论文标题
参加网络：通过视觉注意力冷凝器的边缘的微小图像识别神经网络
AttendNets: Tiny Deep Image Recognition Neural Networks for the Edge via Visual Attention Condensers
论文作者
论文摘要
尽管深度学习的重大进展导致了许多复杂的视觉感知任务的最先进的表现，但涉及涉及现场的Tinyml应用的深神经网络的广泛部署，鉴于深层神经网络的复杂性，低功耗图像识别仍然是一项巨大挑战。在这项研究中，我们介绍了针对内在图像识别的量身定制的“低精油，高度紧凑的深度神经网络”。更具体地说，基于视觉注意力冷凝器具有深度的自我注意力结构，该架构扩展了最近引入的独立注意力冷凝器，以改善空间通道的选择性关注。此外，通过机器驱动的设计探索策略实现了独特的机器设计的宏观结构和微体系结构设计。针对内放设备图像识别任务的Imagenet $ _ {50} $基准数据集的实验结果表明，与精确效率的几个深层神经网络相比，参加网络的体系结构和计算复杂性显着降低乘以add操作，$ \ sim $ 4.17 $ \ times $ $较少的参数，$ \ sim $ 16.7 $ \ times $ $ \ times $降低了Mobilenet-v1的重量内存要求）。基于这些有希望的结果，出席网络说明了视觉注意力冷凝器的有效性，作为为tinyml应用实现各种设备视觉感知任务的基础。
While significant advances in deep learning has resulted in state-of-the-art performance across a large number of complex visual perception tasks, the widespread deployment of deep neural networks for TinyML applications involving on-device, low-power image recognition remains a big challenge given the complexity of deep neural networks. In this study, we introduce AttendNets, low-precision, highly compact deep neural networks tailored for on-device image recognition. More specifically, AttendNets possess deep self-attention architectures based on visual attention condensers, which extends on the recently introduced stand-alone attention condensers to improve spatial-channel selective attention. Furthermore, AttendNets have unique machine-designed macroarchitecture and microarchitecture designs achieved via a machine-driven design exploration strategy. Experimental results on ImageNet$_{50}$ benchmark dataset for the task of on-device image recognition showed that AttendNets have significantly lower architectural and computational complexity when compared to several deep neural networks in research literature designed for efficiency while achieving highest accuracies (with the smallest AttendNet achieving $\sim$7.2% higher accuracy, while requiring $\sim$3$\times$ fewer multiply-add operations, $\sim$4.17$\times$ fewer parameters, and $\sim$16.7$\times$ lower weight memory requirements than MobileNet-V1). Based on these promising results, AttendNets illustrate the effectiveness of visual attention condensers as building blocks for enabling various on-device visual perception tasks for TinyML applications.
