{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,9]],"date-time":"2026-04-09T14:44:15Z","timestamp":1775745855108,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":57,"publisher":"ACM","license":[{"start":{"date-parts":[[2025,5,6]],"date-time":"2025-05-06T00:00:00Z","timestamp":1746489600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62350710797"],"award-info":[{"award-number":["62350710797"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Science and Technology Plan Project of Shenzhen","award":["JSGG20220831110002004"],"award-info":[{"award-number":["JSGG20220831110002004"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,5,6]]},"DOI":"10.1145\/3715014.3722076","type":"proceedings-article","created":{"date-parts":[[2025,5,4]],"date-time":"2025-05-04T23:37:21Z","timestamp":1746401841000},"page":"385-397","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["E3: Early Exiting with Explainable AI for Real-Time and Accurate DNN Inference in Edge-Cloud Systems"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6805-2649","authenticated-orcid":false,"given":"Changyao","family":"Lin","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, Harbin Institute of Technology, Harbin, Heilongjiang, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-7046-4644","authenticated-orcid":false,"given":"Zhenming","family":"Chen","sequence":"additional","affiliation":[{"name":"China Construction Steel Structure Engineering Co., LTD, Shenzhen, Guangdong, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2539-8257","authenticated-orcid":false,"given":"Ziyang","family":"Zhang","sequence":"additional","affiliation":[{"name":"NESLab, Politecnico di Milano, Milano, Italy"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6209-6886","authenticated-orcid":false,"given":"Jie","family":"Liu","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology, Shenzhen, Guangdong, China"},{"name":"National Key Laboratory of Smart Farm Technologies and Systems, Harbin Institute of Technology, Harbin, Heilongjiang, China"}]}],"member":"320","published-online":{"date-parts":[[2025,5,6]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Soft-to-hard vector quantization for end-to-end learning compressible representations. Advances in neural information processing systems 30","author":"Agustsson Eirikur","year":"2017","unstructured":"Eirikur Agustsson, Fabian Mentzer, Michael Tschannen, Lukas Cavigelli, Radu Timofte, Luca Benini, and Luc V Gool. 2017. Soft-to-hard vector quantization for end-to-end learning compressible representations. Advances in neural information processing systems 30 (2017)."},{"key":"e_1_3_2_1_2_1","unstructured":"Raffaello Bonghi. 2024. jetson-stats. https:\/\/rnext.it\/jetson_stats\/."},{"key":"e_1_3_2_1_3_1","volume-title":"Neural Networks: Tricks of the Trade","author":"Bottou L\u00e9on","unstructured":"L\u00e9on Bottou. 2012. Stochastic gradient descent tricks. In Neural Networks: Tricks of the Trade: Second Edition. Springer, 421--436."},{"key":"e_1_3_2_1_4_1","volume-title":"International Conference on Machine Learning. PMLR, 3577--3598","author":"Cao Shengcao","year":"2023","unstructured":"Shengcao Cao, Mengtian Li, James Hays, Deva Ramanan, Yu-Xiong Wang, and Liangyan Gui. 2023. Learning lightweight object detectors via multi-teacher progressive distillation. In International Conference on Machine Learning. PMLR, 3577--3598."},{"key":"e_1_3_2_1_5_1","first-page":"19974","article-title":"Chasing sparsity in vision transformers: An end-to-end exploration","volume":"34","author":"Chen Tianlong","year":"2021","unstructured":"Tianlong Chen, Yu Cheng, Zhe Gan, Lu Yuan, Lei Zhang, and Zhangyang Wang. 2021. Chasing sparsity in vision transformers: An end-to-end exploration. Advances in Neural Information Processing Systems 34 (2021), 19974--19988.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_6_1","volume-title":"LZW data compression. American journal of engineering research 3, 2","author":"Dheemanth HN","year":"2014","unstructured":"HN Dheemanth. 2014. LZW data compression. American journal of engineering research 3, 2 (2014), 22--26."},{"key":"e_1_3_2_1_7_1","first-page":"167","article-title":"Ios: Inter-operator scheduler for cnn acceleration","volume":"3","author":"Ding Yaoyao","year":"2021","unstructured":"Yaoyao Ding, Ligeng Zhu, Zhihao Jia, Gennady Pekhimenko, and Song Han. 2021. Ios: Inter-operator scheduler for cnn acceleration. Proceedings of Machine Learning and Systems 3 (2021), 167--180.","journal-title":"Proceedings of Machine Learning and Systems"},{"key":"e_1_3_2_1_8_1","volume-title":"International Conference on Machine Learning. PMLR, 2793--2803","author":"Dong Yihe","year":"2021","unstructured":"Yihe Dong, Jean-Baptiste Cordonnier, and Andreas Loukas. 