The ability to detect small objects and the speed of the object detector are
very important for the application of autonomous driving, and in this paper, we
propose an effective yet efficient one-stage detector, which gained the second
place in the Road Object Detection competition of CVPR2018 workshop - Workshop
of Autonomous Driving(WAD). The proposed detector inherits the architecture of
SSD and introduces a novel Comprehensive Feature Enhancement(CFE) module into
it. Experimental results on this competition dataset as well as the MSCOCO
dataset demonstrate that the proposed detector (named CFENet) performs much
better than the original SSD and the state-of-the-art method RefineDet
especially for small objects, while keeping high efficiency close to the
original SSD. Specifically, the single scale version of the proposed detector
can run at the speed of 21 fps, while the multi-scale version with larger input
size achieves the mAP 29.69, ranking second on the leaderboard
%0 Generic
%1 citeulike:14620629
%A xxx,
%D 2018
%K backbone detection ssd
%T CFENet: An Accurate and Efficient Single-Shot Object Detector for Autonomous Driving
%U http://arxiv.org/abs/1806.09790
%X The ability to detect small objects and the speed of the object detector are
very important for the application of autonomous driving, and in this paper, we
propose an effective yet efficient one-stage detector, which gained the second
place in the Road Object Detection competition of CVPR2018 workshop - Workshop
of Autonomous Driving(WAD). The proposed detector inherits the architecture of
SSD and introduces a novel Comprehensive Feature Enhancement(CFE) module into
it. Experimental results on this competition dataset as well as the MSCOCO
dataset demonstrate that the proposed detector (named CFENet) performs much
better than the original SSD and the state-of-the-art method RefineDet
especially for small objects, while keeping high efficiency close to the
original SSD. Specifically, the single scale version of the proposed detector
can run at the speed of 21 fps, while the multi-scale version with larger input
size achieves the mAP 29.69, ranking second on the leaderboard
@misc{citeulike:14620629,
abstract = {{The ability to detect small objects and the speed of the object detector are
very important for the application of autonomous driving, and in this paper, we
propose an effective yet efficient one-stage detector, which gained the second
place in the Road Object Detection competition of CVPR2018 workshop - Workshop
of Autonomous Driving(WAD). The proposed detector inherits the architecture of
SSD and introduces a novel Comprehensive Feature Enhancement(CFE) module into
it. Experimental results on this competition dataset as well as the MSCOCO
dataset demonstrate that the proposed detector (named CFENet) performs much
better than the original SSD and the state-of-the-art method RefineDet
especially for small objects, while keeping high efficiency close to the
original SSD. Specifically, the single scale version of the proposed detector
can run at the speed of 21 fps, while the multi-scale version with larger input
size achieves the mAP 29.69, ranking second on the leaderboard}},
added-at = {2019-02-27T22:23:29.000+0100},
archiveprefix = {arXiv},
author = {xxx},
biburl = {https://www.bibsonomy.org/bibtex/22a7e60d4011fed3653d3bb3d8b2aada3/nmatsuk},
citeulike-article-id = {14620629},
citeulike-linkout-0 = {http://arxiv.org/abs/1806.09790},
citeulike-linkout-1 = {http://arxiv.org/pdf/1806.09790},
day = 26,
eprint = {1806.09790},
interhash = {13249eb30df80ec3292d260501a29127},
intrahash = {2a7e60d4011fed3653d3bb3d8b2aada3},
keywords = {backbone detection ssd},
month = jun,
posted-at = {2018-08-01 08:13:44},
priority = {0},
timestamp = {2019-02-27T22:23:29.000+0100},
title = {{CFENet: An Accurate and Efficient Single-Shot Object Detector for Autonomous Driving}},
url = {http://arxiv.org/abs/1806.09790},
year = 2018
}