用三值输入二值权重加速微型视觉系统目标识别
Ternary-Input Binary-Weight CNN Accelerator Design for Miniature Object Classification System with Query-Driven Spatial DVS
- 三值传感器输出+二值权重网络，降低计算与内存需求
- 数据量减81%，乘加操作降27%，功耗仅1.6mW
- 适合空间受限、电池供电的微型视觉设备
微型成像系统在空间受限的应用中至关重要，但受制于存储和功耗限制。尽管机器学习可通过提取关键特征缩小数据规模，其高能耗常超出小型电池承载能力。本文提出一种面向微型成像系统的卷积神经网络硬件加速器，处理来自空间动态视觉传感器（DVS）的数据，并通过像素共享可重构为时序DVS以最小化传感器面积。采用三值DVS输出与三值输入、二值权重神经网络，显著减少计算与内存开销。该加速器在28 nm CMOS工艺下实现，数据量减少81%，乘加操作降低27%。推理时间仅440毫秒，功耗低至1.6毫瓦，相比以往微型系统中的CNN加速器，性能-功耗指标（FoM）提升7.3倍。
原文摘要 · Abstract (English)
Miniature imaging systems are essential for space-constrained applications but are limited by memory and power constraints. While machine learning can reduce data size by extracting key features, its high energy demands often exceed the capacity of small batteries. This paper presents a CNN hardware accelerator optimized for object classification in miniature imaging systems. It processes data from a spatial Dynamic Vision Sensor (DVS), reconfigurable to a temporal DVS via pixel sharing, minimizing sensor area. By using ternary DVS outputs and a ternary-input, binary-weight neural network, the design reduces computation and memory needs. Fabricated in 28 nm CMOS, the accelerator cuts data size by 81% and MAC operations by 27%. It achieves 440 ms inference time at just 1.6 mW power consumption, improving the Figure-of-Merit (FoM) by 7.3x over prior CNN accelerators for miniature systems.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。