R. Girshick. (2015)cite arxiv:1504.08083Comment: To appear in ICCV 2015.
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.
%0 Generic
%1 girshick2015
%A Girshick, Ross
%D 2015
%K cs.CV
%T Fast R-CNN
%U http://arxiv.org/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 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.
@misc{girshick2015,
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.},
added-at = {2021-02-09T04:17:36.000+0100},
author = {Girshick, Ross},
biburl = {https://www.bibsonomy.org/bibtex/249692f92da388790a9018d7faed9ccf3/aerover},
description = {[1504.08083] Fast R-CNN},
interhash = {51c671e48116130c4810b16bc8403b69},
intrahash = {49692f92da388790a9018d7faed9ccf3},
keywords = {cs.CV},
note = {cite arxiv:1504.08083Comment: To appear in ICCV 2015},
timestamp = {2021-02-09T04:17:36.000+0100},
title = {Fast R-CNN},
url = {http://arxiv.org/abs/1504.08083},
year = 2015
}