YOLOv8改进：动态蛇形卷积（Dynamic Snake Convolution），实现暴力涨点 | ICCV2023
原创
YOLOv8改进：动态蛇形卷积（Dynamic Snake Convolution），实现暴力涨点 | ICCV2023
原创
AI小怪兽
发布于 2023-10-06 15:29:50
发布于 2023-10-06 15:29:50
代码可运行
运行总次数：0
代码可运行
💡💡💡本文独家改进：动态蛇形卷积（Dynamic Snake Convolution），增强细长微弱的局部结构特征与复杂多变的全局形态特征
Dynamic Snake Convolution | 亲测在多个数据集能够实现大幅涨点
💡💡💡Yolov8魔术师，独家首发创新（原创），适用于Yolov5、Yolov7、Yolov8等各个Yolo系列，专栏文章提供每一步步骤和源码，轻松带你上手魔改网络
💡💡💡重点：通过本专栏的阅读，后续你也可以自己魔改网络，在网络不同位置（Backbone、head、detect、loss等）进行魔改，实现创新！！！
专栏介绍：
https://blog.csdn.net/m0_63774211/category_12289773.html
✨✨✨原创魔改网络、复现前沿论文，组合优化创新
🚀🚀🚀小目标、遮挡物、难样本性能提升
🍉🍉🍉持续更新中，定期更新不同数据集涨点情况
1.Dynamic Snake Convolution
论文： 2307.08388.pdf (arxiv.org)
摘要：血管、道路等拓扑管状结构的精确分割在各个领域都至关重要，确保下游任务的准确性和效率。 然而，许多因素使任务变得复杂，包括薄的局部结构和可变的全局形态。在这项工作中，我们注意到管状结构的特殊性，并利用这些知识来指导我们的 DSCNet 在三个阶段同时增强感知：特征提取、特征融合、 和损失约束。 首先，我们提出了一种动态蛇卷积，通过自适应地关注细长和曲折的局部结构来准确捕获管状结构的特征。 随后，我们提出了一种多视图特征融合策略，以补充特征融合过程中多角度对特征的关注，确保保留来自不同全局形态的重要信息。 最后，提出了一种基于持久同源性的连续性约束损失函数，以更好地约束分割的拓扑连续性。 2D 和 3D 数据集上的实验表明，与多种方法相比，我们的 DSCNet 在管状结构分割任务上提供了更好的准确性和连续性。 我们的代码是公开的。
主要的挑战源于细长微弱的局部结构特征与复杂多变的全局形态特征。本文关注到管状结构细长连续的特点，并利用这一信息在神经网络以下三个阶段同时增强感知：特征提取、特征融合和损失约束。分别设计了动态蛇形卷积（Dynamic Snake Convolution），多视角特征融合策略与连续性拓扑约束损失。
我们希望卷积核一方面能够自由地贴合结构学习特征，另一方面能够在约束条件下不偏离目标结构太远。在观察管状结构的细长连续的特征后，脑海里想到了一个动物——蛇。我们希望卷积核能够像蛇一样动态地扭动，来贴合目标的结构。
我们希望卷积核一方面能够自由地贴合结构学习特征，另一方面能够在约束条件下不偏离目标结构太远。在观察管状结构的细长连续的特征后，脑海里想到了一个动物——蛇。我们希望卷积核能够像蛇一样动态地扭动，来贴合目标的结构。
2.Dynamic Snake Convolution引入到yolov8
2.1 新建Dynamic Snake Convolution加入ultralytics/nn/Conv/dynamic_snake_conv.py
核心代码：
# Core code, for ease of understanding, we mark the dimensions of input and output next to the code
class DSC(object):
def __init__(self, input_shape, kernel_size, extend_scope, morph):
self.num_points = kernel_size
self.width = input_shape[2]
self.height = input_shape[3]
self.morph = morph
self.extend_scope = extend_scope # offset (-1 ~ 1) * extend_scope
# define feature map shape
"""
B: Batch size C: Channel W: Width H: Height
"""
self.num_batch = input_shape[0]
self.num_channels = input_shape[1]
"""
input: offset [B,2*K,W,H] K: Kernel size (2*K: 2D image, deformation contains <x_offset> and <y_offset>)
output_x: [B,1,W,K*H] coordinate map
output_y: [B,1,K*W,H] coordinate map
"""
def _coordinate_map_3D(self, offset, if_offset):
device = offset.device
# offset
y_offset, x_offset = torch.split(offset, self.num_points, dim=1)
y_center = torch.arange(0, self.width).repeat([self.height])
y_center = y_center.reshape(self.height, self.width)
y_center = y_center.permute(1, 0)
y_center = y_center.reshape([-1, self.width, self.height])
y_center = y_center.repeat([self.num_points, 1, 1]).float()
y_center = y_center.unsqueeze(0)
x_center = torch.arange(0, self.height).repeat([self.width])
x_center = x_center.reshape(self.width, self.height)
x_center = x_center.permute(0, 1)
x_center = x_center.reshape([-1, self.width, self.height])
x_center = x_center.repeat([self.num_points, 1, 1]).float()
x_center = x_center.unsqueeze(0)
if self.morph == 0:
"""
Initialize the kernel and flatten the kernel
y: only need 0
x: -num_points//2 ~ num_points//2 (Determined by the kernel size)
!!! The related PPT will be submitted later, and the PPT will contain the whole changes of each step
"""
y = torch.linspace(0, 0, 1)
x = torch.linspace(
-int(self.num_points // 2),
int(self.num_points // 2),
int(self.num_points),
)
y, x = torch.meshgrid(y, x)
y_spread = y.reshape(-1, 1)
