Although recent advances in deep neural networks (DNNs) have enabled remarkable performance on various computer vision tasks, it is challenging for edge devices to perform real-time inference of complex DNN models due to their stringent resource constraints. To enhance the inference throughput, recent studies have proposed collaborative intelligence (CI), which splits DNN computation into edge and cloud platforms, mostly for simple tasks, such as image classification. However, for general DNN-based object detectors with a branching architecture, CI is highly restricted because of a significant feature transmission overhead. To resolve this issue, in this study, we propose a reconfigurable DNN architecture for real-time object detection that can configure the optimal split point according to the edge–cloud CI environment. The proposed architecture allows the DNN model to be splittable by a feature reconstruction network and asymmetric scaling. Based on the splittable architecture, we integrate independent splittable models for each split point into a single-weight reconfigurable model that enables multipath inference by switchable quantization and distribution matching. Finally, we introduce an adaptive application procedure of the reconfigurable model for efficient CI, which includes asymmetric scale configuration and split point selection. The performance evaluation using YOLOv5 as the baseline showed that the proposed architecture achieved 30 frames/s ( $2.6\times $ and $1.6\times $ higher than edge-only and cloud-only inference, respectively), on the NVIDIA Jetson TX2 platform in a WiFi environment.

中文翻译：

---

用于边缘-云协作实时目标检测的可重构神经架构

尽管深度神经网络 (DNN) 的最新进展已经在各种计算机视觉任务上取得了显着的性能，但由于其严格的资源限制，边缘设备很难对复杂的 DNN 模型进行实时推理。为了提高推理吞吐量，最近的研究提出了协作智能 (CI)，它将 DNN 计算分为边缘和云平台，主要用于简单的任务，例如图像分类。然而，对于具有分支架构的一般基于 DNN 的对象检测器，CI 由于显着的特征传输开销而受到高度限制。为了解决这个问题，在本研究中，我们提出了一种用于实时对象检测的可重构 DNN 架构，该架构可以根据边缘-云 CI 环境配置最佳分割点。所提出的架构允许 DNN 模型通过特征重建网络和不对称缩放进行拆分。基于可拆分架构，我们将每个拆分点的独立可拆分模型集成到一个单权重可重构模型中，通过可切换的量化和分布匹配实现多路径推理。最后，我们介绍了高效 CI 的可重构模型的自适应应用程序，包括非对称尺度配置和分割点选择。使用 YOLOv5 作为基线的性能评估表明，所提出的架构达到了 30 帧/秒（我们将每个分割点的独立可分割模型集成到一个单权重可重构模型中，该模型通过可切换的量化和分布匹配实现多路径推理。最后，我们介绍了高效 CI 的可重构模型的自适应应用程序，包括非对称尺度配置和分割点选择。使用 YOLOv5 作为基线的性能评估表明，所提出的架构达到了 30 帧/秒（我们将每个分割点的独立可分割模型集成到一个单权重可重构模型中，该模型通过可切换的量化和分布匹配实现多路径推理。最后，我们介绍了高效 CI 的可重构模型的自适应应用程序，包括非对称尺度配置和分割点选择。使用 YOLOv5 作为基线的性能评估表明，所提出的架构达到了 30 帧/秒（ $2.6\次 $和 $1.6\次 $在 WiFi 环境中的 NVIDIA Jetson TX2 平台上分别高于仅边缘和仅云推理）。