<noscript id="8ssuq"></noscript>
<td id="8ssuq"><rt id="8ssuq"></rt></td>
  • <li id="8ssuq"></li>
    <table id="8ssuq"></table>
  • [论文理解] Receptive Field Block Net for Accurate and Fast Object Detection

    Receptive Field Block Net for Accurate and Fast Object Detection

    简介

    本文在SSD基础上提出了RFB Module,利用神经科学的先验知识来解释这种效果提升。本质上是设计一种新的结构来提升感受野,并表明了人类视网膜的感受野有一个特点,离视线中心越远,其感受野是越大的,越靠近视线中间,感受野越小。基于此,本文提出的RFB Module就是来模拟人类这种视觉特点的。

    分享图片

    RFB Module

    结构如下图所示。

    分享图片

    为什么要用空洞卷积呢?

    首先要提高感受野,直观的想法就是要么加深层数,要么使用更大的卷积核,要么就是卷积之前使用pooling。加深层数网络参数就会变多,没法完成轻量级的任务;更大的卷积核一样参数也会变多;pooling虽然不会增加参数,但是会使信息损失,不利于后面层的信息传递。所以作者这里很自然的想到用空洞卷积,既不增加参数量,又能够提高感受野。

    为什么要用这种多分支结构呢?

    这是为了捕捉不同感受野的信息,如前面提到的,人类视野的特点就是距视野中心距离不同感受野不同,所以使用多分支结构,每个分支捕捉一种感受野,最后通过concat来融合感受野信息,就能达到模拟人类视觉的效果了。作者这里也给了一张图来说明。

    分享图片

    为什么要提出两种版本的RFB呢?

    左边的结构是原始的RFB,右边的结构相比RFB把3×3的conv变成了两个1×3和3×1的分支,一是减少了参数量,二是增加了更小的感受野,这样也是在模拟人类视觉系统,捕捉更小的感受野。

    网络结构

    整体网络结构如下所示,很好理解。

    分享图片

    前面就是vgg19,然后从中间的层分出6个预测分支,比较好理解没啥记的。

    代码复现

    import torch
    import torch.nn as nn
    import torch.nn.functional as F
    from torchsummary import summary
    class RFBModule(nn.Module):
        def __init__(self,out,stride = 1):
            super(RFBModule,self).__init__()
            self.s1 = nn.Sequential(
                nn.Conv2d(out,out,kernel_size = 1),
                nn.Conv2d(out,out,kernel_size=3,dilation = 1,padding = 1,stride = stride)
            )
            self.s2 = nn.Sequential(
                nn.Conv2d(out,out,kernel_size =1),
                nn.Conv2d(out,out,kernel_size=3,padding = 1),
                nn.Conv2d(out,out,kernel_size=3,dilation = 3,padding = 3,stride = stride)
            )
            self.s3 = nn.Sequential(
                nn.Conv2d(out,out,kernel_size =1),
                nn.Conv2d(out,out,kernel_size = 5,padding =2),
                nn.Conv2d(out,out,kernel_size=3,dilation=5,padding = 5,stride = stride)
            )
            self.shortcut = nn.Conv2d(out,out,kernel_size = 1,stride = stride)
            self.conv1x1 = nn.Conv2d(out*3,out,kernel_size =1)
        def forward(self,x):
            s1 = self.s1(x)
            s2 = self.s2(x)
            s3 = self.s3(x)
            #print(s1.size(),s2.size(),s3.size())
            mix = torch.cat([s1,s2,s3],dim = 1)
            mix = self.conv1x1(mix)
            shortcut = self.shortcut(x)
            return mix + shortcut
    class RFBsModule(nn.Module):
        def __init__(self,out,stride = 1):
            super(RFBsModule,self).__init__()
            self.s1 = nn.Sequential(
                nn.Conv2d(out,out,kernel_size = 1),
                nn.Conv2d(out,out,kernel_size=3,dilation = 1,padding = 1,stride = stride)
            )
            self.s2 = nn.Sequential(
                nn.Conv2d(out,out,kernel_size =1),
                nn.Conv2d(out,out,kernel_size=(1,3),padding = (0,1)),
                nn.Conv2d(out,out,kernel_size=3,dilation = 3,padding = 3,stride = stride)
            )
            self.s3 = nn.Sequential(
                nn.Conv2d(out,out,kernel_size =1),
                nn.Conv2d(out,out,kernel_size = (3,1),padding =(1,0)),
                nn.Conv2d(out,out,kernel_size=3,dilation=3,padding = 3,stride = stride)
            )
            self.s4 = nn.Sequential(
                nn.Conv2d(out,out,kernel_size =1),
                nn.Conv2d(out,out,kernel_size=3),
                nn.Conv2d(out,out,kernel_size = 3,dilation = 5,stride = stride,padding = 6)
            )
            self.shortcut = nn.Conv2d(out,out,kernel_size = 1,stride = stride)
            self.conv1x1 = nn.Conv2d(out*4,out,kernel_size =1)
        def forward(self,x):
            s1 = self.s1(x)
            s2 = self.s2(x)
            s3 = self.s3(x)
            s4 = self.s4(x)
            #print(s1.size(),s2.size(),s3.size(),s4.size())
            #print(s1.size(),s2.size(),s3.size())
            mix = torch.cat([s1,s2,s3,s4],dim = 1)
            mix = self.conv1x1(mix)
            shortcut = self.shortcut(x)
            return mix + shortcut
    
