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.
Keywords
Computer scienceConvolutional neural networkPascal (unit)Python (programming language)Artificial intelligenceObject detectionDeep learningPattern 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...
Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation
Object detection performance, as measured on the canonical PASCAL VOC dataset, has plateaued in the last few years. The best-performing methods are complex ensemble systems that...
Publication Info
- Year
- 2015
- Type
- article
- Pages
- 1440-1448
- Citations
- 26511
- Access
- Closed
External Links
Social Impact
Altmetric
PlumX Metrics
Social media, news, blog, policy document mentions
Citation Metrics
26511
OpenAlex
23351
CrossRef
Cite This
Ross Girshick
(2015).
Fast R-CNN.
2015 IEEE International Conference on Computer Vision (ICCV)
, 1440-1448.
https://doi.org/10.1109/iccv.2015.169
Identifiers
- DOI
- 10.1109/iccv.2015.169