Neighborhood Attention Transformer (CVPR 2023)

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

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

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

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

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

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

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

Couplformer: Rethinking Vision Transformer with Coupling Attention MapПодробнее

CVPR 2023 BadViTПодробнее

(CVPR 2023) Visual Atoms: Pre-training Vision Transformers with Sinusoidal WavesПодробнее

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

Learning Attention as Disentangler for Compositional Zero-shot Learning (CVPR 2023)Подробнее

2023CVPR Castling-ViTПодробнее