Home

Awesome

Faster R-CNN in MXNet with distributed implementation and data parallelization


This repo is forked from https://github.com/precedenceguo/mx-rcnn, and added some new features on it:


Region Proposal Network solves object detection as a regression problem from the objectness perspective. Bounding boxes are predicted by applying learned bounding box deltas to base boxes, namely anchor boxes across different positions in feature maps. Training process directly learns a mapping from raw image intensities to bounding box transformation targets.

Fast R-CNN treats general object detection as a classification problem and bounding box prediction as a regression problem. Classifying cropped region feature maps and predicting bounding box displacements together yields detection results. Cropping feature maps instead of image input accelerates computation utilizing shared convolution maps. Bounding box displacements are simultaneously learned in the training process.

Faster R-CNN utilize an alternate optimization training process between RPN and Fast R-CNN. Fast R-CNN weights are used to initiate RPN for training.

Getting Started

Show Result

Training and Testing Faster R-CNN

Training and Testing Fast R-CNN

Information

Disclaimer

This repository used code from MXNet, Fast R-CNN, Faster R-CNN, caffe. Training data are from Pascal VOC, ImageNet. Model comes from VGG16.

References

  1. Tianqi Chen, Mu Li, Yutian Li, Min Lin, Naiyan Wang, Minjie Wang, Tianjun Xiao, Bing Xu, Chiyuan Zhang, and Zheng Zhang. MXNet: A Flexible and Efficient Machine Learning Library for Heterogeneous Distributed Systems. In Neural Information Processing Systems, Workshop on Machine Learning Systems, 2015
  2. Ross Girshick. "Fast R-CNN." In Proceedings of the IEEE International Conference on Computer Vision, 2015.
  3. Shaoqing Ren, Kaiming He, Ross Girshick, and Jian Sun. "Faster R-CNN: Towards real-time object detection with region proposal networks." In Advances in Neural Information Processing Systems, 2015.
  4. Yangqing Jia, Evan Shelhamer, Jeff Donahue, Sergey Karayev, Jonathan Long, Ross Girshick, Sergio Guadarrama, and Trevor Darrell. "Caffe: Convolutional architecture for fast feature embedding." In Proceedings of the ACM International Conference on Multimedia, 2014.
  5. Mark Everingham, Luc Van Gool, Christopher KI Williams, John Winn, and Andrew Zisserman. "The pascal visual object classes (voc) challenge." International journal of computer vision 88, no. 2 (2010): 303-338.
  6. Jia Deng, Wei Dong, Richard Socher, Li-Jia Li, Kai Li, and Li Fei-Fei. "ImageNet: A large-scale hierarchical image database." In Computer Vision and Pattern Recognition, IEEE Conference on, 2009.
  7. Karen Simonyan, and Andrew Zisserman. "Very deep convolutional networks for large-scale image recognition." arXiv preprint arXiv:1409.1556 (2014).