EfficientViT: Memory Efficient Vision Transformer with Cascaded Group Attention.
Xinyu LiuHouwen PengNingxin ZhengYuqing YangHan HuYixuan YuanPublished in: CVPR (2023)
Keyphrases
- memory efficient
- computer vision
- external memory
- fuzzy logic
- visual field
- vision system
- multiple sequence alignment
- multi dimensional
- pattern growth
- image processing
- iterative deepening
- face detection
- power system
- group members
- focus of attention
- visual attention
- visual perception
- data sets
- mobile robot
- genetic algorithm