【CV】斯坦福CS231n DL-CV by李飞飞 team

Supplements

• PPT downloads

Chap 01: Introduction to CV

• Why CV so important? over 85% of data on Internet is pixel-based, images or videos => Vision.
• Why is CV exploding?
  • Sensors. All kinds of cameras everywhere. (smartphones, cars, drones, surveillances)
  • Big Data. Dark matters on Internet. beyond human ability.

Chap 15： Convolutional Neural Networks

Chap 27: Segmentation & (Soft)Attention

• Segmentation
  • semantic segmentation : 只输出不同的类别class
  • instance segmentation: 即使是同一个class, 不同的个体instance, 也独立标出
• (Soft)Attention
  • Discrete locations
  • Continuous locations (Spatical Transformers)

multi-scale, upsampling, downsampling, deconvolution

• FCN
  

• Multi-scale
  

• Refinement : iteratively
  

• Upsampling

• Deconv = normal conv back-propagation pass, a bad name, sounds like inverse of conv, in fact, it means conv transpose, or upconvolution, backward strided conv or 1/2 strided convolution.

Chap 28: Segmentation & (Soft)Attention