没有合适的资源?快使用搜索试试~ 我知道了~
Faster_R-CNN中英文对照翻译1
需积分: 0 0 下载量 127 浏览量
2022-08-03
20:06:54
上传
评论
收藏 1.48MB PDF 举报
温馨提示
试读
71页
摘要最先进的目标检测网络依靠 region proposal 算法来推理检测目标的位置。SPPnet[1]和 Fast R-CNN[2]等类似的研究已经减少了这
资源详情
资源评论
资源推荐
Faster R-CNN: Towards Real-Time Object Detection with
Region Proposal Networks
Faster R-CNN:通过 Region Proposal 网络实现实时目标检
测
Shaoqing Ren, Kaiming He, Ross Girshick, and Jian Sun
Abstract
State-of-the-art object detection networks depend on region proposal
algorithms to hypothesize object locations. Advances like SPPnet [1] and
Fast R-CNN [2] have reduced the running time of these detection networks,
exposing region proposal computation as a bottleneck. In this work, we
introduce a Region Proposal Network (RPN) that shares full-image
convolutional features with the detection network, thus enabling nearly
cost-free region proposals. An RPN is a fully convolutional network that
simultaneously predicts object bounds and objectness scores at each
position. The RPN is trained end-to-end to generate high-quality region
proposals, which are used by Fast R-CNN for detection. We further merge
RPN and Fast R-CNN into a single network by sharing their convolutional
features——using the recently popular terminology of neural networks
with “attention” mechanisms, the RPN component tells the unified network
where to look. For the very deep VGG-16 model [3], our detection system
has a frame rate of 5fps (including all steps) on a GPU, while achieving
state-of-the-art object detection accuracy on PASCAL VOC 2007, 2012,
and MS COCO datasets with only 300 proposals per image. In ILSVRC
and COCO 2015 competitions, Faster R-CNN and RPN are the foundations
of the 1st-place winning entries in several tracks. Code has been made
publicly available.
Index Terms
Object Detection, Region Proposal, Convolutional Neural Network.
摘要
最先进的目标检测网络依靠 region proposal 算法来推理检测目标
的位置。SPPnet[1]和 Fast R-CNN[2]等类似的研究已经减少了这些检
测网络的运行时间,使得 region proposal 计算成为一个瓶颈。在这项
工作中,我们引入了一个 region proposal 网络(RPN),该网络与检
测网络 共享 整个图像的卷积 特征 , 从而使近 乎零成 本的 region
proposal 成为可能。RPN 是一个全卷积网络,可以同时在每个位置预
测目标边界和目标分数。RPN 经过端到端的训练,可以生成高质量的
region proposal,并使用 Fast R-CNN 完成检测。我们将 RPN 和 Fast
R-CNN 通过共享卷积特征进一步合并为一个单一的网络——使用最
近流行的具有“注意力”机制的神经网络术语,RPN 组件告诉统一网络
在哪里寻找。对于非常深的 VGG-16 模型[3],我们的检测系统在 GPU
上的帧率为 5fps(包括所有步骤),同时在 PASCAL VOC 2007、2012
和 MS COCO 数据集上达到了目前最好的目标检测精度,每个图像只
有 300 个 proposals。在 ILSVRC 和 COCO 2015 竞赛中,Faster R-CNN
和 RPN 是多个比赛中获得第一名的基础。代码已公开。
关键字
目标检测,Region Proposal,卷积神经网络
1. Introduction
Recent advances in object detection are driven by the success of
region proposal methods (e.g., [4]) and region-based convolutional neural
networks (R-CNNs) [5]. Although region-based CNNs were
computationally expensive as originally developed in [5], their cost has
been drastically reduced thanks to sharing convolutions across proposals
[1], [2]. The latest incarnation, Fast R-CNN [2], achieves near real-time
rates using very deep networks [3], when ignoring the time spent on region
proposals. Now, proposals are the test-time computational bottleneck in
state-of-the-art detection systems.
