Fast R-CNN

TL;DR

Fast R-CNN introduces a highly efficient object detection method that significantly accelerates training and testing times while improving accuracy, by building on deep convolutional networks and innovative training techniques.

Contribution

Fast R-CNN presents a novel framework that greatly speeds up training and testing of deep object detectors, outperforming previous methods like R-CNN and SPPnet.

Findings

Training VGG16 9x faster than R-CNN

Testing speed 213x faster than R-CNN

Higher mAP on PASCAL VOC 2012

Abstract

This paper proposes a Fast Region-based Convolutional Network method (Fast R-CNN) for object detection. Fast R-CNN builds on previous work to efficiently classify object proposals using deep convolutional networks. Compared to previous work, Fast R-CNN employs several innovations to improve training and testing speed while also increasing detection accuracy. Fast R-CNN trains the very deep VGG16 network 9x faster than R-CNN, is 213x faster at test-time, and achieves a higher mAP on PASCAL VOC 2012. Compared to SPPnet, Fast R-CNN trains VGG16 3x faster, tests 10x faster, and is more accurate. Fast R-CNN is implemented in Python and C++ (using Caffe) and is available under the open-source MIT License at https://github.com/rbgirshick/fast-rcnn.