{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,8]],"date-time":"2025-10-08T16:23:17Z","timestamp":1759940597299,"version":"3.41.0"},"reference-count":31,"publisher":"Association for Computing Machinery (ACM)","issue":"5","license":[{"start":{"date-parts":[[2024,8,28]],"date-time":"2024-08-28T00:00:00Z","timestamp":1724803200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Embed. Comput. Syst."],"published-print":{"date-parts":[[2024,9,30]]},"abstract":"<jats:p>The current times ask for resource-constrained devices such as drones, light mobile robots, XR glasses, or mobile phones to perform object detection efficiently and in real time. However, when executed on the device, object detection fails to achieve the accuracy requirements. In addition, depending on a powerful edge to offload computation is time-consuming as it requires the transmission of a large amount of data and limits the usage in degraded network conditions. In this article, we propose OffloaD, a novel offloading scheduler based on the detection of failures for object detection. The method addresses the problem of offloading between a resource-constrained device and an edge by leveraging the accuracy of the object detection model at the device and the network conditions. Accuracy is considered through a detection failure metric that consists of introspective, golden, and latency scores. Our main contribution is the offloading scheduler based on the detection of failures of the object detector, which reduces unnecessary data transmission without accuracy degradation. Our method demonstrates that offloading to expensive detectors will not always increase performance and enables detection results and failure estimations even if the network is degraded or unavailable. We implement OffloaD in a physical testbed and perform extensive comparisons against several baselines. The experiments suggest that our approach improves the overall precision-latency performance by reducing the end-to-end latency between 18% and 37% in ideal network conditions and a low latency increase in degraded network conditions while obtaining an accuracy with minimum degradation compared to the baselines. In addition, comparisons to related work methods demonstrate the state-of-the-art performance of OffloaD.<\/jats:p>","DOI":"10.1145\/3677321","type":"journal-article","created":{"date-parts":[[2024,7,30]],"date-time":"2024-07-30T11:44:13Z","timestamp":1722339853000},"page":"1-26","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["OffloaD: Detection Failure-based Scheduler for Offloading Object Detection"],"prefix":"10.1145","volume":"23","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4859-5053","authenticated-orcid":false,"given":"Clara","family":"Gomez","sequence":"first","affiliation":[{"name":"Ericsson Research, Ericsson AB, Stockholm, Sweden"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-5049-5491","authenticated-orcid":false,"given":"Davron","family":"Patkhullaev","sequence":"additional","affiliation":[{"name":"Ericsson Research, Ericsson AB, Stockholm Sweden and KTH Royal Institute of Technology, Stockholm, Sweden"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1398-1296","authenticated-orcid":false,"given":"Alejandra C.","family":"Hernandez","sequence":"additional","affiliation":[{"name":"Ericsson Research, Ericsson AB, Stockholm, Sweden"}]}],"member":"320","published-online":{"date-parts":[[2024,8,28]]},"reference":[{"key":"e_1_3_3_2_2","doi-asserted-by":"publisher","DOI":"10.1145\/3510831"},{"key":"e_1_3_3_3_2","first-page":"96","volume-title":"ACM Conference on Embedded Networked Sensor Systems (SenSys)","author":"Apicharttrisorn Kittipat","year":"2019","unstructured":"Kittipat Apicharttrisorn, Xukan Ran, Jiasi Chen, Srikanth V. Krishnamurthy, and Amit K. Roy-Chowdhury. 2019. Frugal following: Power thrifty object detection and tracking for mobile augmented reality. In ACM Conference on Embedded Networked Sensor Systems (SenSys). 96\u2013109."},{"key":"e_1_3_3_4_2","article-title":"YOLOv4: Optimal speed and accuracy of object detection","author":"Bochkovskiy Alexey","year":"2020","unstructured":"Alexey Bochkovskiy, Chien-Yao Wang, and Hong-Yuan Mark Liao. 2020. YOLOv4: Optimal speed and accuracy of object detection. arXiv (2020).","journal-title":"arXiv"},{"key":"e_1_3_3_5_2","article-title":"SmartDet: Context-aware dynamic control of edge task offloading for mobile object detection","author":"Callegaro Davide","year":"2022","unstructured":"Davide Callegaro, Francesco Restuccia, and Marco Levorato. 