ChainerCV: a Library for Deep Learning in Computer Vision
Y. Niitani, T. Ogawa, S. Saito, and M. Saito. (2017)cite arxiv:1708.08169Comment: Accepted to ACM MM 2017 Open Source Software Competition.
Abstract
Despite significant progress of deep learning in the field of computer
vision, there has not been a software library that covers these methods in a
unifying manner. We introduce ChainerCV, a software library that is intended to
fill this gap. ChainerCV supports numerous neural network models as well as
software components needed to conduct research in computer vision. These
implementations emphasize simplicity, flexibility and good software engineering
practices. The library is designed to perform on par with the results reported
in published papers and its tools can be used as a baseline for future research
in computer vision. Our implementation includes sophisticated models like
Faster R-CNN and SSD, and covers tasks such as object detection and semantic
segmentation.
Description
[1708.08169] ChainerCV: a Library for Deep Learning in Computer Vision
%0 Generic
%1 niitani2017chainercv
%A Niitani, Yusuke
%A Ogawa, Toru
%A Saito, Shunta
%A Saito, Masaki
%D 2017
%K 2017 arxiv computer-vision deep-learning library paper
%T ChainerCV: a Library for Deep Learning in Computer Vision
%U http://arxiv.org/abs/1708.08169
%X Despite significant progress of deep learning in the field of computer
vision, there has not been a software library that covers these methods in a
unifying manner. We introduce ChainerCV, a software library that is intended to
fill this gap. ChainerCV supports numerous neural network models as well as
software components needed to conduct research in computer vision. These
implementations emphasize simplicity, flexibility and good software engineering
practices. The library is designed to perform on par with the results reported
in published papers and its tools can be used as a baseline for future research
in computer vision. Our implementation includes sophisticated models like
Faster R-CNN and SSD, and covers tasks such as object detection and semantic
segmentation.
@misc{niitani2017chainercv,
abstract = {Despite significant progress of deep learning in the field of computer
vision, there has not been a software library that covers these methods in a
unifying manner. We introduce ChainerCV, a software library that is intended to
fill this gap. ChainerCV supports numerous neural network models as well as
software components needed to conduct research in computer vision. These
implementations emphasize simplicity, flexibility and good software engineering
practices. The library is designed to perform on par with the results reported
in published papers and its tools can be used as a baseline for future research
in computer vision. Our implementation includes sophisticated models like
Faster R-CNN and SSD, and covers tasks such as object detection and semantic
segmentation.},
added-at = {2018-06-25T09:36:13.000+0200},
author = {Niitani, Yusuke and Ogawa, Toru and Saito, Shunta and Saito, Masaki},
biburl = {https://www.bibsonomy.org/bibtex/2a2cc663b433302d985942fd7eced1ff7/achakraborty},
description = {[1708.08169] ChainerCV: a Library for Deep Learning in Computer Vision},
interhash = {e1acefea21850a71115cbcefbc304ebd},
intrahash = {a2cc663b433302d985942fd7eced1ff7},
keywords = {2017 arxiv computer-vision deep-learning library paper},
note = {cite arxiv:1708.08169Comment: Accepted to ACM MM 2017 Open Source Software Competition},
timestamp = {2018-06-25T09:36:13.000+0200},
title = {ChainerCV: a Library for Deep Learning in Computer Vision},
url = {http://arxiv.org/abs/1708.08169},
year = 2017
}