# ShoufaChen/DiffusionDet

[ICCV2023 Best Paper Finalist] PyTorch implementation of DiffusionDet (https://arxiv.org/abs/2211.09788)

Repository: https://github.com/ShoufaChen/DiffusionDet
Canonical: https://ross.abutalabs.com/products/diffusiondet
Language: Python
License: NOASSERTION
License Family: other
Last push: 2022-12-22T04:40:55+00:00

## Health v2 (maintenance only)
Score: 22/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 8, longevity 98
- inputs: {"age_days": 1385, "days_push": 1350, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2257, forks 184 (observed 2026-08-28T04:06:31.465797+00:00)

## What it is
PyTorch implementation of DiffusionDet, the first diffusion-model-based object detection framework (ICCV 2023 Best Paper Finalist). It provides pretrained models on COCO and LVIS with configurable backbones like ResNet and Swin Transformer.

## Use cases
- detect objects in images using a diffusion model
- run object detection with a variable number of denoising steps
- reproduce ICCV 2023 DiffusionDet paper results on COCO and LVIS
- fine-tune a diffusion-based object detector on custom datasets
- compare diffusion-based detection against DETR-style detectors
- use pretrained ResNet or Swin backbone detection models

## When to choose
- you want to experiment with diffusion models for object detection
- you need a research baseline for diffusion-based detection
- you want flexible inference with adjustable denoising steps trading speed for accuracy

## When to avoid
- you need a production-ready, actively maintained detector
- you need real-time detection at high frame rates
- you require a permissive commercial license (CC-BY-NC 4.0 restricts commercial use)

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning, computer-vision, image-processing
- domain: computer-vision, deep-learning, machine-learning, artificial-intelligence
- platform: python
- tags: object-detection, diffusion-model, pytorch, research-code, iccv2023, coco, lvis, linux, gpu

## Member repositories
- ShoufaChen/DiffusionDet (main) score 22

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:31.465797+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 2026-08-30T02:43:39.826723+00:00, confidence not recorded.
  - readme: https://github.com/ShoufaChen/DiffusionDet (fetched 2026-08-28T04:06:31.465797+00:00, sha 7de482164d89)
- Data as of 2026-08-30T08:39:29.467469+00:00.