Deep Contextualized Compressive Offloading for Images
Deep Contextualized Compressive Offloading for Images
复制标题
DOI：
10.1145/3485730.3493452
复制
发表时间：
2021-11
期刊：
影响因子：
--
通讯作者：
Bo Chen;Zhisheng Yan;Hongpeng Guo;Zhe Yang;Ahmed Ali-Eldin;Prashant J. Shenoy;K. Nahrstedt
中科院分区：
文献类型：
--
作者：
Bo Chen;Zhisheng Yan;Hongpeng Guo;Zhe Yang;Ahmed Ali-Eldin;Prashant J. Shenoy;K. Nahrstedt
近年来，传感器已成为我们生活中不可或缺的一部分，而相机是最流行和广泛部署的传感器之一。该摄像头催生了许多基于视觉的物联网应用程序，这些应用程序通过对移动或嵌入式设备等终端设备进行分析，生成对实时视频流的高级理解。通常，这些应用程序是使用深度学习 (DL) 模型构建的，以执行复杂的视觉任务，例如图像分类和对象检测。由于在靠近摄像头的终端设备上运行深度学习模型的成本高昂且计算能力有限，因此广泛采用将计算卸载到附近强大的边缘服务器。然而，终端设备受限的卸载带宽与直播视频流产生的大量图像数据之间存在差距。在本文中，我们提出了图像深度上下文压缩卸载（DCCOI），这是一种轻量级、上下文感知且带宽高效的图像卸载框架。 DCCOI 由空间自适应编码器、用于空间自适应压缩图像的轻量级神经网络以及用于从压缩数据重建图像的生成解码器组成。与现有的基于深度学习的编码器相比，空间自适应编码器允许根据图像区域中的信息将图像区域编码为不同数量的特征值。这为图像压缩提供了一种可变长度编码方法，与现有基于深度学习的压缩方法所采用的固定长度编码方法相比，这是一种更优化的压缩方式，并且展示了卓越的精度与压缩率权衡。我们在为基于对象检测的应用程序提供服务时，针对多种基线压缩技术评估 DCCOI。结果表明，DCCOI 将 JPEG 的卸载大小大致减少了 9 倍，而最先进的卸载方法 DeepCOD 则减少了 20%，且精度相似，压缩开销小于 50 毫秒。
Recent years have witnessed sensors becoming an indispensable part of our life with the camera being one of the most popular and widely deployed sensors. The camera gives rise to numerous vision-based IoT applications that generate high-level understandings of a live video stream by performing analysis on end devices like mobile or embedded devices. Typically, these applications are built with deep learning (DL) models to conduct complex vision tasks, e.g., image classification and object detection. Due to the prohibitive cost of running DL models on end devices close to the camera and with limited computation capabilities, it is widely adopted to offload the computation to a nearby powerful edge server. However, there is a gap between the restricted offloading bandwidth of the end device and the large volume of image data incurred by the live video stream. In this paper, we present Deep Contextualized Compressive Offloading for Images (DCCOI), a lightweight, context-aware, and bandwidth-efficient offloading framework for images. DCCOI consists of the spatial-adaptive encoder, a lightweight neural network, to spatial-adaptively compress the image, and the generative decoder for reconstructing the image from the compressed data. In contrast to existing DL-based encoders, the spatial-adaptive encoder allows an image region to be encoded into different numbers of feature values based on the information in it. This offers a variable-length coding method for image compression, which is a more optimal way for compression than the fix-length coding method took by existing DL-based compression approaches and demonstrates superior accuracy-compression rate trade-offs. We evaluate DCCOI against several baseline compression techniques while serving an object detection-based application. The results show that DCCOI roughly reduces the offloading size of JPEG by a factor of 9 and DeepCOD, the state-of-the-art offloading approach, by 20% with similar accuracy and a compression overhead less than 50ms.