AQD: Towards Accurate Quantized Object Detection
2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)(2021)
摘要
Network quantization allows inference to be conducted using low-precision arithmetic for improved inference efficiency of deep neural networks on edge devices. However, designing aggressively low-bit (e.g., 2-bit) quantization schemes on complex tasks, such as object detection, still remains challenging in terms of severe performance degradation and unverifiable efficiency on common hardware. In t...
更多查看译文
关键词
Performance evaluation,Degradation,Quantization (signal),Image edge detection,Object detection,Detectors,Hardware
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络