Computer Vision
Teaching machines to see: from a single convolution sliding over pixels to architectures that read an image as a sequence of patches.
In this chapter
■□□ Foundations ■■□ Practitioner ■■■ Research- § 1 Convolutions In preparation Level: Foundations
- § 2 CNN Architectures In preparation Level: Practitioner
- § 3 Object Detection In preparation Level: Practitioner
- § 4 Vision Transformers In preparation Level: Research
Topics: Convolutions · CNN architectures · Detection · Vision transformers · Formats: 3D plates · PyTorch · Papers