832973+00:00, confidence not recorded.
  - readme: https://github.com/Intellindust-AI-Lab/DEIMv2 (fetched 2026-08-28T04:06:03.677450+00:00, sha 31f332fa3a5c)
  - homepage: https://intellindust-ai-lab.github.io/projects/DEIMv2/ (fetched 2026-08-29T10:41:56.226839+00:00, sha 4f8b567aa97e)
- Data as of 2026-08-30T08:39:29.467469+00:00.