实时目标检测--Pelee: A Real-Time Object Detection System on Mobile Devices

Pelee: A Real-Time Object Detection System on Mobile Devices
ICLR 2018
Code: https://github.com/Robert-JunWang/Pelee

CNN模型在嵌入式设备中运行成为一种趋势，为此提出了一些模型如 MobileNet, ShuffleNet, and NASNet-A，他们主要依赖于 depthwise separable convolution ，但是在当前主要深度学习框架中，depthwise separable convolution 没有被高效的实现， lacks efficient implementation。这里我们提出了一个网络结构 PeleeNet，它基于 conventional convolution。

PeleeNet 主要特征模块：
1）Two-Way Dense Layer ： to get different scales of receptive fields
2）Stem Block：This stem block can effectively improve the feature expression ability without adding computational cost too much

3） Dynamic Number of Channels in Bottleneck Layer 根据输入形状动态决定通道数目， this method can save up to
28.5% of the computational cost with a small impact on accuracy

4） Transition Layer without Compression 我们的实验显示在 transition layers 中进行压缩会伤害 feature expression

5）Composite Function 为了提速，我们使用 post-activation (Convolution - Batch Normalization - Relu
For post-activation, all batch normalization layers can be merged with convolution layer at the inference stage, which can accelerate the speed greatly.

针对目标检测问题，我们将 PeleeNet 嵌入到 SSD 中，主要注意点如下：
1） Feature Map Selection：我们选择了 5 scale feature maps (19 x 19, 10 x 10, 5 x 5, 3 x 3, and 1 x 1). 为了节约计算，我们没有选择 38 x 38 feature map
2）Residual Prediction Block ：加了一个 a residual block (ResBlock) before conducting prediction.
3） Small Convolutional Kernel for Prediction：1x1 kernels reduce the computational cost by 21.5%

Overview of PeleeNet architecture

实时目标检测--Pelee: A Real-Time Object Detection System on Mobile Devices相关推荐

感知算法论文（二）Pelee: A Real-Time Object Detection System on Mobile Devices（2018）译文
摘要目前在计算能力和内存资源有限的移动设备上运行卷积神经网络模型的需求越来越大,这样一来就刺激了对高效模型的设计和研究. MobileNet.ShuffleNet和MobileNetV2等高效的网络 ...
目标检测-Oriented RepPoints for Aerial Object Detection(CVPR 2022)
目标检测-Oriented RepPoints for Aerial Object Detection(CVPR 2022) 论文地址:Oriented RepPoints for Aerial Ob ...
【开放域目标检测】一：Open-Vocabulary Object Detection Using Captions论文讲解
出发点是制定一种更加通用的目标检测问题,目的是借助于大量的image-caption数据来覆盖更多的object concept,使得object detection不再受限于带标注数据的少数类别,从 ...
深度学习之目标检测（Swin Transformer for Object Detection）
目录 1.MMdetection系列版本编辑 2. MMDetection和MMCV兼容版本 3.Installation(Linux系统环境安装) 3.1 搭建基本环境 3.2 安装mmcv-fu ...
点云 3D 目标检测 - CenterPoint：Center-based 3D Object Detection and Tracking（CVPR 2021）
点云 3D 目标检测 - CenterPoint: Center-based 3D Object Detection and Tracking - 基于中心的3D目标检测与跟踪(CVPR 2021) ...
多尺度目标检测--Scale-Aware Trident Networks for Object Detection
Scale-Aware Trident Networks for Object Detection https://github.com/TuSimple/simpledet/tree/master/ ...
目标检测--Focal Loss for Dense Object Detection
Focal Loss for Dense Object Detection ICCV2017 https://arxiv.org/abs/1708.02002 本文算是用简单的方法解决复杂的问题了,好 ...
目标检测--Feature Pyramid Networks for Object Detection
CVPR2017 Feature Pyramid Networks for Object Detection https://arxiv.org/abs/1612.03144 Code will be ...
目标检测--Wide-Residual-Inception Networks for Real-time Object Detection
本文主要是在 Residual 和 Inception 基础上构建新的模型,实现实时物体检测.构建的新模型特色是占用内存少,计算量小.新网络命名为 wide-residual-inception (W ...

实时目标检测--Pelee: A Real-Time Object Detection System on Mobile Devices

实时目标检测--Pelee: A Real-Time Object Detection System on Mobile Devices相关推荐

最新文章

热门文章