有什么问题可以加作者微信讨论,cyx645016617 上千人的粉丝群已经成立,氛围超好。为大家提供一个遇到问题有可能得到答案的平台。
0 概述
- 论文名称:“Richer Convolutional Features for Edge Detection”
- 论文链接:https://openaccess.thecvf.com/content_cvpr_2017/papers/Liu_Richer_Convolutional_Features_CVPR_2017_paper.pdf
- 缩写:RCF
这一篇文论在我看来,是CVPR 2015年 HED网络(holistically-nested edge detection)的一个改进,RCF的论文中也基本上和HED网络处处对比。
在上一篇文章中,我们依稀记得HED模型有这样一个图:
其中有HED的五个side output的特征图,下图是RCF论文中的图:
我们从这两个图的区别中来认识RCF相比HED的改进,大家可以看一看图。
揭晓答案:
- HED是豹子的图片,但是RCF是两只小鸟的图片(手动狗头)
- HED中的是side output的输出的特征图,而RCF中是conv3_1,conv3_2,这意味着RCF似乎把每一个卷积之后的输出的特征图都作为了一个side output。
没错,HED选取了5个side output,每一个side output都是池化层之前的卷积层输出的特征图;而RCF则对每一次卷积的输出特征图都作为side output,换句话说 最终的side output中,同一尺寸的输出可能不止一个。
如果还没有理解,请看下面章节,模型结构。
1 模型结构
RCF的backbone是VGG模型:
从图中可以看到:
- 主干网络上分成state1到5,stage1有两个卷积层,stage2有两个卷积层,总共有13个卷积层,每一次卷积输出的图像,再额外接入一个1x1的卷积,来降低通道数,所以可以看到,图中有大量的21通道的卷积层。
- 同一个stage的21通道的特征图经过通道拼接,变成42通道或者是63通道的特征图,然后再经过一个1x1的卷积层,来把通道数降低成1,再进过sigmoid层,输出的结果就是一个RCF模型中的side output了
2 损失函数
这里的损失函数其实和HED来说类似:
首先整体来看,损失函数依然使用二值交叉熵
其中(|Y^-|) 表示 negative的像素值,(|Y^+|)表示positive的像素值。一般来说轮廓检测任务中,positive的样本应该是较少的,因此(alpha)的值较小,因此损失函数中第一行,y=0也就是计算非轮廓部分的损失的时候,就会增加一个较小的权重,来避免类别不均衡的问题。
损失函数中有两个常数,一个是(lambda),这个就是权重常数,默认为1.1;另外一个是(eta)。论文中的描述为:
Edge datasets in this community are usually labeled by several annotators using their knowledge about the presences of objects and object parts. Though humans vary in cognition, these human-labeled edges for the same image share high consistency. For each image, we average all the ground truth to generate an edge probability map, which ranges from 0 to 1. Here, 0 means no annotator labeled at this pixel, and 1 means all annotators have labeled at this pixel. We consider the pixels with edge probability higher than η as positive samples and the pixels with edge probability equal to 0 as negative samples. Otherwise, if a pixel is marked by fewer than η of the annotators, this pixel may be semantically controversial to be an edge point. Thus, whether regarding it as positive or negative samples may confuse networks. So we ignore pixels in this category.
