Proceedings of the 5th International Workshop on Embedded and Mobile Deep Learning最新文献

Battery-Free Camera Occupancy Detection System 无电池摄像头占用检测系统

Proceedings of the 5th International Workshop on Embedded and Mobile Deep Learning Pub Date : 2021-06-25 DOI: 10.1145/3469116.3470013

Ali Saffari, Sin Yong Tan, Mohamad Katanbaf, Homagni Saha, Joshua R. Smith, S. Sarkar

引用次数: 12

Are Mobile DNN Accelerators Accelerating DNNs? 移动深度神经网络加速器加速深度神经网络吗?

Proceedings of the 5th International Workshop on Embedded and Mobile Deep Learning Pub Date : 2021-06-24 DOI: 10.1145/3469116.3470011

Qingqing Cao, Alexandru Eugen Irimiea, Mohamed Abdelfattah, A. Balasubramanian, N. Lane

引用次数: 6

Towards Ubiquitous Learning: A First Measurement of On-Device Training Performance 走向泛在学习:设备上训练性能的第一个测量

Proceedings of the 5th International Workshop on Embedded and Mobile Deep Learning Pub Date : 2021-06-24 DOI: 10.1145/3469116.3470009

Dongqi Cai, Qipeng Wang, Yuanqiang Liu, Yunxin Liu, Shangguang Wang, Mengwei Xu

引用次数: 9

Benchmarking Video Object Detection Systems on Embedded Devices under Resource Contention 资源竞争下嵌入式设备视频目标检测系统的基准测试

Proceedings of the 5th International Workshop on Embedded and Mobile Deep Learning Pub Date : 2021-06-24 DOI: 10.1145/3469116.3470010

Jayoung Lee, Pengcheng Wang, Ran Xu, Venkateswara Dasari, Noah Weston, Yin Li, S. Bagchi, S. Chaterji

{"title":"Benchmarking Video Object Detection Systems on Embedded Devices under Resource Contention","authors":"Jayoung Lee, Pengcheng Wang, Ran Xu, Venkateswara Dasari, Noah Weston, Yin Li, S. Bagchi, S. Chaterji","doi":"10.1145/3469116.3470010","DOIUrl":"https://doi.org/10.1145/3469116.3470010","url":null,"abstract":"Adaptive and efficient computer vision systems have been proposed to make computer vision tasks, e.g., object classification and object detection, optimized for embedded boards or mobile devices. These studies focus on optimizing the model (deep network) or system itself, by designing an efficient network architecture or adapting the network architecture at runtime using approximation knobs, such as image size, type of object tracker, head of the object detector (e.g., lighter-weight heads such as one-shot object detectors like YOLO over two-shot object detectors like FRCNN). In this work, we benchmark different video object detection protocols, including FastAdapt, with respect to accuracy, latency, and energy consumption on three different embedded boards that represent the leading edge mobile GPUs. Our set of protocols consists of Faster R-CNN, YOLOv3, SELSA, MEGA, and REPP. Further, we characterize their performance under different levels of resource contention, specifically GPU contention, as would arise due to co-located applications on these boards, contending with the video object detection task. Our key insights are that object detectors have to be coupled with trackers to keep up with the latency requirements (e.g., 30 fps). With this, FastAdapt achieves up to 76 fps on the most well-resourced NVIDIA Jetson-class board---the NVIDIA AGX Xavier. Second, adaptive protocols like FastAdapt, FRCNN, and YOLO (specifically our adaptive variants, FRCNN+ and YOLO+) work well under resource constraints. Among the latest video object detection heads, SELSA achieves the highest accuracy but at a latency of over 2 sec per frame. Our energy consumption experiments bring out that FastAdapt, adaptive FRCNN, and adaptive YOLO are best-in-class, relative to the non-adaptive protocols SELSA, MEGA, and REPP.","PeriodicalId":162801,"journal":{"name":"Proceedings of the 5th International Workshop on Embedded and Mobile Deep Learning","volume":"235 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134072321","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 11

Enabling Binary Neural Network Training on the Edge 启用边缘二进制神经网络训练

Proceedings of the 5th International Workshop on Embedded and Mobile Deep Learning Pub Date : 2021-06-24 DOI: 10.1145/3469116.3470015

Erwei Wang, James J. Davis, Daniele Moro, Piotr Zielinski, Jia Jie Lim, Claudionor José Nunes Coelho, Satrajit Chatterjee, Peter Y. K. Cheung, G. Constantinides

引用次数: 11

ParallelFusion ParallelFusion

Proceedings of the 5th International Workshop on Embedded and Mobile Deep Learning Pub Date : 2021-06-24 DOI: 10.1145/3469116.3470014

Jingyu Lee, Yunxin Liu, Youngki Lee

引用次数: 4

Adaptive Inference through Early-Exit Networks: Design, Challenges and Directions 早期退出网络的自适应推理:设计、挑战和方向

Proceedings of the 5th International Workshop on Embedded and Mobile Deep Learning Pub Date : 2021-06-09 DOI: 10.1145/3469116.3470012

Stefanos Laskaridis, Alexandros Kouris, N. Lane

引用次数: 56