深度学习论文

在GPU上运行的backbone ：
VGG
ResNet
ResNeXt
DenseNet

在CPU上运行的backbone ：
SqueezeNet
MobileNet
ShuffleNet

深度学习的neck 结构
Feature Pyramid Network (FPN)
Path Aggregation Network (PAN)
BiFPN
NAS-FPN

普通的物体探测器由几个部分：

• Input: Image, Patches, Image Pyramid
• Backbones:
  • VGG16
  • ResNet-50
  • SpineNet
  • EfficientNet-B0/B7
  • CSPResNeXt50
  • CSPDarknet53
• Neck:

  • Additional blocks:

    • SPP
    • ASPP
    • RFB
    • SAM

  • Path-aggregation blocks

    • FPN
    • PAN [49]
    • NAS-FPN
    • Fully-connected FPN
    • BiFPN
    • ASFF
    • SFAM
• Heads

  • Dense Prediction (one-stage):

    • RPN 、SSD 、YOLO、RetinaNet、(anchor based)
    • CornerNet , CenterNet , MatrixNet, FCOS (anchor free)

  • Sparse Prediction (two-stage):

    • Faster R-CNN , R-FCN , Mask RCNN (anchor based)
    • RepPoints (anchor free)