Paper Reading Group, June 15: ConViT
The paper reading groups are supported by experiments, blogs & code implementation! This is your chance to come talk about the paper that interests you!
Created on June 11|Last edited on June 11
Comment
Don't miss our host Aman Arora taking you on a deep dive on this ConViT paper!
Improving Vision Transformers with Soft Convolutional Inductive Biases (Paper / Blog post on paper summary)
Together you'll look into the ConViT transformer architecture in detail & learn all about it. Also the gated positional self-attention (GPSA) layer! You'll also see how the ConViT architecture gets the best of both worlds and obtains the benefits of both Transformers and CNNs.
Register here for this & upcoming bi-weekly PRGs.
For a better understanding we recommend you reading the paper before the session.
Add a comment