BiFormer: Vision Transformer Bi-Level Routing Attention (CVPR 2023)

BiFormer: Vision Transformer Bi-Level Routing Attention (CVPR 2023)

Neighborhood Attention Transformer (CVPR 2023)Подробнее

Neighborhood Attention Transformer (CVPR 2023)

🎄Мир под ёлку. Разворот Макрона. Курские Кошмары ВСУ. Бандера в Славянске. ТЦК за бугром - АрестовичПодробнее

🎄Мир под ёлку. Разворот Макрона. Курские Кошмары ВСУ. Бандера в Славянске. ТЦК за бугром - Арестович

CVPR 2023: Adaptive Spot-Guided Transformer for Consistent Local Feature MatchingПодробнее

CVPR 2023: Adaptive Spot-Guided Transformer for Consistent Local Feature Matching

HEAT: Holistic Edge Attention Transformer for Structured Reconstruction, CVPR 2022.Подробнее

HEAT: Holistic Edge Attention Transformer for Structured Reconstruction, CVPR 2022.

OCTUF (CVPR 2023)Подробнее

OCTUF (CVPR 2023)

TransVPR: Transformer Based Place Recognition With Multi Level Attention Aggregation | CVPR 2022Подробнее

TransVPR: Transformer Based Place Recognition With Multi Level Attention Aggregation | CVPR 2022

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

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

CVPR 2023 BadViTПодробнее

CVPR 2023 BadViT

[CVPR 2023] AShapeFormerПодробнее

[CVPR 2023] AShapeFormer

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

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

A ViT: Adaptive Tokens for Efficient Vision Transformer | CVPR 2022Подробнее

A ViT: Adaptive Tokens for Efficient Vision Transformer | CVPR 2022

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

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

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

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

FlexiViT (CVPR'23)Подробнее

FlexiViT (CVPR'23)

[CVPR 2023] OneFormer: One Transformer to Rule Universal Image SegmentationПодробнее

[CVPR 2023] OneFormer: One Transformer to Rule Universal Image Segmentation

[CVPR 2023] POTTER: Pooling Attention Transformer for Efficient Human Mesh RecoveryПодробнее

[CVPR 2023] POTTER: Pooling Attention Transformer for Efficient Human Mesh Recovery

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

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

CVPR 2023 - SVGformer: Representation Learning for Continuous Vector Graphics using TransformersПодробнее

CVPR 2023 - SVGformer: Representation Learning for Continuous Vector Graphics using Transformers