Computer Vision Section 057

CNN Backbones and Pretraining

The famous image networks, taken one at a time, plus the modern trick of training them before you have a single label.

13 of 13 lessons published Three reading levels on every lesson

Start with “Padding, stride and output shapes”

Lessons in order

Work top to bottom. Each lesson assumes the one above it.

  1. Padding, stride and output shapes
  2. Receptive fields
  3. Residual and skip connections
  4. Inception and GoogLeNet
  5. ResNet
  6. The MobileNet family
  7. EfficientNet and compound scaling
  8. ConvNeXt
  9. Swin transformer
  10. Contrastive learning for images
  11. Masked image modelling
  12. DINO and self-distillation
  13. Choosing a backbone