DNN-SAM: Split-and-Merge DNN Execution for Real-Time Object Detection
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Kang, Woosung | - |
dc.contributor.author | Chung, Siwoo | - |
dc.contributor.author | Kim, Jeremy Yuhyun | - |
dc.contributor.author | Lee, Youngmoon | - |
dc.contributor.author | Lee, Kilho | - |
dc.contributor.author | Lee, Jinkyu | - |
dc.contributor.author | Shin, Kang G. | - |
dc.contributor.author | Chwa, Hoon Sung | - |
dc.date.accessioned | 2023-07-05T05:46:13Z | - |
dc.date.available | 2023-07-05T05:46:13Z | - |
dc.date.issued | 2022-06 | - |
dc.identifier.issn | 1545-3421 | - |
dc.identifier.uri | https://scholarworks.bwise.kr/erica/handle/2021.sw.erica/113321 | - |
dc.description.abstract | As real-time object detection systems, such as autonomous cars, need to process input images acquired from multiple cameras, they face significant challenges in delivering accurate and timely inferences often based on machine learning (ML). To meet these challenges, we want to provide different levels of object detection accuracy and timeliness to different portions within each input image with different criticality levels. Specifically, we develop DNN-SAM, a dynamic Split-And-Merge Deep Neural Network (DNN) execution and scheduling framework, that enables seamless split-and-merge DNN execution for unmodified DNN models. Instead of processing an entire input image once in a full DNN model, DNN-SAM first splits a DNN inference task into two smaller sub-tasks-a mandatory sub-task dedicated for a safety-critical (cropped) portion of each image and an optional sub-task for processing a down-scaled image-then executes them independently, and finally merges their results into a complete inference. To achieve DNN-SAM's timely and accurate detection of objects in each image, we also develop two scheduling algorithms that prioritize sub-tasks according to their criticality levels and adaptively adjust the scale of the input image to meet the timing constraints while minimizing the response time of mandatory sub-tasks or maximizing the accuracy of optional sub-tasks. We have implemented and evaluated DNN-SAM on a representative ML framework. Our evaluation shows DNN-SAM to improve detection accuracy in the safety-critical region by 2.0-3.7x and lower average inference latency by 4.8-9.7x over existing approaches without violating any timing constraints. | - |
dc.format.extent | 13 | - |
dc.language | 영어 | - |
dc.language.iso | ENG | - |
dc.publisher | IEEE | - |
dc.title | DNN-SAM: Split-and-Merge DNN Execution for Real-Time Object Detection | - |
dc.type | Article | - |
dc.publisher.location | 미국 | - |
dc.identifier.doi | 10.1109/RTAS54340.2022.00021 | - |
dc.identifier.scopusid | 2-s2.0-85133653851 | - |
dc.identifier.wosid | 000951295600013 | - |
dc.identifier.bibliographicCitation | 2022 IEEE 28th Real-Time and Embedded Technology and Applications Symposium (RTAS), pp 160 - 172 | - |
dc.citation.title | 2022 IEEE 28th Real-Time and Embedded Technology and Applications Symposium (RTAS) | - |
dc.citation.startPage | 160 | - |
dc.citation.endPage | 172 | - |
dc.type.docType | Proceedings Paper | - |
dc.description.isOpenAccess | N | - |
dc.description.journalRegisteredClass | scopus | - |
dc.relation.journalResearchArea | Computer Science | - |
dc.relation.journalWebOfScienceCategory | Computer Science, Theory & Methods | - |
dc.subject.keywordPlus | VISION | - |
dc.identifier.url | https://ieeexplore.ieee.org/document/9804671?arnumber=9804671&SID=EBSCO:edseee | - |
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.
55 Hanyangdeahak-ro, Sangnok-gu, Ansan, Gyeonggi-do, 15588, Korea+82-31-400-4269 sweetbrain@hanyang.ac.kr
COPYRIGHT © 2021 HANYANG UNIVERSITY. ALL RIGHTS RESERVED.
Certain data included herein are derived from the © Web of Science of Clarivate Analytics. All rights reserved.
You may not copy or re-distribute this material in whole or in part without the prior written consent of Clarivate Analytics.