# sfzhang15/RefineDet

Single-Shot Refinement Neural Network for Object Detection, CVPR, 2018

Repository: https://github.com/sfzhang15/RefineDet
Canonical: https://ross.abutalabs.com/products/refinedet
Language: C++
License: NOASSERTION
License Family: other
Topics: object-detection
Last push: 2019-03-18T12:42:45+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": 3210, "days_push": 2725, "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 1424, forks 383 (observed 2026-08-28T04:04:41.403903+00:00)

## What it is
RefineDet is a C++/Caffe implementation of the CVPR 2018 single-shot object detection model that refines anchors to combine one-stage speed with two-stage accuracy. It provides training, evaluation, and pre-trained models for object detection research.

## Use cases
- train a single-shot object detection model
- reproduce RefineDet CVPR 2018 results
- evaluate object detectors on VOC and COCO
- compare one-stage vs two-stage detector accuracy
- fine-tune a pre-trained object detection model
- research anchor refinement for detection

## When to choose
- you need a research-grade object detector with published CVPR results
- you want to build on or extend a Caffe-based detection pipeline
- you need pre-trained RefineDet models for benchmarking

## When to avoid
- you need a maintained framework with recent GPU/CUDA support
- you want PyTorch or TensorFlow tooling
- you need production-ready detection with easy deployment

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, computer-vision, image-processing
- domain: computer-vision, deep-learning, machine-learning
- platform: cpp, python
- tags: object-detection, caffe, cvpr-2018, single-shot-detector, research-code, linux, gpu

## Member repositories
- sfzhang15/RefineDet (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:41.403903+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 2026-08-30T04:37:36.793600+00:00, confidence not recorded.
  - readme: https://github.com/sfzhang15/RefineDet (fetched 2026-08-28T04:04:41.403903+00:00, sha bed1ff7371f1)
- Data as of 2026-08-30T08:39:29.467469+00:00.