2022. SmartDet: Context-aware dynamic control of edge task offloading for mobile object detection. arXiv (2022).","journal-title":"arXiv"},{"key":"e_1_3_3_6_2","first-page":"155","volume-title":"ACM Conference on Embedded Networked Sensor Systems (SenSys)","author":"Chen Tiffany Yu-Han","year":"2015","unstructured":"Tiffany Yu-Han Chen, Lenin Ravindranath, Shuo Deng, Paramvir Bahl, and Hari Balakrishnan. 2015. Glimpse: Continuous, real-time object recognition on mobile devices. In ACM Conference on Embedded Networked Sensor Systems (SenSys). 155\u2013168."},{"key":"e_1_3_3_7_2","first-page":"1743","volume-title":"IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","author":"Daftry Shreyansh","year":"2016","unstructured":"Shreyansh Daftry, Sam Zeng, J. Andrew Bagnell, and Martial Hebert. 2016. Introspective perception: Learning to predict failures in vision systems. In IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS). IEEE, 1743\u20131750."},{"key":"e_1_3_3_8_2","first-page":"1","volume-title":"IEEE INFOCOM Conference on Computer Communications","author":"Hanyao Mengxi","year":"2021","unstructured":"Mengxi Hanyao, Yibo Jin, Zhuzhong Qian, Sheng Zhang, and Sanglu Lu. 2021. Edge-assisted online on-device object detection for real-time video analytics. In IEEE INFOCOM Conference on Computer Communications. 1\u201310."},{"key":"e_1_3_3_9_2","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3062319"},{"key":"e_1_3_3_10_2","first-page":"2366","volume-title":"IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Hore Alain","year":"2010","unstructured":"Alain Hore and Djemel Ziou. 2010. Image quality metrics: PSNR vs. SSIM. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 2366\u20132369."},{"key":"e_1_3_3_11_2","first-page":"1314","volume-title":"IEEE\/CVF International Conference on Computer Vision (ICCV)","year":"2019","unstructured":"Andrew Howard, Mark Sandler, Grace Chu, Liang-Chieh Chen, Bo Chen, Mingxing Tan, Weijun Wang, Yukun Zhu, Ruoming Pang, Vijay Vasudevan, Quoc V. Le, and Hartwig Adam. 2019. Searching for mobilenetv3. In IEEE\/CVF International Conference on Computer Vision (ICCV). 1314\u20131324."},{"key":"e_1_3_3_12_2","doi-asserted-by":"publisher","DOI":"10.1145\/3230543.3230574"},{"issue":"1","key":"e_1_3_3_13_2","doi-asserted-by":"crossref","first-page":"177","DOI":"10.1109\/MNET.011.2000248","article-title":"Edge-network-assisted real-time object detection framework for autonomous driving","volume":"35","author":"Kim Seung-Wook","year":"2021","unstructured":"Seung-Wook Kim, Keunsoo Ko, Haneul Ko, and Victor C. M. Leung. 2021. Edge-network-assisted real-time object detection framework for autonomous driving. IEEE Network 35, 1 (2021), 177\u2013183.","journal-title":"IEEE Network"},{"key":"e_1_3_3_14_2","first-page":"1","volume-title":"Annual International Conference on Mobile Computing and Networking (MobiCom)","author":"Liu Luyang","year":"2019","unstructured":"Luyang Liu, Hongyu Li, and Marco Gruteser. 2019. Edge assisted real-time object detection for mobile augmented reality. In Annual International Conference on Mobile Computing and Networking (MobiCom). 1\u201316."},{"key":"e_1_3_3_15_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_8"},{"key":"e_1_3_3_16_2","doi-asserted-by":"publisher","DOI":"10.1109\/JSYST.2022.3188997"},{"key":"e_1_3_3_17_2","first-page":"4839","volume-title":"IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","author":"Rahman Quazi Marufur","year":"2021","unstructured":"Quazi Marufur Rahman, Niko S\u00fcnderhauf, and Feras Dayoub. 2021. Online monitoring of object detection performance during deployment. In IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS). IEEE, 4839\u20134845."},{"key":"e_1_3_3_18_2","first-page":"152","volume-title":"IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Rahman Quazi Marufur","year":"2021","unstructured":"Quazi Marufur Rahman, Niko Sunderhauf, and Feras Dayoub. 2021. Per-frame mAP prediction for continuous performance monitoring of object detection during deployment. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 152\u2013160."},{"key":"e_1_3_3_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2857402"},{"key":"e_1_3_3_20_2","first-page":"1421","volume-title":"IEEE INFOCOM Conference on Computer Communications","author":"Ran Xukan","year":"2018","unstructured":"Xukan Ran, Haolianz Chen, Xiaodan Zhu, Zhenming Liu, and Jiasi Chen. 2018. Deepdecision: A mobile deep learning framework for edge video analytics. In IEEE INFOCOM Conference on Computer Communications. 1421\u20131429."},{"key":"e_1_3_3_21_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"e_1_3_3_22_2","first-page":"4510","volume-title":"IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Sandler Mark","year":"2018","unstructured":"Mark Sandler, Andrew Howard, Menglong Zhu, Andrey Zhmoginov, and Liang-Chieh Chen. 2018. Mobilenetv2: Inverted residuals and linear bottlenecks. