1. SCConv
卷积在各种计算机视觉任务中表现出色，但是由于卷积层提取冗余特征，其计算资源需求巨大。虽然过去用于改善网络效率的各种模型压缩策略和网络设计，包括网络剪枝、权重量化、低秩分解和知识蒸馏等。然而，这些方法都被视为后处理步骤，因此它们的性能通常受到给定初始模型的上限约束。而网络设计另辟蹊径，试图减少密集模型参数中的固有冗余，进一步开发轻量级网络模型。
SCConv模块的设计
为了解决上述问题，论文（SCConv: Spatial and Channel Reconstruction Convolution for Feature Redundancy (thecvf.com)）提出了一个新的卷积模块，名为SCConv，这个模块利用了两个组件：空间重建单元（SRU）和通道重建单元（CRU）。
SRU 通过一种分离-重建的方法抑制空间冗余
CRU 则采用一种分割-转换-融合的策略减少通道冗余
此外，SCConv 是一个即插即用的架构单元，可以直接替换各种卷积神经网络中的标准卷积。
SCConv模块的性能
SCConv 模块旨在有效地限制特征冗余，不仅减少了模型参数和FLOPs的数量，而且增强了特征表示的能力。实际上，SCConv 模块提供了一种新的视角来看待CNNs的特征提取过程，提出了一种更有效地利用空间和通道冗余的方法，从而在减少冗余特征的同时提高模型性能。实验结果显示，嵌入了 SCConv 模块的模型能够通过显著降低复杂性和计算成本，减少冗余特征，从而达到更好的性能。
SRU
CRU
2. YOLOv8 C2f融合SCConv模块
加入融合ScConv的C2f模块，在ultralytics包中的nn包的modules中的block.py文件中添加改进模块。代码如下：
class SRU(nn.Module): def __init__(self, oup_channels: int, group_num: int = 16, gate_treshold: float = 0.5 ): super().__init__() self.gn = GroupBatchnorm2d(oup_channels, group_num=group_num) self.gate_treshold = gate_treshold self.sigomid = nn.Sigmoid() def forward(self, x): gn_x = self.gn(x) w_gamma = self.gn.gamma / sum(self.gn.gamma) reweigts = self.sigomid(gn_x * w_gamma) # Gate info_mask = reweigts >= self.gate_treshold noninfo_mask = reweigts < self.gate_treshold x_1 = info_mask * x x_2 = noninfo_mask * x x = self.reconstruct(x_1, x_2) return x def reconstruct(self, x_1, x_2): x_11, x_12 = torch.split(x_1, x_1.size(1) // 2, dim=1) x_21, x_22 = torch.split(x_2, x_2.size(1) // 2, dim=1) return torch.cat([x_11 + x_22, x_12 + x_21], dim=1) class CRU(nn.Module): ''' alpha: 0<alpha<1 ''' def __init__(self, op_channel: int, alpha: float = 1 / 2, squeeze_radio: int = 2, group_size: int = 2, group_kernel_size: int = 3, ): super().__init__() self.up_channel = up_channel = int(alpha * op_channel) self.low_channel = low_channel = op_channel - up_channel self.squeeze1 = nn.Conv2d(up_channel, up_channel // squeeze_radio, kernel_size=1, bias=False) self.squeeze2 = nn.Conv2d(low_channel, low_channel // squeeze_radio, kernel_size=1, bias=False) # up self.GWC = nn.Conv2d(up_channel // squeeze_radio, op_channel, kernel_size=group_kernel_size, stride=1, padding=group_kernel_size // 2, groups=group_size) self.PWC1 = nn.Conv2d(up_channel // squeeze_radio, op_channel, kernel_size=1, bias=False) # low self.PWC2 = nn.Conv2d(low_channel // squeeze_radio, op_channel - low_channel // squeeze_radio, kernel_size=1, bias=False) self.advavg = nn.AdaptiveAvgPool2d(1) def forward(self, x): # Split up, low = torch.split(x, [self.up_channel, self.low_channel], dim=1) up, low = self.squeeze1(up), self.squeeze2(low) # Transform Y1 = self.GWC(up) + self.PWC1(up) Y2 = torch.cat([self.PWC2(low), low], dim=1) # Fuse out = torch.cat([Y1, Y2], dim=1) out = F.softmax(self.advavg(out), dim=1) * out out1, out2 = torch.split(out, out.size(1) // 2, dim=1) return out1 + out2 class ScConv(nn.Module): # https://github.com/cheng-haha/ScConv/blob/main/ScConv.py def __init__(self, op_channel: int, group_num: int = 16, gate_treshold: float = 0.5, alpha: float = 1 / 2, squeeze_radio: int = 2, group_size: int = 2, group_kernel_size: int = 3, ): super().