大意就是:一般对数据集进行标注,是有多个人来完成的。不同的人虽然有不同的意识,但是他们对于同一个图片的轮廓标注往往是具有一致性。RCF网络最后的输出,是由5个side output融合产生的,因此你这个RCF的输出也应该把大于(eta)的考虑为positive,然后小于(eta)的考虑为negative。 其实这一点我自己在复现的时候并没有考虑,我看网上的github和官方的代码中,都没有考虑这个,都是直接交叉熵。。。我这就也就多此一举的讲解一下论文中的这个(eta)的含义
3 pytorch部分代码
对于这个RCF论文来说,关键就是一个模型的构建,另外一个就是损失函数的构建,这里放出这两部分的代码,来帮助大家更好的理解上面的内容。
3.1 模型部分
下面的代码在上采样部分的写法比较老旧,因为这个网上找来的pytorch版本估计比较老,当时还没有Conv2DTrans这样的函数封装,但是不妨碍大家通过代码来学习RCF。
class RCF(nn.Module):
def __init__(self):
super(RCF, self).__init__()
#lr 1 2 decay 1 0
self.conv1_1 = nn.Conv2d(3, 64, 3, padding=1)
self.conv1_2 = nn.Conv2d(64, 64, 3, padding=1)
self.conv2_1 = nn.Conv2d(64, 128, 3, padding=1)
self.conv2_2 = nn.Conv2d(128, 128, 3, padding=1)
self.conv3_1 = nn.Conv2d(128, 256, 3, padding=1)
self.conv3_2 = nn.Conv2d(256, 256, 3, padding=1)
self.conv3_3 = nn.Conv2d(256, 256, 3, padding=1)
self.conv4_1 = nn.Conv2d(256, 512, 3, padding=1)
self.conv4_2 = nn.Conv2d(512, 512, 3, padding=1)
self.conv4_3 = nn.Conv2d(512, 512, 3, padding=1)
self.conv5_1 = nn.Conv2d(512, 512, kernel_size=3,
stride=1, padding=2, dilation=2)
self.conv5_2 = nn.Conv2d(512, 512, kernel_size=3,
stride=1, padding=2, dilation=2)
self.conv5_3 = nn.Conv2d(512, 512, kernel_size=3,
stride=1, padding=2, dilation=2)
self.relu = nn.ReLU()
self.maxpool = nn.MaxPool2d(2, stride=2, ceil_mode=True)
self.maxpool4 = nn.MaxPool2d(2, stride=1, ceil_mode=True)
#lr 0.1 0.2 decay 1 0
self.conv1_1_down = nn.Conv2d(64, 21, 1, padding=0)
self.conv1_2_down = nn.Conv2d(64, 21, 1, padding=0)
self.conv2_1_down = nn.Conv2d(128, 21, 1, padding=0)
self.conv2_2_down = nn.Conv2d(128, 21, 1, padding=0)
self.conv3_1_down = nn.Conv2d(256, 21, 1, padding=0)
self.conv3_2_down = nn.Conv2d(256, 21, 1, padding=0)
self.conv3_3_down = nn.Conv2d(256, 21, 1, padding=0)
self.conv4_1_down = nn.Conv2d(512, 21, 1, padding=0)
self.conv4_2_down = nn.Conv2d(512, 21, 1, padding=0)
self.conv4_3_down = nn.Conv2d(512, 21, 1, padding=0)
self.conv5_1_down = nn.Conv2d(512, 21, 1, padding=0)
self.conv5_2_down = nn.Conv2d(512, 21, 1, padding=0)
self.conv5_3_down = nn.Conv2d(512, 21, 1, padding=0)
#lr 0.01 0.02 decay 1 0
self.score_dsn1 = nn.Conv2d(21, 1, 1)
self.score_dsn2 = nn.Conv2d(21, 1, 1)
self.score_dsn3 = nn.Conv2d(21, 1, 1)
self.score_dsn4 = nn.Conv2d(21, 1, 1)
self.score_dsn5 = nn.Conv2d(21, 1, 1)
#lr 0.001 0.002 decay 1 0
self.score_final = nn.Conv2d(5, 1, 1)
def forward(self, x):
# VGG
img_H, img_W = x.shape[2], x.shape[3]
conv1_1 = self.relu(self.conv1_1(x))
conv1_2 = self.relu(self.conv1_2(conv1_1))
pool1 = self.maxpool(conv1_2)
conv2_1 = self.relu(self.conv2_1(pool1))
conv2_2 = self.relu(self.conv2_2(conv2_1))
pool2 = self.maxpool(conv2_2)
conv3_1 = self.relu(self.conv3_1(pool2))
