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 this https URL.
Keywords
Computer sciencePascal (unit)Convolutional neural networkPython (programming language)Artificial intelligenceDeep learningObject detectionPattern recognition (psychology)
Affiliated Institutions
Related Publications
Fast R-CNN
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 proposa...
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
State-of-the-art object detection networks depend on region proposal algorithms to hypothesize object locations. Advances like SPPnet and Fast R-CNN have reduced the running tim...
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal\n Networks
State-of-the-art object detection networks depend on region proposal\nalgorithms to hypothesize object locations. Advances like SPPnet and Fast R-CNN\nhave reduced the running t...
Object Detection Networks on Convolutional Feature Maps
Most object detectors contain two important components: a feature extractor and an object classifier. The feature extractor has rapidly evolved with significant research efforts...
Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition
Existing deep convolutional neural networks (CNNs) require a fixed-size (e.g., 224 × 224) input image. This requirement is "artificial" and may reduce the recognition accuracy f...
Publication Info
- Year
- 2015
- Type
- preprint
- Citations
- 1766
- Access
- Closed
External Links
Citation Metrics
1766
OpenAlex
Cite This
Ross Girshick
(2015).
Fast R-CNN.
arXiv (Cornell University)
.