摘要翻译：
在过去的几年里，计算机视觉以惊人的速度取得了进步，这是基于深度神经网络构造和训练的新发现，以及大规模标记数据集的可用性。将这些网络应用于图像需要很高的计算工作量，并将最新的网络应用于实时视频数据超出了嵌入式平台的范围。近年来，许多研究都集中在降低嵌入式计算平台上实时推理的网络复杂度上。我们采用正交的观点，利用像素变化的时空稀疏性，提出了一种新的算法。在Tegra X2平台上，这种优化的推理过程比cuDNN的平均速度提高了9.1×，而准确率损失小于0.1%，而且对于语义分割应用程序，网络没有重新训练，因此，这种优化的推理过程比cuDNN的平均速度提高了9.1×cuDNN的平均速度提高了9.1×cuDNN的平均速度提高了9.1×cuDNN的平均速度更快。同样地，在静态摄像机视频监视数据上，位姿检测DNN的平均速度提高了7.0倍，目标检测所需执行的算术运算次数减少了5倍。这些吞吐量增益与较低的功率消耗相结合导致能量效率为511GOP/S/W，而基线为70GOP/S/W。
---
英文标题：
《CBinfer: Exploiting Frame-to-Frame Locality for Faster Convolutional
  Network Inference on Video Streams》
---
作者：
Lukas Cavigelli, Luca Benini
---
最新提交年份：
2019
---
分类信息：

一级分类：Computer Science        计算机科学
二级分类：Computer Vision and Pattern Recognition        计算机视觉与模式识别
分类描述：Covers image processing, computer vision, pattern recognition, and scene understanding. Roughly includes material in ACM Subject Classes I.2.10, I.4, and I.5.
涵盖图像处理、计算机视觉、模式识别和场景理解。大致包括ACM课程I.2.10、I.4和I.5中的材料。
--
一级分类：Computer Science        计算机科学
二级分类：Artificial Intelligence        人工智能
分类描述：Covers all areas of AI except Vision, Robotics, Machine Learning, Multiagent Systems, and Computation and Language (Natural Language Processing), which have separate subject areas. In particular, includes Expert Systems, Theorem Proving (although this may overlap with Logic in Computer Science), Knowledge Representation, Planning, and Uncertainty in AI. Roughly includes material in ACM Subject Classes I.2.0, I.2.1, I.2.3, I.2.4, I.2.8, and I.2.11.
涵盖了人工智能的所有领域，除了视觉、机器人、机器学习、多智能体系统以及计算和语言（自然语言处理），这些领域有独立的学科领域。特别地，包括专家系统，定理证明（尽管这可能与计算机科学中的逻辑重叠），知识表示，规划，和人工智能中的不确定性。大致包括ACM学科类I.2.0、I.2.1、I.2.3、I.2.4、I.2.8和I.2.11中的材料。
--
一级分类：Computer Science        计算机科学
二级分类：Neural and Evolutionary Computing        神经与进化计算
分类描述：Covers neural networks, connectionism, genetic algorithms, artificial life, adaptive behavior. Roughly includes some material in ACM Subject Class C.1.3, I.2.6, I.5.
涵盖神经网络，连接主义，遗传算法，人工生命，自适应行为。大致包括ACM学科类C.1.3、I.2.6、I.5中的一些材料。
--
一级分类：Electrical Engineering and Systems Science        电气工程与系统科学
二级分类：Image and Video Processing        图像和视频处理
分类描述：Theory, algorithms, and architectures for the formation, capture, processing, communication, analysis, and display of images, video, and multidimensional signals in a wide variety of applications. Topics of interest include: mathematical, statistical, and perceptual image and video modeling and representation; linear and nonlinear filtering, de-blurring, enhancement, restoration, and reconstruction from degraded, low-resolution or tomographic data; lossless and lossy compression and coding; segmentation, alignment, and recognition; image rendering, visualization, and printing; computational imaging, including ultrasound, tomographic and magnetic resonance imaging; and image and video analysis, synthesis, storage, search and retrieval.
用于图像、视频和多维信号的形成、捕获、处理、通信、分析和显示的理论、算法和体系结构。感兴趣的主题包括：数学，统计，和感知图像和视频建模和表示；线性和非线性滤波、去模糊、增强、恢复和重建退化、低分辨率或层析数据；无损和有损压缩编码；分割、对齐和识别；图像渲染、可视化和打印；计算成像，包括超声、断层和磁共振成像；以及图像和视频的分析、合成、存储、搜索和检索。
--

---
英文摘要：
  The last few years have brought advances in computer vision at an amazing pace, grounded on new findings in deep neural network construction and training as well as the availability of large labeled datasets. Applying these networks to images demands a high computational effort and pushes the use of state-of-the-art networks on real-time video data out of reach of embedded platforms. Many recent works focus on reducing network complexity for real-time inference on embedded computing platforms. We adopt an orthogonal viewpoint and propose a novel algorithm exploiting the spatio-temporal sparsity of pixel changes. This optimized inference procedure resulted in an average speed-up of 9.1x over cuDNN on the Tegra X2 platform at a negligible accuracy loss of <0.1% and no retraining of the network for a semantic segmentation application. Similarly, an average speed-up of 7.0x has been achieved for a pose detection DNN and a reduction of 5x of the number of arithmetic operations to be performed for object detection on static camera video surveillance data. These throughput gains combined with a lower power consumption result in an energy efficiency of 511 GOp/s/W compared to 70 GOp/s/W for the baseline.
---
PDF链接：
https://arxiv.org/pdf/1808.05488