conv3_2 = self.relu(self.conv3_2(conv3_1))
conv3_3 = self.relu(self.conv3_3(conv3_2))
pool3 = self.maxpool(conv3_3)
conv4_1 = self.relu(self.conv4_1(pool3))
conv4_2 = self.relu(self.conv4_2(conv4_1))
conv4_3 = self.relu(self.conv4_3(conv4_2))
pool4 = self.maxpool4(conv4_3)
conv5_1 = self.relu(self.conv5_1(pool4))
conv5_2 = self.relu(self.conv5_2(conv5_1))
conv5_3 = self.relu(self.conv5_3(conv5_2))
conv1_1_down = self.conv1_1_down(conv1_1)
conv1_2_down = self.conv1_2_down(conv1_2)
conv2_1_down = self.conv2_1_down(conv2_1)
conv2_2_down = self.conv2_2_down(conv2_2)
conv3_1_down = self.conv3_1_down(conv3_1)
conv3_2_down = self.conv3_2_down(conv3_2)
conv3_3_down = self.conv3_3_down(conv3_3)
conv4_1_down = self.conv4_1_down(conv4_1)
conv4_2_down = self.conv4_2_down(conv4_2)
conv4_3_down = self.conv4_3_down(conv4_3)
conv5_1_down = self.conv5_1_down(conv5_1)
conv5_2_down = self.conv5_2_down(conv5_2)
conv5_3_down = self.conv5_3_down(conv5_3)
so1_out = self.score_dsn1(conv1_1_down + conv1_2_down)
so2_out = self.score_dsn2(conv2_1_down + conv2_2_down)
so3_out = self.score_dsn3(conv3_1_down + conv3_2_down + conv3_3_down)
so4_out = self.score_dsn4(conv4_1_down + conv4_2_down + conv4_3_down)
so5_out = self.score_dsn5(conv5_1_down + conv5_2_down + conv5_3_down)
## transpose and crop way
weight_deconv2 = make_bilinear_weights(4, 1).cuda()
weight_deconv3 = make_bilinear_weights(8, 1).cuda()
weight_deconv4 = make_bilinear_weights(16, 1).cuda()
weight_deconv5 = make_bilinear_weights(32, 1).cuda()
upsample2 = torch.nn.functional.conv_transpose2d(so2_out, weight_deconv2, stride=2)
upsample3 = torch.nn.functional.conv_transpose2d(so3_out, weight_deconv3, stride=4)
upsample4 = torch.nn.functional.conv_transpose2d(so4_out, weight_deconv4, stride=8)
upsample5 = torch.nn.functional.conv_transpose2d(so5_out, weight_deconv5, stride=8)
### center crop
so1 = crop(so1_out, img_H, img_W)
so2 = crop(upsample2, img_H, img_W)
so3 = crop(upsample3, img_H, img_W)
so4 = crop(upsample4, img_H, img_W)
so5 = crop(upsample5, img_H, img_W)
fusecat = torch.cat((so1, so2, so3, so4, so5), dim=1)
fuse = self.score_final(fusecat)
results = [so1, so2, so3, so4, so5, fuse]
results = [torch.sigmoid(r) for r in results]
return results
3.2 损失函数部分
def cross_entropy_loss_RCF(prediction, label):
label = label.long()
mask = label.float()
num_positive = torch.sum((mask==1).float()).float()
num_negative = torch.sum((mask==0).float()).float()
mask[mask == 1] = 1.0 * num_negative / (num_positive + num_negative)
mask[mask == 0] = 1.1 * num_positive / (num_positive + num_negative)
mask[mask == 2] = 0
cost = torch.nn.functional.binary_cross_entropy(
prediction.float(),label.float(), weight=mask, reduce=False)
return torch.sum(cost)
参考文章: