Presentation | 2023-05-19 Evaluation of Multi-edge Object Detection System using Deep Feature Compression Transmission Kohji Yamada, Yuichiro Kora, Meguru Yamazaki, Xuying Lei, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | Collaborative Intelligence has been proposed to divide DNN model and perform inferences collaborating on edge and cloud. Deep feature compression transmission has been developed to extract deep feature by executing the first half of the DNN model at the edge and compress the deep feature by Autoencoder and transmit the compressed deep feature to cloud and restore the compressed deep feature and execute the second half of the DNN model. It has been confirmed that the deep feature compression transmission technology can perform inference with low delay in a one-to-one configuration between an edge device and a server. In this paper, we report the performance evaluation of a deep feature compression transmission system, such as a video monitoring system, in which multiple edge devices are connected to a single server. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Deep Feature Compression Transmission / Deep Learning / Low Latency, / Collaborative Intelligence |
Paper # | SeMI2023-13 |
Date of Issue | 2023-05-11 (SeMI) |
Conference Information | |
Committee | SeMI / IPSJ-ITS / IPSJ-MBL / IPSJ-DPS |
---|---|
Conference Date | 2023/5/18(2days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | Okinawa Institute of Science and Technology (OIST) |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | |
Chair | Koji Yamamoto(Kyoto Univ.) / Yuichi Tokunaga(Kanazawa Institute of Technology) / Hirozumi Yamaguchi(Osaka University) / Takuo Suganuma(Tohoku University) |
Vice Chair | Kazuya Monden(Hitachi) / Yasunori Owada(NICT) / Shunsuke Saruwatari(Osaka Univ.) |
Secretary | Kazuya Monden(NTT DOCOMO) / Yasunori Owada(Tokyo Univ. of Agri. and Tech.) / Shunsuke Saruwatari(Osaka Univ.) |
Assistant | Yuki Matsuda(NAIST) / Akihito Taya(Aoyama Gakuin Univ.) / Takeshi Hirai(Osaka Univ.) |
Paper Information | |
Registration To | Technical Committee on Sensor Network and Mobile Intelligence / Special Interest Group on Intelligent Transport Systems and Smart Community / Special Interest Group on Mobile Computing and Smart Society System / Special Interest Group on Distributed Processing System |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Evaluation of Multi-edge Object Detection System using Deep Feature Compression Transmission |
Sub Title (in English) | |
Keyword(1) | Deep Feature Compression Transmission |
Keyword(2) | Deep Learning |
Keyword(3) | Low Latency, |
Keyword(4) | Collaborative Intelligence |
1st Author's Name | Kohji Yamada |
1st Author's Affiliation | Fujitsu Limited(Fujitsu) |
2nd Author's Name | Yuichiro Kora |
2nd Author's Affiliation | Fujitsu Limited(Fujitsu) |
3rd Author's Name | Meguru Yamazaki |
3rd Author's Affiliation | Fujitsu Limited(Fujitsu) |
4th Author's Name | Xuying Lei |
4th Author's Affiliation | Fujitsu Limited(Fujitsu) |
Date | 2023-05-19 |
Paper # | SeMI2023-13 |
Volume (vol) | vol.123 |
Number (no) | SeMI-31 |
Page | pp.pp.53-57(SeMI), |
#Pages | 5 |
Date of Issue | 2023-05-11 (SeMI) |