1.Dynamic Region-Aware Convolution
论文：https://arxiv.org/pdf/2003.12243.pdf
摘要 旷视研究院提出一种新颖的卷积方式，名为动态区域感知卷积(DRConv)，它能为特征具有相似表示的相应空间区域自动地分配定制卷积核，相较标准卷积，这种卷积方式大大地增强了对图像语义多样性的建模能力。DRConv通过可学习的指示器(learnable instructor)将逐步增加的通道维卷积核变换至空间维，这一方面增强了卷积的表征能力，另一方面控制计算成本并使平移不变性保持与标准卷积一致。（由于每个卷积层可以视为一次滤波操作，所以我把文中的filter理解为网络指定卷积层中的等效卷积核）。
DRConv是一种高效且灵活的卷积方法，适用于处理复杂且多变的空间信息分布，在各种模型(MobileNet series, ShuffleNetV2, etc.)与视觉任务(Classification, Face Recognition, Detection and Segmentation)中证实了其有效性和优越性。
本文提出了一种新的卷积算法，称为动态区域卷积算法（DRConv） ，该算法能够自动将滤波器分配到相应的空间区域，因此，DRConv具有强大的语义表示能力，并完美地保持了平移不变性。
DRConv的结构如上图所示，首先用标准卷积从输入生成引导特征，然后根据引导特征，将空间维度划分为多个区域，每个区域用不同的颜色表示。在每个共享区域中，作者用滤波器生成器模块生成多个滤波器来执行二维卷积运算。
2.DRConv引入到Yolov5
2.1 DRConv加入到common.py
代码语言：javascript复制###################### CVPR2021 DRConv #### start by AI&CV ###############################
from torch.autograd import Variable, Function
class asign_index(torch.autograd.Function):
@staticmethod
def forward(ctx, kernel, guide_feature):
ctx.save_for_backward(kernel, guide_feature)
guide_mask = torch.zeros_like(guide_feature).scatter_(1, guide_feature.argmax(dim=1, keepdim=True),
1).unsqueeze(2) # B x 3 x 1 x 25 x 25
return torch.sum(kernel * guide_mask, dim=1)
@staticmethod
def backward(ctx, grad_output):
kernel, guide_feature = ctx.saved_tensors
guide_mask = torch.zeros_like(guide_feature).scatter_(1, guide_feature.argmax(dim=1, keepdim=True),
1).unsqueeze(2) # B x 3 x 1 x 25 x 25
grad_kernel = grad_output.clone().unsqueeze(1) * guide_mask # B x 3 x 256 x 25 x 25
grad_guide = grad_output.clone().unsqueeze(1) * kernel # B x 3 x 256 x 25 x 25
grad_guide = grad_guide.sum(dim=2) # B x 3 x 25 x 25
softmax = F.softmax(guide_feature, 1) # B x 3 x 25 x 25
grad_guide = softmax * (grad_guide - (softmax * grad_guide).sum(dim=1, keepdim=True)) # B x 3 x 25 x 25
return grad_kernel, grad_guide
def xcorr_slow(x, kernel, kwargs):
"""for loop to calculate cross correlation
"""
batch = x.size()[0]
out = []
for i in range(batch):
px = x[i]
pk = kernel[i]
px = px.view(1, px.size()[0], px.size()[1], px.size()[2])
pk = pk.view(-1, px.size()[1], pk.size()[1], pk.size()[2])
po = F.conv2d(px, pk, **kwargs)
out.append(po)
out = torch.cat(out, 0)
return out
def xcorr_fast(x, kernel, kwargs):
"""group conv2d to calculate cross correlation
"""
batch = kernel.size()[0]
pk = kernel.view(-1, x.size()[1], kernel.size()[2], kernel.size()[3])
px = x.view(1, -1, x.size()[2], x.size()[3])
po = F.conv2d(px, pk, **kwargs, groups=batch)
po = po.view(batch, -1, po.size()[2], po.size()[3])
return po
class Corr(Function):
@staticmethod
def symbolic(g, x, kernel, groups):
return g.op("Corr", x, kernel, groups_i=groups)
@staticmethod
def forward(self, x, kernel, groups, kwargs):
"""group conv2d to calculate cross correlation
"""
batch = x.size(0)
channel = x.size(1)
x = x.view(1, -1, x.size(2), x.size(3))
kernel = kernel.view(-1, channel // groups, kernel.size(2), kernel.size(3))
out = F.conv2d(x, kernel, **kwargs, groups=groups * batch)
out = out.view(batch, -1, out.size(2), out.size(3))
return out
class Correlation(nn.Module):
use_slow = True
def __init__(self, use_slow=None):
super(Correlation, self).__init__()
if use_slow is not None:
self.use_slow = use_slow
else:
self.use_slow = Correlation.use_slow
def extra_repr(self):
if self.use_slow: return "xcorr_slow"
return "xcorr_fast"
def forward(self, x, kernel, **kwargs):
if self.training:
if self.use_slow:
return xcorr_slow(x, kernel, kwargs)
else:
return xcorr_fast(x, kernel, kwargs)
else:
return Corr.apply(x, kernel, 1, kwargs)
class DRConv2d(nn.Module):
def __init__(self, in_channels, out_channels, kernel_size, region_num=8, **kwargs):
super(DRConv2d, self).__init__()
self.region_num = region_num
self.conv_kernel = nn.Sequential(
nn.AdaptiveAvgPool2d((kernel_size, kernel_size)),
nn.Conv2d(in_channels, region_num * region_num, kernel_size=1),
nn.Sigmoid(),
nn.Conv2d(region_num * region_num, region_num * in_channels * out_channels, kernel_size=1,
groups=region_num)
)
self.conv_guide = nn.Conv2d(in_channels, region_num, kernel_size=kernel_size, **kwargs)
self.corr = Correlation(use_slow=False)
self.kwargs = kwargs
self.asign_index = asign_index.apply
def forward(self, input):
kernel = self.conv_kernel(input)
kernel = kernel.view(kernel.size(0), -1, kernel.size(2), kernel.size(3)) # B x (r*in*out) x W X H
output = self.corr(input, kernel, **self.kwargs) # B x (r*out) x W x H
output = output.view(output.size(0), self.region_num, -1, output.size(2), output.size(3)) # B x r x out x W x H
guide_feature = self.conv_guide(input)
output = self.asign_index(output, guide_feature)
return output
###################### CVPR2021 DRConv #### END by AI&CV ###############################
by CSDN AI小怪兽 https://blog.csdn.net/m0_63774211/article/details/130370597
我正在参与2023腾讯技术创作特训营第三期有奖征文，组队打卡瓜分大奖！
