Proceedings of the 4th International Workshop on Embedded and Mobile Deep Learning最新文献

Classifying WLAN Packets from the RF Envelope: Towards More Efficient Wireless Network Performance 从射频信封中对WLAN数据包进行分类:实现更高效的无线网络性能

Proceedings of the 4th International Workshop on Embedded and Mobile Deep Learning Pub Date : 2020-09-21 DOI: 10.1145/3410338.3412337

Zerina Kapetanovic, Gregory E. Moore, S. Garman, Joshua R. Smith

引用次数: 1

Amplitude Suppression and Direction Activation in Networks for 1-bit Faster R-CNN 1位更快R-CNN网络的幅度抑制和方向激活

Proceedings of the 4th International Workshop on Embedded and Mobile Deep Learning Pub Date : 2020-09-21 DOI: 10.1145/3410338.3412340

Sheng Xu, Zhendong Liu, Xuan Gong, Chunlei Liu, Mingyuan Mao, Baochang Zhang

{"title":"Amplitude Suppression and Direction Activation in Networks for 1-bit Faster R-CNN","authors":"Sheng Xu, Zhendong Liu, Xuan Gong, Chunlei Liu, Mingyuan Mao, Baochang Zhang","doi":"10.1145/3410338.3412340","DOIUrl":"https://doi.org/10.1145/3410338.3412340","url":null,"abstract":"Recent advances in object detection have been driven by the success of deep convolutional neural networks (DCNNs). Deploying a DCNN detector on resource-limited hardware such as embedded devices and smart phones, however, remains challenging due to the massive number of parameters a typical model contains. In this paper, we propose an amplitude suppression and direction activation for Faster R-CNN (ASDA-FRCNN) framework to significantly compress DCNNs for highly efficient performance. The shared amplitude between the full-precision and the binary kernels can be significantly suppressed through a simple but effective loss, which is then incorporated into the existing Faster R-CNN detector. Furthermore, the ASDA module is generic and flexible to be incorporated into existing DCNNs for different tasks. Experiments demonstrate the superiority of 1-bit ASDA-FRCNN which achieves superior performance on various datasets. Specifically, ASDA-FRCNN shows the best speed-accuracy trade off with 63.4% at estimated 711 FPS and 19.4% mAP at and estimated 362 FPS with ResNet-18 on the PASCAL VOC 2007 and MS COCO validation datasets respectively, which demonstrate the superior performance and strong generalization of our method.","PeriodicalId":401260,"journal":{"name":"Proceedings of the 4th International Workshop on Embedded and Mobile Deep Learning","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116546878","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: 8

Hybrid Fusion Learning: A Hierarchical Learning Model For Distributed Systems 混合融合学习:分布式系统的分层学习模型

Proceedings of the 4th International Workshop on Embedded and Mobile Deep Learning Pub Date : 2020-09-21 DOI: 10.1145/3410338.3412339

Anirudh Kasturi, Anish Reddy Ellore, Paresh Saxena, C. Hota

{"title":"Hybrid Fusion Learning: A Hierarchical Learning Model For Distributed Systems","authors":"Anirudh Kasturi, Anish Reddy Ellore, Paresh Saxena, C. Hota","doi":"10.1145/3410338.3412339","DOIUrl":"https://doi.org/10.1145/3410338.3412339","url":null,"abstract":"Federated and fusion learning methods are state-of-the-art distributed learning approaches which enable model training without collecting private data from users. While federated learning involves lower computation cost as compared to fusion learning, the overall communication cost is higher due to a large number of communication rounds between the clients and the server. On the other hand, fusion learning reduces the overall communication cost by sending distributions of features and model parameters using only one communication round but suffers from high computation cost as it needs to find the distributions of features at the client. This paper presents hybrid fusion learning, a system that leverages hierarchical client-edge-cloud architecture and builds a deep learning model by integrating both fusion and federated learning methods. Our proposed approach uses fusion learning between the client and the edge layer to minimise the communication cost whereas it uses federated learning between the edge and the cloud layer to minimise the computation cost. Our results show that the proposed hybrid fusion learning can significantly reduce the total time taken to train the model with a small drop of around 2% in accuracies as compared to the other two algorithms. Specifically, our results show that fusion and federated learning algorithms take up to 26.28% and 9.74% higher average total time to build the model, respectively, than the proposed hybrid fusion learning approach.","PeriodicalId":401260,"journal":{"name":"Proceedings of the 4th International Workshop on Embedded and Mobile Deep Learning","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132130467","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: 1

Split Computing for Complex Object Detectors: Challenges and Preliminary Results 复杂目标检测器的分离计算:挑战和初步结果

Proceedings of the 4th International Workshop on Embedded and Mobile Deep Learning Pub Date : 2020-07-27 DOI: 10.1145/3410338.3412338

Yoshitomo Matsubara, M. Levorato

引用次数: 11

Proceedings of the 4th International Workshop on Embedded and Mobile Deep Learning 第四届嵌入式和移动深度学习国际研讨会论文集

Proceedings of the 4th International Workshop on Embedded and Mobile Deep Learning Pub Date : 1900-01-01 DOI: 10.1145/3410338

引用次数: 0