__init__() self.SRU = SRU(op_channel, group_num=group_num, gate_treshold=gate_treshold) self.CRU = CRU(op_channel, alpha=alpha, squeeze_radio=squeeze_radio, group_size=group_size, group_kernel_size=group_kernel_size) def forward(self, x): x = self.SRU(x) x = self.CRU(x) return x class Bottleneck_ScConv(Bottleneck): def __init__(self, c1, c2, shortcut=True, g=1, k=(3, 3), e=0.5): super().__init__(c1, c2, shortcut, g, k, e) c_ = int(c2 * e) # hidden channels self.cv1 = Conv(c1, c_, k[0], 1) self.cv2 = ScConv(c2) class C2f_ScConv(C2f): def __init__(self, c1, c2, n=1, shortcut=False, g=1, e=0.5): super().__init__(c1, c2, n, shortcut, g, e) self.m = nn.ModuleList(Bottleneck_ScConv(self.c, self.c, shortcut, g, k=(3, 3), e=1.0) for _ in range(n))
对融合ScConv的C2f模块的进行注册和引用，注册方式参考YOLOv8改进算法之添加CA注意力机制-CSDN博客
在tasks.py中的parse_model中添加C2f_ScConv：
新建相应的yaml文件，代码如下：
# Ultralytics YOLO 🚀, AGPL-3.0 license # YOLOv8 object detection model with P3-P5 outputs. For Usage examples see https://docs.ultralytics.com/tasks/detect # Parameters nc: 80 # number of classes scales: # model compound scaling constants, i.e. 'model=yolov8n.yaml' will call yolov8.yaml with scale 'n' # [depth, width, max_channels] n: [0.33, 0.25, 1024] # YOLOv8n summary: 225 layers, 3157200 parameters, 3157184 gradients, 8.9 GFLOPs s: [0.33, 0.50, 1024] # YOLOv8s summary: 225 layers, 11166560 parameters, 11166544 gradients, 28.8 GFLOPs m: [0.67, 0.75, 768] # YOLOv8m summary: 295 layers, 25902640 parameters, 25902624 gradients, 79.3 GFLOPs l: [1.00, 1.00, 512] # YOLOv8l summary: 365 layers, 43691520 parameters, 43691504 gradients, 165.7 GFLOPs x: [1.00, 1.25, 512] # YOLOv8x summary: 365 layers, 68229648 parameters, 68229632 gradients, 258.5 GFLOPs # YOLOv8.0n backbone backbone: # [from, repeats, module, args] - [-1, 1, Conv, [64, 3, 2]] # 0-P1/2 - [-1, 1, Conv, [128, 3, 2]] # 1-P2/4 - [-1, 3, C2f_ScConv, [128, True]] - [-1, 1, Conv, [256, 3, 2]] # 3-P3/8 - [-1, 6, C2f_ScConv, [256, True]] - [-1, 1, Conv, [512, 3, 2]] # 5-P4/16 - [-1, 6, C2f_ScConv, [512, True]] - [-1, 1, Conv, [1024, 3, 2]] # 7-P5/32 - [-1, 3, C2f_ScConv, [1024, True]] - [-1, 1, SPPF, [1024, 5]] # 9 # YOLOv8.0n head head: - [-1, 1, nn.Upsample, [None, 2, 'nearest']] - [[-1, 6], 1, Concat, [1]] # cat backbone P4 - [-1, 3, C2f, [512]] # 12 - [-1, 1, nn.Upsample, [None, 2, 'nearest']] - [[-1, 4], 1, Concat, [1]] # cat backbone P3 - [-1, 3, C2f, [256]] # 15 (P3/8-small) - [-1, 1, Conv, [256, 3, 2]] - [[-1, 12], 1, Concat, [1]] # cat head P4 - [-1, 3, C2f, [512]] # 18 (P4/16-medium) - [-1, 1, Conv, [512, 3, 2]] - [[-1, 9], 1, Concat, [1]] # cat head P5 - [-1, 3, C2f, [1024]] # 21 (P5/32-large) - [[15, 18, 21], 1, Detect, [nc]] # Detect(P3, P4, P5)