x_spread = x.reshape(-1, 1)
y_grid = y_spread.repeat([1, self.width * self.height])
y_grid = y_grid.reshape([self.num_points, self.width, self.height])
y_grid = y_grid.unsqueeze(0) # [B*K*K, W,H]
x_grid = x_spread.repeat([1, self.width * self.height])
x_grid = x_grid.reshape([self.num_points, self.width, self.height])
x_grid = x_grid.unsqueeze(0) # [B*K*K, W,H]
y_new = y_center + y_grid
x_new = x_center + x_grid
y_new = y_new.repeat(self.num_batch, 1, 1, 1).to(device)
x_new = x_new.repeat(self.num_batch, 1, 1, 1).to(device)
y_offset_new = y_offset.detach().clone()
if if_offset:
y_offset = y_offset.permute(1, 0, 2, 3)
y_offset_new = y_offset_new.permute(1, 0, 2, 3)
center = int(self.num_points // 2)
# The center position remains unchanged and the rest of the positions begin to swing
# This part is quite simple. The main idea is that "offset is an iterative process"
y_offset_new[center] = 0
for index in range(1, center):
y_offset_new[center + index] = (y_offset_new[center + index - 1] + y_offset[center + index])
y_offset_new[center - index] = (y_offset_new[center - index + 1] + y_offset[center - index])
y_offset_new = y_offset_new.permute(1, 0, 2, 3).to(device)
y_new = y_new.add(y_offset_new.mul(self.extend_scope))
y_new = y_new.reshape(
[self.num_batch, self.num_points, 1, self.width, self.height])
y_new = y_new.permute(0, 3, 1, 4, 2)
y_new = y_new.reshape([
self.num_batch, self.num_points * self.width, 1 * self.height
])
x_new = x_new.reshape(
[self.num_batch, self.num_points, 1, self.width, self.height])
x_new = x_new.permute(0, 3, 1, 4, 2)
x_new = x_new.reshape([
self.num_batch, self.num_points * self.width, 1 * self.height
])
return y_new, x_new
else:
"""
Initialize the kernel and flatten the kernel
y: -num_points//2 ~ num_points//2 (Determined by the kernel size)
x: only need 0
"""
y = torch.linspace(
-int(self.num_points // 2),
int(self.num_points // 2),
int(self.num_points),
)
x = torch.linspace(0, 0, 1)
y, x = torch.meshgrid(y, x)
y_spread = y.reshape(-1, 1)
x_spread = x.reshape(-1, 1)
y_grid = y_spread.repeat([1, self.width * self.height])
y_grid = y_grid.reshape([self.num_points, self.width, self.height])
y_grid = y_grid.unsqueeze(0)
x_grid = x_spread.repeat([1, self.width * self.height])
x_grid = x_grid.reshape([self.num_points, self.width, self.height])
x_grid = x_grid.unsqueeze(0)
y_new = y_center + y_grid
x_new = x_center + x_grid
y_new = y_new.repeat(self.num_batch, 1, 1, 1)
x_new = x_new.repeat(self.num_batch, 1, 1, 1)
y_new = y_new.to(device)
x_new = x_new.to(device)
x_offset_new = x_offset.detach().clone()
if if_offset:
x_offset = x_offset.permute(1, 0, 2, 3)
x_offset_new = x_offset_new.permute(1, 0, 2, 3)
center = int(self.num_points // 2)
x_offset_new[center] = 0
for index in range(1, center):
x_offset_new[center + index] = (x_offset_new[center + index - 1] + x_offset[center + index])
x_offset_new[center - index] = (x_offset_new[center - index + 1] + x_offset[center - index])
x_offset_new = x_offset_new.permute(1, 0, 2, 3).to(device)
x_new = x_new.add(x_offset_new.mul(self.extend_scope))
y_new = y_new.reshape(
[self.num_batch, 1, self.num_points, self.width, self.height])
y_new = y_new.permute(0, 3, 1, 4, 2)
y_new = y_new.reshape([
self.num_batch, 1 * self.width, self.num_points * self.height
])
x_new = x_new.reshape(
[self.num_batch, 1, self.num_points, self.width, self.height])
x_new = x_new.permute(0, 3, 1, 4, 2)
