Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Caffe implementation of multiple popular object detection frameworks
| Date | Stars |
|---|---|
| 2026-07-24 | 1062 |
| 2026-07-25 | 1063 |
| 2026-07-28 | 1063 |
| 2026-07-30 | 1063 |
| 2026-08-06 | 1063 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# Cascade R-CNN: Delving into High Quality Object Detection
by Zhaowei Cai and Nuno Vasconcelos
This repository is written by Zhaowei Cai at UC San Diego.
## Introduction
This repository implements mulitple popular object detection algorithms, including Faster R-CNN, R-FCN, FPN, and our recently proposed Cascade R-CNN, on the MS-COCO and PASCAL VOC datasets. Multiple choices are available for backbone network, including AlexNet, VGG-Net and ResNet. It is written in C++ and powered by [Caffe](https://github.com/BVLC/caffe) deep learning toolbox.
[Cascade R-CNN](http://www.svcl.ucsd.edu/publications/conference/2018/cvpr/cascade-rcnn.pdf) is a multi-stage extension of the popular two-stage R-CNN object detection framework. The goal is to obtain high quality object detection, which can effectively reject close false positives. It consists of a sequence of detectors trained end-to-end with increasing IoU thresholds, to be sequentially more selective against close false positives. The output of a previous stage detector is forwarded to a later stage detector, and the detection results will be improved stage by stage. This idea can be applied to any detector based on the two-stage R-CNN framework, including Faster R-CNN, R-FCN, FPN, Mask R-CNN, etc, and reliable gains are available independently of baseline strength. A vanilla Cascade R-CNN on FPN detector of ResNet-101 backbone network, without any training or inference bells and whistles, achieved state-of-the-art results on the challenging MS-COCO dataset.
## Update
The re-implementation of Cascade R-CNN in Detectron has been released. See [Detectron-Cascade-RCNN](https://github.com/zhaoweicai/Detectron-Cascade-RCNN). Very consistent improvements are available for all tested models, independent of baseline strength.
It is also recommended to use the third-party implementation, [mmdetection](https://github.com/open-mmlab/mmdetection) based on PyTorch and [tensorpack](https://github.com/tensorpack/tensorpack/tree/master/examples/FasterRCNN) based on TensorFlow.
## Citation
If you use our code/model/data, please cite our paper:
@inproceedings{cai18cascadercnn,
author = {Zhaowei Cai and Nuno Vasconcelos},
Title = {Cascade R-CNN: Delving into High Quality Object Detection},
booktitle = {CVPR},
Year = {2018}
}
or its extension:
@article{cai2019cascadercnn,
author = {Zhaowei Cai and Nuno Vasconcelos},
title = {Cascade R-CNN: High Quality Object Detection and Instance Segmentation},
journal = {arXiv preprint arXiv:1906.09756},
year = {2019}
}
## Benchmarking
We benchmark mulitple detector models on the MS-COCO and PASCAL VOC datasets in the below tables.
1. MS-COCO (Train/Test: train2017/val2017, shorter size: 800 for FPN and 600 for the others)
model | #GPUs | bs | lr | iter | train time | test time | AP | AP50 | AP75
---------|--------|-----|--------|-----|-----|-------|-------|--------|-----
VGG-RPN-baseline | 2 | 4 |3e-3| 100k | 12.5 hr | 0.075s | 23.6 | 43.9 | 23.0
VGG-RPN-Cascade | 2 | 4 |3e-3| 100k | 15.5 hr | 0.115s | 27.0 | 44.2 | 27.7
Res50-RFCN-baseline | 4 | 1 |3e-3| 280k | 19 hr | 0.07s | 27.0 | 48.7 | 26.9
Res50-RFCN-Cascade | 4 | 1 |3e-3| 280k | 22.5 hr | 0.075s | 31.1 | 49.8 | 32.8
Res101-RFCN-baseline | 4 | 1 |3e-3| 280k | 29 hr | 0.075s | 30.3 | 52.2 | 30.8
Res101-RFCN-Cascade | 4 | 1 |3e-3| 280k | 30.5 hr | 0.085s | 33.3 | 52.0 | 35.2
Res50-FPN-baseline | 8 | 1 |5e-3| 280k | 32 hr | 0.095s | 36.5 | 58.6 | 39.2
Res50-FPN-Cascade | 8 | 1 |5e-3| 280k | 36 hr | 0.115s | 40.3 | 59.4 | 43.7
Res101-FPN-baseline | 8 | 1 |5e-3| 280k | 37 hr | 0.115s | 38.5 | 60.6 | 41.7
Res101-FPN-Cascade | 8 | 1 |5e-3| 280k | 46 hr | 0.14s | 42.7 | 61.6 | 46.6
2. PASCAL VOC 2007 (Train/Test: 2007+2012trainval/2007test, shorter size: 600)
model | #GPUs | bs | lr | iter | train time | AP | Excerpt of 10,498 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:2af664ed596006f8, topic:object-detection, desc:object detection, readme:object detection