Faster R-CNN is an object detection model that improves on Fast R-CNN by utilising a region proposal network (RPN) with the CNN model. The RPN shares full-image convolutional features with the detection network, enabling nearly cost-free region proposals. It is a fully convolutional network that simultaneously predicts object bounds and objectness scores at each position. The RPN is trained end-to-end to generate high-quality region proposals, which are used by Fast R-CNN for detection. RPN and Fast R-CNN are merged into a single network by sharing their convolutional features: the RPN component tells the unified network where to look.
There are several Faster R-CNN models available in Detectron2, with different backbones and learning schedules.
To load from the Detectron2 model zoo:
from detectron2 import model_zoo
model = model_zoo.get("COCO-Detection/faster_rcnn_R_50_C4_1x.yaml", trained=True)
Replace the configuration path with the variant you want to use. You can find the paths in the model summaries at the top of this page.
You can follow the Getting Started guide on Colab to see how to train a model.
You can also read the official Detectron2 documentation.
@misc{wu2019detectron2,
author = {Yuxin Wu and Alexander Kirillov and Francisco Massa and
Wan-Yen Lo and Ross Girshick},
title = {Detectron2},
howpublished = {\url{https://github.com/facebookresearch/detectron2}},
year = {2019}
}
Object Detection on COCO minival
| MODEL | BOX AP |
|---|---|
| Faster R-CNN (X101-FPN, 3x) | 43.0 |
| Faster R-CNN (R101-FPN, 3x) | 42.0 |
| Faster R-CNN (R101-C4, 3x) | 41.1 |
| Faster R-CNN (R101-DC5, 3x) | 40.6 |
| Faster R-CNN (R50-FPN, 3x) | 40.2 |
| Faster R-CNN (R50-DC5, 3x) | 39.0 |
| Faster R-CNN (R50-C4, 3x) | 38.4 |
| Faster R-CNN (R50-FPN, 1x) | 37.9 |
| Faster R-CNN (R50-DC5, 1x) | 37.3 |
| Faster R-CNN (R50-C4, 1x) | 35.7 |
