DeepViT

Introduced by Zhou et al. in DeepViT: Towards Deeper Vision Transformer

DeepViT is a type of vision transformer that replaces the self-attention layer within the transformer block with a Re-attention module to address the issue of attention collapse and enables training deeper ViTs.

Source: DeepViT: Towards Deeper Vision Transformer

Read Paper See Code

Papers

Paper	Code	Results	Date	Stars

Tasks

Task	Papers	Share
Image Classification	1	100.00%

Usage Over Time

This feature is experimental; we are continuously improving our matching algorithm.

Components

Component	Type	Add Remove
Re-Attention Module	Attention Modules

Categories

Add Remove

Vision Transformers

Image Models