一： SBCFormer [ PDF]
SBCFormer 是一种 CNN-ViT 轻量混合网络backbone，能在单板计算机上能以每秒 1 帧速度进行全尺寸 ImageNet 分类的轻量级网络。
通过在低端 CPU 上实现高准确性和快速计算，为树莓派 4 型号 B 的 ARM-Cortex A72 CPU 提供了以往无法达到的每秒 1.0。
- This paper introduces a CNN-ViT hybrid network called SBCFormer, which achieves high accuracy and fast computation on such low-end CPUs.
- We compare our SBCFormers against a wide range of relevant and up-todate alternatives.
- SBCFormer uses the proposed hourglass attention computation to aggregate global information from the entire image while minimizing computational costs.
- SBCFormer achieves the highest trade-off between accuracy and speed on a Raspberry Pi 4 Model B with an ARM-Cortex A72 CPU.
二：网络架构
三、性能
ImageNet-1K Classification
COCO 2017 Object Detection
四、Reference
@article{lu2024sbcformer,title={SBCFormer: Lightweight Network Capable of Full-size ImageNet Classification at 1 FPS on Single Board Computers},author={Xiangyong Lu, Masanori Suganuma, Takayuki Okatani},booktitle={Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)},year={2024}
}
