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 9× faster than R-CNN, is 213× faster at test-time, and achieves a higher mAP on PASCAL VOC 2012. Compared to SPPnet, Fast R-CNN trains VGG16 3× faster, tests 10× 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.
%0 Journal Article
%1 noauthororeditor
%A Girshick, Ross
%D 2015
%J CoRR
%K cnn detection fast image object r-cnn thema thema:RCNN
%T Fast R-CNN
%U http://www.cv-foundation.org/openaccess/content_iccv_2015/papers/Girshick_Fast_R-CNN_ICCV_2015_paper.pdf
%V abs/1504.08083
%X 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 9× faster than R-CNN, is 213× faster at test-time, and achieves a higher mAP on PASCAL VOC 2012. Compared to SPPnet, Fast R-CNN trains VGG16 3× faster, tests 10× 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.
@article{noauthororeditor,
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 9× faster than R-CNN, is 213× faster at test-time, and achieves a higher mAP on PASCAL VOC 2012. Compared to SPPnet, Fast R-CNN trains VGG16 3× faster, tests 10× 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.},
added-at = {2017-04-19T21:06:53.000+0200},
author = {Girshick, Ross},
biburl = {https://www.bibsonomy.org/bibtex/29e600f207cdf002feee65c43d18a98dd/lautenschlager},
interhash = {51c671e48116130c4810b16bc8403b69},
intrahash = {9e600f207cdf002feee65c43d18a98dd},
journal = {CoRR},
keywords = {cnn detection fast image object r-cnn thema thema:RCNN},
timestamp = {2017-04-25T13:24:08.000+0200},
title = {Fast R-CNN},
url = {http://www.cv-foundation.org/openaccess/content_iccv_2015/papers/Girshick_Fast_R-CNN_ICCV_2015_paper.pdf},
volume = {abs/1504.08083},
year = 2015
}