# PeizeSun/SparseR-CNN

[CVPR2021, PAMI2023] End-to-End Object Detection with Learnable Proposal

Repository: https://github.com/PeizeSun/SparseR-CNN
Canonical: https://ross.abutalabs.com/products/sparser-cnn
Language: Python
License: MIT
License Family: permissive
Last push: 2023-04-30T18:33:48+00:00

## Health v2 (maintenance only)
Score: 23/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 2113, "days_push": 1221, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1343, forks 191 (observed 2026-08-28T04:04:26.487474+00:00)

## What it is
Sparse R-CNN is a PyTorch implementation (built on Detectron2) of the CVPR 2021 / PAMI 2023 paper 'End-to-End Object Detection with Learnable Proposals'. It provides a sparse, set-based object detection model that replaces dense candidate generation with a small set of learnable proposals, with pretrained models and training configs included.

## Use cases
- run end-to-end object detection with learnable proposals
- train a sparse detection model on custom datasets
- reproduce CVPR 2021 Sparse R-CNN benchmark results
- compare sparse detectors against DETR and Faster R-CNN
- download pretrained COCO detection checkpoints
- research learnable proposal-based detection architectures

## When to choose
- you need a sparse, end-to-end object detector without dense candidate generation
- you want to reproduce or extend published Sparse R-CNN results
- you already use Detectron2 and want a set-based detection head
- you need pretrained COCO models with reported AP and inference speeds

## When to avoid
- you need a maintained production detector - the repo has seen little activity since 2023
- you want plug-and-play detection without GPU training infrastructure
- you need detection on mobile or edge devices
- you require non-PyTorch or non-Detectron2 ecosystems

## 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, sparse-r-cnn, cvpr-2021, detectron2, learnable-proposals, computer-vision-research, pytorch, gpu, linux, docker

## Member repositories
- PeizeSun/SparseR-CNN (main) score 23

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:26.487474+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 2026-08-30T04:42:52.212628+00:00, confidence not recorded.
  - readme: https://github.com/PeizeSun/SparseR-CNN (fetched 2026-08-28T04:04:26.487474+00:00, sha 958e48302d1f)
- Data as of 2026-08-30T08:39:29.467469+00:00.