# daijifeng001/R-FCN

R-FCN: Object Detection via Region-based Fully Convolutional Networks

Repository: https://github.com/daijifeng001/R-FCN
Canonical: https://ross.abutalabs.com/products/r-fcn
Language: MATLAB
License: NOASSERTION
License Family: other
Last push: 2017-05-05T15:50:59+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": 3729, "days_push": 3407, "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 1248, forks 533 (observed 2026-08-28T04:04:07.680951+00:00)

## What it is
MATLAB implementation of R-FCN, a region-based fully convolutional object detection framework described in a NIPS 2016 paper. It builds on a custom Caffe branch with ResNet backbones and provides training, inference, and demo scripts for object detection on datasets like PASCAL VOC.

## Use cases
- detect objects in images with a fully convolutional region-based detector
- train an object detection model on PASCAL VOC with ResNet backbones
- run the R-FCN demo to localize and classify objects in images
- reproduce NIPS 2016 R-FCN paper results
- compare R-FCN against Faster R-CNN baselines
- use a faster alternative to per-region subnetwork detectors

## When to choose
- you need the original MATLAB R-FCN implementation for research reproduction
- you work in MATLAB with Caffe and NVIDIA GPUs
- you want an efficient fully convolutional object detector sharing computation across the whole image

## When to avoid
- you want a maintained Python or MXNet implementation (use py-R-FCN or Deformable ConvNets instead)
- you need modern detection frameworks like PyTorch or TensorFlow
- you require end-to-end training with recent tooling

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, computer-vision, image-processing
- domain: computer-vision, deep-learning, machine-learning
- platform: windows
- tags: object-detection, r-fcn, caffe, resnet, deep-learning, research-code, nips-2016, linux, matlab, gpu

## Member repositories
- daijifeng001/R-FCN (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:07.680951+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 2026-08-30T05:07:51.711355+00:00, confidence not recorded.
  - readme: https://github.com/daijifeng001/R-FCN (fetched 2026-08-28T04:04:07.680951+00:00, sha 2fec99a882ba)
- Data as of 2026-08-30T08:39:29.467469+00:00.