1. 引言
目标检测的最新进展是由 region proposal 方法(例如[4])和基于
区域的卷积神经网络(R-CNN)[5]的成功驱动的。尽管在[5]中最初开
发的基于区域的 CNN 计算代价很大,但是由于在各种 proposals 中共
享卷积,所以其成本已经大大降低了[1],[2]。忽略花费在 region
proposals 上的时间,最新版本 Fast R-CNN[2]利用非常深的网络[3]实
现了接近实时的速率。现在,proposals 是最新的检测系统中测试时间
的计算瓶颈。
Region proposal methods typically rely on inexpensive features and
economical inference schemes. Selective Search [4], one of the most
popular methods, greedily merges superpixels based on engineered low-
level features. Yet when compared to efficient detection networks [2],
Selective Search is an order of magnitude slower, at 2 seconds per image
in a CPU implementation. EdgeBoxes [6] currently provides the best
tradeoff between proposal quality and speed, at 0.2 seconds per image.
Nevertheless, the region proposal step still consumes as much running time
as the detection network.
Region proposal 方法通常依赖廉价的特征和简练的推断方案。
Selective Search [4]是最流行的方法之一,它贪婪地合并基于设计的低
级特征的超级像素。然而,与有效的检测网络[2]相比,Selective Search
速度慢了一个数量级,在 CPU 实现中每张图像的时间为 2 秒。
EdgeBoxes[6]目前提出了在 proposal 质量和速度之间的最佳权衡,每
张图像 0.2 秒。尽管如此,region proposal 步骤仍然像检测网络那样
消耗同样多的运行时间。
One may note that fast region-based CNNs take advantage of GPUs,
while the region proposal methods used in research are implemented on the
CPU, making such runtime comparisons inequitable. An obvious way to
accelerate proposal computation is to re-implement it for the GPU. This
may be an effective engineering solution, but re-implementation ignores
the down-stream detection network and therefore misses important
opportunities for sharing computation.
有人可能会注意到,基于区域的快速 CNN 利用 GPU,而在研究
中使用的 region proposal 方法在 CPU 上实现,使得运行时间比较不
公平。加速 region proposal 计算的一个显而易见的方法是将其在 GPU
上重新实现。这可能是一个有效的工程解决方案,但重新实现忽略了
下游检测网络,因此错过了共享计算的重要机会。
In this paper, we show that an algorithmic change——computing
proposals with a deep convolutional neural network——leads to an elegant
and effective solution where proposal computation is nearly cost-free given
the detection network’s computation. To this end, we introduce novel
Region Proposal Networks (RPNs) that share convolutional layers with
state-of-the-art object detection networks [1], [2]. By sharing convolutions
at test-time, the marginal cost for computing proposals is small (e.g., 10ms
per image).
在本文中,我们展示了算法的变化——用深度卷积神经网络计算
region proposal——获得了一个优雅和有效的解决方案,其中在给定
检测网络计算的情况下 region proposal 计算接近零成本。为此,我们
引入了新的 region proposal 网络(RPN),它们共享最先进目标检测
网络的卷积层[1],[2]。通过在测试时共享卷积,计算 region proposal
的边际成本很小(例如,每张图像仅需 10ms)。
Our observation is that the convolutional feature maps used by region-
based detectors, like Fast R-CNN, can also be used for generating region
proposals. On top of these convolutional features, we construct an RPN by
剩余70页未读,继续阅读
乖巧是我姓名
- 粉丝: 26
- 资源: 344
上传资源 快速赚钱
- 我的内容管理 展开
- 我的资源 快来上传第一个资源
- 我的收益 登录查看自己的收益
- 我的积分 登录查看自己的积分
- 我的C币 登录后查看C币余额
- 我的收藏
- 我的下载
- 下载帮助
安全验证
文档复制为VIP权益,开通VIP直接复制
信息提交成功
评论0