论文标题
SplitNet：设计神经体系结构，以在头部安装系统上有效分布式计算
SplitNets: Designing Neural Architectures for Efficient Distributed Computing on Head-Mounted Systems
论文作者
论文摘要
我们设计深神经网络（DNNS）和相应的网络的分组，以将DNNS的工作负载分配到相机传感器和头部安装设备上的集中聚合器，以在给定的硬件资源约束下以推理准确性和潜伏期满足系统性能目标。为了在计算，沟通和性能之间达到最佳平衡，引入了分裂感知的神经体系结构搜索框架，即拆分网络，以同时进行模型设计，拆分和交流。我们进一步将框架扩展到多视图系统，以学习从多个相机传感器中融合具有最佳性能和系统性效率的输入。我们验证了ImageNet上的单视图系统以及3D分类的多视图系统，并证明Splitnets框架与现有方法相比，Splitnets框架达到了最先进的性能（SOTA）性能和系统延迟。
We design deep neural networks (DNNs) and corresponding networks' splittings to distribute DNNs' workload to camera sensors and a centralized aggregator on head mounted devices to meet system performance targets in inference accuracy and latency under the given hardware resource constraints. To achieve an optimal balance among computation, communication, and performance, a split-aware neural architecture search framework, SplitNets, is introduced to conduct model designing, splitting, and communication reduction simultaneously. We further extend the framework to multi-view systems for learning to fuse inputs from multiple camera sensors with optimal performance and systemic efficiency. We validate SplitNets for single-view system on ImageNet as well as multi-view system on 3D classification, and show that the SplitNets framework achieves state-of-the-art (SOTA) performance and system latency compared with existing approaches.