    class RFBNet(nn.Module):
        def __init__(self):
            super(RFBNet,self).__init__()
            self.feature_1 = nn.Sequential(
                nn.Conv2d(3,64,kernel_size = 3,padding = 1),
                nn.ReLU(),
                nn.Conv2d(64,64,kernel_size=3,padding=1),
                nn.ReLU(),
                nn.MaxPool2d(kernel_size = 2,stride = 2),
                nn.Conv2d(64,128,kernel_size = 3,padding = 1),
                nn.ReLU(),
                nn.Conv2d(128,128,kernel_size=3,padding=1),
                nn.ReLU(),
                nn.MaxPool2d(kernel_size = 2,stride = 2),
                nn.Conv2d(128,256,kernel_size = 3,padding = 1),
                nn.ReLU(),
                nn.Conv2d(256,256,kernel_size=3,padding=1),
                nn.ReLU(),
                nn.Conv2d(256,256,kernel_size=3,padding=1),
                nn.ReLU(),
                nn.MaxPool2d(kernel_size = 2,stride = 2),
                nn.Conv2d(256,512,kernel_size = 3,padding = 1),
                nn.ReLU(),
                nn.Conv2d(512,512,kernel_size=3,padding=1),
                nn.ReLU(),
                nn.Conv2d(512,512,kernel_size=3,padding=1),
                nn.ReLU(),
            )
            
            self.feature_2 = nn.Sequential(
                nn.MaxPool2d(kernel_size = 2,stride = 2),
                nn.Conv2d(512,512,kernel_size = 3,padding = 1),
                nn.ReLU(),
                nn.Conv2d(512,512,kernel_size=3,padding=1),
                nn.ReLU(),
                nn.Conv2d(512,512,kernel_size=3,padding=1),
                nn.ReLU(),
            )
            self.pre = nn.Conv2d(512,64,kernel_size = 1)
            self.fc = nn.Conv2d(512,64,kernel_size = 1)
            self.det1 = RFBsModule(out = 64,stride = 1)
            self.det2 = RFBModule(out = 64,stride = 1)
            self.det3 = RFBModule(out = 64,stride = 2)
            self.det4 = RFBModule(out = 64,stride = 2)
            self.det5 = nn.Conv2d(64,64,kernel_size = 3)
            self.det6 = nn.Conv2d(64,64,kernel_size=3)
            
        def forward(self,x):
            x = self.feature_1(x)
            det1 = self.det1(self.fc(x))
            x = self.feature_2(x)
            x = self.pre(x)
            det2 = self.det2(x)
            det3 = self.det3(det2)
            det4 = self.det4(det3)
            det5 = self.det5(det4)
            det6 = self.det6(det5)
            det1 = det1.permute(0,2,3,1).contiguous().view(x.size(0),-1,64)
            det2 = det2.permute(0,2,3,1).contiguous().view(x.size(0),-1,64)
            det3 = det3.permute(0,2,3,1).contiguous().view(x.size(0),-1,64)
            det4 = det4.permute(0,2,3,1).contiguous().view(x.size(0),-1,64)
            det5 = det5.permute(0,2,3,1).contiguous().view(x.size(0),-1,64)
            det6 = det6.permute(0,2,3,1).contiguous().view(x.size(0),-1,64)
                
                
                
            return torch.cat([det1,det2,det3,det4,det5,det6],dim = 1)
    
    if __name__ == "__main__":
        net = RFBNet()
        x = torch.randn(2,3,300,300)
        summary(net,(3,300,300),device = "cpu")
        print(net(x).size())

    论文原文:https://arxiv.org/pdf/1711.07767.pdf

    相关文章
    天空彩票平特精选图 绥宁县| 镇远县| 临洮县| 土默特右旗| 原平市| 德兴市| 正宁县| 中阳县| 萍乡市| 湄潭县| 长垣县| 威海市| 横峰县| 阿尔山市| 杭锦旗| 新营市| 安乡县| 锡林郭勒盟| 濉溪县| 乐山市| 常山县| 台东市| 堆龙德庆县| 渑池县| 丰都县| 且末县| 林芝县| 衡东县| 邻水| 石屏县| 江城| 师宗县| 炉霍县| 客服| 汤阴县| 宁晋县| 南木林县| 清徐县| 施甸县| 永平县| 二连浩特市| 蕉岭县| 安平县| 瑞丽市| 桃园市| 合作市| 山西省| 吴堡县| 工布江达县| 宁武县| 宜兰县| 康乐县| 宁德市| 延边| 绥中县| 冕宁县| 准格尔旗| 团风县| 金山区| 榆树市| 和林格尔县| 阿拉善盟| 开封县| 安吉县| 石屏县| 高安市| 贺州市| 衡山县| 锡林浩特市| 吉隆县| 安溪县| 葵青区| 淮南市| 延津县| 墨竹工卡县| 永吉县| 西乌珠穆沁旗| 高要市| 应用必备| 汾阳市| 娱乐| 黄山市| 威宁| 凯里市| 赤峰市| 安塞县| 桦甸市| http://www.hsourcer888.com http://hstickr888.com http://m.flsheeto888.com http://www.htruer888.com http://www.hwallpaperr888.com http://wap.hvisar888.com http://www.hspyr888.com http://m.gwvisitl888.com http://hstockr888.com http://www.hslider888.com http://htowerr888.com