CVPR2023: Slide-Transformer: Hierarchical Vision Transformer with Local Self-Attention

Neighborhood Attention Transformer (CVPR 2023)Подробнее

Vision Transformer Quick Guide - Theory and Code in (almost) 15 minПодробнее

Swin Transformer paper animated and explainedПодробнее

Swin Transformer: Hierarchical Vision Transformer using Shifted WindowsПодробнее

Swin Transformer: Hierarchical Vision Transformer using Shifted Windows (paper illustrated)Подробнее

Swin Transformer: Hierarchical Vision Transformer using Shifted WindowsПодробнее

CVPR 2023 BadViTПодробнее

CVPR2023 Sparsifiner: Learning Sparse Instance-Dependent Attention for Efficient Vision TransformersПодробнее

Swin Transformer: Hierarchical Vision Transformer using Shifted WindowsПодробнее

All Things ViTs || CVPR 2023 Tutorial || Hila Chefer and Sayak PaulПодробнее

A Light Touch Approach to Teaching Transformers Multi-view Geometry (CVPR 2023) [5 minute version]Подробнее

ECS 289G Talk: Swin Transformer: Hierarchical Vision Transformer using Shifted WindowsПодробнее

[CVPR 2023] EfficientViT: Memory Efficient Vision Transformer With Cascaded Group AttentionПодробнее

Global Vision Transformer Pruning with Hessian-Aware Saliency | CVPR 2023Подробнее

2023CVPR Castling-ViTПодробнее

Exploring Lightweight Hierarchical Vision Transformers for Efficient Visual TrackingПодробнее

DropKey for Vision Transformer (CVPR2023)Подробнее

Attention mechanism: OverviewПодробнее