NoteNextra-origin/content/CSE559A/CSE559A_L13.md

CSE559A Lecture 13

Positional Encodings

Fixed Positional Encodings

Set of sinusoids of different frequencies.

f(p,2i)=\sin(\frac{p}{10000^{2i/d}})\quad f(p,2i+1)=\cos(\frac{p}{10000^{2i/d}})

source

Positional Encodings in Reconstruction

MLP is hard to learn high-frequency information from scaler input (x,y).

Example: network mapping from (x,y) to (r,g,b).

Generalized Positional Encodings

• Dependence on location, scaler, metadata, etc.
• Can just be fully learned (use nn.Embedding and optimize based on a categorical input.)

Vision Transformer (ViT)

Class Token

In Vision Transformers, a special token called the class token is added to the input sequence to aggregate information for classification tasks.

Hidden CNN Modules

• PxP convolution with stride P (split the image into patches and use positional encoding)

ViT + ResNet Hybrid

Build a hybrid model that combines the vision transformer after 50 layer of ResNet.

Moving Forward

At least for now, CNN and ViT architectures have similar performance at least in ImageNet.

• General Consensus: once the architecture is big enough, and not designed terribly, it can do well.
• Differences remain:
  • Computational efficiency
  • Ease of use in other tasks and with other input data
  • Ease of training

Wrap up

Self attention as a key building block

Flexible input specification using tokens with positional encodings

A wide variety of architectural styles

Up Next: Training deep neural networks