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 4510\u20134520."},{"key":"e_1_3_3_23_2","first-page":"1","volume-title":"IEEE INFOCOM Conference on Computer Communications","author":"Wang Xu","year":"2021","unstructured":"Xu Wang, Zheng Yang, Jiahang Wu, Yi Zhao, and Zimu Zhou. 2021. Edgeduet: Tiling small object detection for edge assisted autonomous mobile vision. In IEEE INFOCOM Conference on Computer Communications. 1\u201310."},{"key":"e_1_3_3_24_2","article-title":"Video Test Media","year":"2017","unstructured":"XIPH.org. 2017. Video Test Media. https:\/\/media.xiph.org\/video\/derf\/. (2017).","journal-title":"https:\/\/media.xiph.org\/video\/derf\/"},{"key":"e_1_3_3_25_2","first-page":"2528","volume-title":"IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Xu Ran","year":"2022","unstructured":"Ran Xu, Fangzhou Mu, Jayoung Lee, Preeti Mukherjee, Somali Chaterji, Saurabh Bagchi, and Yin Li. 2022. SMARTADAPT: Multi-branch Object detection framework for videos on mobiles. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 2528\u20132538."},{"key":"e_1_3_3_26_2","first-page":"449","volume-title":"ACM Conference on Embedded Networked Sensor Systems (SenSys)","author":"Xu Ran","year":"2020","unstructured":"Ran Xu, Chen-lin Zhang, Pengcheng Wang, Jayoung Lee, Subrata Mitra, Somali Chaterji, Yin Li, and Saurabh Bagchi. 2020. ApproxDet: Content and contention-aware approximate object detection for mobiles. In ACM Conference on Embedded Networked Sensor Systems (SenSys). 449\u2013462."},{"issue":"12","key":"e_1_3_3_27_2","doi-asserted-by":"crossref","first-page":"9878","DOI":"10.1109\/JIOT.2020.3016694","article-title":"Offloading optimization in edge computing for deep-learning-enabled target tracking by internet of UAVs","volume":"8","author":"Yang Bo","year":"2020","unstructured":"Bo Yang, Xuelin Cao, Chau Yuen, and Lijun Qian. 2020. Offloading optimization in edge computing for deep-learning-enabled target tracking by internet of UAVs. IEEE Internet of Things Journal 8, 12 (2020), 9878\u20139893.","journal-title":"IEEE Internet of Things Journal"},{"key":"e_1_3_3_28_2","first-page":"1898","volume-title":"IEEE INFOCOM Conference on Computer Communications","author":"Yang Kichang","year":"2022","unstructured":"Kichang Yang, Juheon Yi, Kyungjin Lee, and Youngki Lee. 2022. FlexPatch: Fast and accurate object detection for on-device high-resolution live video analytics. In IEEE INFOCOM Conference on Computer Communications. 1898\u20131907."},{"key":"e_1_3_3_29_2","article-title":"COCA: Contrastive captioners are image-text foundation models","author":"Yu Jiahui","year":"2022","unstructured":"Jiahui Yu, Zirui Wang, Vijay Vasudevan, Legg Yeung, Mojtaba Seyedhosseini, and Yonghui Wu. 2022. COCA: Contrastive captioners are image-text foundation models. arXiv (2022).","journal-title":"arXiv"},{"key":"e_1_3_3_30_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3157876"},{"key":"e_1_3_3_31_2","first-page":"3566","volume-title":"IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Zhang Peng","year":"2014","unstructured":"Peng Zhang, Jiuling Wang, Ali Farhadi, Martial Hebert, and Devi Parikh. 2014. Predicting failures of vision systems. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 3566\u20133573."},{"key":"e_1_3_3_32_2","article-title":"MR-DRO: A fast and efficient task offloading algorithm in heterogeneous edge\/cloud computing environments","author":"Zhang Ziru","year":"2021","unstructured":"Ziru Zhang, Nianfu Wang, Huaming Wu, Chaogang Tang, and Ruidong Li. 2021. MR-DRO: A fast and efficient task offloading algorithm in heterogeneous edge\/cloud computing environments. IEEE Internet of Things Journal (2021).","journal-title":"IEEE Internet of Things Journal"}],"container-title":["ACM Transactions on Embedded Computing Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3677321","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3677321","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:04:21Z","timestamp":1750291461000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3677321"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8,28]]},"references-count":31,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2024,9,30]]}},"alternative-id":["10.1145\/3677321"],"URL":"https:\/\/doi.org\/10.1145\/3677321","relation":{},"ISSN":["1539-9087","1558-3465"],"issn-type":[{"type":"print","value":"1539-9087"},{"type":"electronic","value":"1558-3465"}],"subject":[],"published":{"date-parts":[[2024,8,28]]},"assertion":[{"value":"2023-11-27","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-06-18","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-08-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}