EfficientViT: Memory Efficient Vision Transformer with Cascaded Group Attention.
Xinyu LiuHouwen PengNingxin ZhengYuqing YangHan HuYixuan YuanPublished in: CoRR (2023)
Keyphrases
- memory efficient
- vision system
- external memory
- visual attention
- real time
- iterative deepening
- computer vision
- face detection
- integral image
- visual field
- pre attentive
- high voltage
- computational vision
- distribution network
- multiple sequence alignment
- group members
- saliency map
- power system
- search space
- data structure
- decision making