# IDEA-Research/DINO

[ICLR 2023] Official implementation of the paper "DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection"

Repository: https://github.com/IDEA-Research/DINO
Canonical: https://ross.abutalabs.com/products/idea-research-dino
Language: Python
License: Apache-2.0
License Family: permissive
Topics: object-detection, computer-vision, deep-learning
Last push: 2024-07-31T13:56:21+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 1640, "days_push": 763, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2834, forks 309 (observed 2026-08-28T04:07:24.474624+00:00)

## What it is
Official PyTorch implementation of DINO, a state-of-the-art end-to-end object detection model based on DETR with improved denoising anchor boxes (ICLR 2023). It provides model code, training scripts, and pretrained checkpoints for COCO object detection.

## Use cases
- train a state-of-the-art object detection model on COCO
- run DETR-style transformer object detection inference
- reproduce ICLR 2023 DINO paper results
- fine-tune a pretrained object detector on custom images
- compare detection model baselines for research

## When to choose
- you need a top-performing end-to-end transformer-based object detector
- you want to reproduce or build on published DINO research results
- you need pretrained COCO detection checkpoints

## When to avoid
- you need open-vocabulary/text-prompted detection (use Grounding DINO instead)
- you need image segmentation (use Mask DINO or Semantic-SAM)
- you want a lightweight detector for edge or mobile deployment

## Facets
- artifact type: library
- maturity: maintenance
- function: computer-vision, machine-learning, deep-learning
- domain: computer-vision, deep-learning, machine-learning
- platform: python
- tags: object-detection, detr, transformer-detection, pytorch, research-code, iclr-2023, linux, gpu

## Member repositories
- IDEA-Research/DINO (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:24.474624+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 2026-08-30T07:37:48.524088+00:00, confidence not recorded.
  - readme: https://github.com/IDEA-Research/DINO (fetched 2026-08-28T04:07:24.474624+00:00, sha bfceff03e0c8)
- Data as of 2026-08-30T08:39:29.467469+00:00.