x_new = x_new.reshape([
self.num_batch, 1 * self.width, self.num_points * self.height
])
return y_new, x_new
"""
input: input feature map [N,C,D,W,H]；coordinate map [N,K*D,K*W,K*H]
output: [N,1,K*D,K*W,K*H] deformed feature map
"""
def _bilinear_interpolate_3D(self, input_feature, y, x):
device = input_feature.device
y = y.reshape([-1]).float()
x = x.reshape([-1]).float()
zero = torch.zeros([]).int()
max_y = self.width - 1
max_x = self.height - 1
# find 8 grid locations
y0 = torch.floor(y).int()
y1 = y0 + 1
x0 = torch.floor(x).int()
x1 = x0 + 1
# clip out coordinates exceeding feature map volume
y0 = torch.clamp(y0, zero, max_y)
y1 = torch.clamp(y1, zero, max_y)
x0 = torch.clamp(x0, zero, max_x)
x1 = torch.clamp(x1, zero, max_x)
input_feature_flat = input_feature.flatten()
input_feature_flat = input_feature_flat.reshape(
self.num_batch, self.num_channels, self.width, self.height)
input_feature_flat = input_feature_flat.permute(0, 2, 3, 1)
input_feature_flat = input_feature_flat.reshape(-1, self.num_channels)
dimension = self.height * self.width
base = torch.arange(self.num_batch) * dimension
base = base.reshape([-1, 1]).float()
repeat = torch.ones([self.num_points * self.width * self.height
]).unsqueeze(0)
repeat = repeat.float()
base = torch.matmul(base, repeat)
base = base.reshape([-1])
base = base.to(device)
base_y0 = base + y0 * self.height
base_y1 = base + y1 * self.height
# top rectangle of the neighbourhood volume
index_a0 = base_y0 - base + x0
index_c0 = base_y0 - base + x1
# bottom rectangle of the neighbourhood volume
index_a1 = base_y1 - base + x0
index_c1 = base_y1 - base + x1
# get 8 grid values
value_a0 = input_feature_flat[index_a0.type(torch.int64)].to(device)
value_c0 = input_feature_flat[index_c0.type(torch.int64)].to(device)
value_a1 = input_feature_flat[index_a1.type(torch.int64)].to(device)
value_c1 = input_feature_flat[index_c1.type(torch.int64)].to(device)
# find 8 grid locations
y0 = torch.floor(y).int()
y1 = y0 + 1
x0 = torch.floor(x).int()
x1 = x0 + 1
# clip out coordinates exceeding feature map volume
y0 = torch.clamp(y0, zero, max_y + 1)
y1 = torch.clamp(y1, zero, max_y + 1)
x0 = torch.clamp(x0, zero, max_x + 1)
x1 = torch.clamp(x1, zero, max_x + 1)
x0_float = x0.float()
x1_float = x1.float()
y0_float = y0.float()
y1_float = y1.float()
vol_a0 = ((y1_float - y) * (x1_float - x)).unsqueeze(-1).to(device)
vol_c0 = ((y1_float - y) * (x - x0_float)).unsqueeze(-1).to(device)
vol_a1 = ((y - y0_float) * (x1_float - x)).unsqueeze(-1).to(device)
vol_c1 = ((y - y0_float) * (x - x0_float)).unsqueeze(-1).to(device)
outputs = (value_a0 * vol_a0 + value_c0 * vol_c0 + value_a1 * vol_a1 +
value_c1 * vol_c1)
if self.morph == 0:
outputs = outputs.reshape([
self.num_batch,
self.num_points * self.width,
1 * self.height,
self.num_channels,
])
outputs = outputs
else:
outputs = outputs.reshape([
self.num_batch,
1 * self.width,
self.num_points * self.height,
self.num_channels,
])
outputs = outputs
return outputs
def deform_conv(self, input, offset, if_offset):
y, x = self._coordinate_map_3D(offset, if_offset)
deformed_feature = self._bilinear_interpolate_3D(input, y, x)
return deformed_feature
原文详见：https://cv2023.blog.csdn.net/article/details/132689577
原创声明：本文系作者授权腾讯云开发者社区发表，未经许可，不得转载。
如有侵权，请联系 cloudcommunity@tencent.com 删除。
原创声明：本文系作者授权腾讯云开发者社区发表，未经许可，不得转载。
如有侵权，请联系 cloudcommunity@tencent.com 删除。
评论
登录后参与评论
推荐阅读
目录
腾讯云开发者