2021. Attention is not all you need: Pure attention loses rank doubly exponentially with depth. In International Conference on Machine Learning. PMLR, 2793--2803."},{"key":"e_1_3_2_1_9_1","volume-title":"An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929","author":"Dosovitskiy Alexey","year":"2020","unstructured":"Alexey Dosovitskiy. 2020. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-84858-7"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00447"},{"key":"e_1_3_2_1_13_1","volume-title":"Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531","author":"Hinton Geoffrey","year":"2015","unstructured":"Geoffrey Hinton, Oriol Vinyals, and Jeff Dean. 2015. Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531 (2015)."},{"key":"e_1_3_2_1_14_1","volume-title":"Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861","author":"Howard Andrew G","year":"2017","unstructured":"Andrew G Howard, Menglong Zhu, Bo Chen, Dmitry Kalenichenko, Weijun Wang, Tobias Weyand, Marco Andreetto, and Hartwig Adam. 2017. Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861 (2017)."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3495243.3560551"},{"key":"e_1_3_2_1_17_1","unstructured":"Bert Hubert Jacco Geul and Simon S\u00e9hier. 2020. The Wonder Shaper 1.4.1. https:\/\/github.com\/magnific0\/wondershaper."},{"key":"e_1_3_2_1_18_1","unstructured":"Alexander Jung. 2020. Overview of Augmenters. https:\/\/imgaug.readthedocs.io\/en\/latest\/source\/overview_of_augmenters.html."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3093337.3037698"},{"key":"e_1_3_2_1_20_1","volume-title":"International conference on machine learning. PMLR, 3301--3310","author":"Kaya Yigitcan","year":"2019","unstructured":"Yigitcan Kaya, Sanghyun Hong, and Tudor Dumitras. 2019. Shallow-deep networks: Understanding and mitigating network overthinking. In International conference on machine learning. PMLR, 3301--3310."},{"key":"e_1_3_2_1_21_1","unstructured":"Alex Krizhevsky Geoffrey Hinton et al. 2009. Learning multiple layers of features from tiny images. (2009)."},{"key":"e_1_3_2_1_22_1","volume-title":"Imagenet classification with deep convolutional neural networks. Advances in neural information processing systems 25","author":"Krizhevsky Alex","year":"2012","unstructured":"Alex Krizhevsky, Ilya Sutskever, and Geoffrey E Hinton. 2012. Imagenet classification with deep convolutional neural networks. Advances in neural information processing systems 25 (2012)."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3372224.3419194"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2019.2946140"},{"key":"e_1_3_2_1_25_1","volume-title":"Darts: Differentiable architecture search. arXiv preprint arXiv:1806.09055","author":"Liu Hanxiao","year":"2018","unstructured":"Hanxiao Liu, Karen Simonyan, and Yiming Yang. 2018. Darts: Differentiable architecture search. arXiv preprint arXiv:1806.09055 (2018)."},{"key":"e_1_3_2_1_26_1","volume-title":"Proceedings of the Asian conference on computer vision. 3396--3411","author":"Liu Yufan","year":"2022","unstructured":"Yufan Liu, Jiajiong Cao, Bing Li, Weiming Hu, Jingting Ding, and Liang Li. 2022. Cross-architecture knowledge distillation. In Proceedings of the Asian conference on computer vision. 3396--3411."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.5555\/3104322.3104425"},{"key":"e_1_3_2_1_28_1","unstructured":"NVIDIA. 2015. CUDA Multi-Streams. https:\/\/developer.nvidia.com\/blog\/gpu-pro-tip-cuda-7-streams-simplify-concurrency\/."},{"key":"e_1_3_2_1_29_1","unstructured":"NVIDIA. 2020. GeForce RTX 3080 Family. https:\/\/www.nvidia.com\/en-us\/geforce\/graphics-cards\/30-series\/rtx-3080-3080ti\/."},{"key":"e_1_3_2_1_30_1","unstructured":"NVIDIA. 2020. Multi-Instance GPU. https:\/\/docs.nvidia.com\/datacenter\/tesla\/mig-user-guide\/."},{"key":"e_1_3_2_1_31_1","unstructured":"NVIDIA. 2020. Multi-Process Service. https:\/\/docs.nvidia.com\/deploy\/pdf\/CUDA_Multi_Process_Service_Overview.pdf."},{"key":"e_1_3_2_1_32_1","unstructured":"NVIDIA. 2022. NVIDIA Jetson Nano. https:\/\/www.nvidia.com\/en-us\/autonomous-machines\/embedded-systems\/jetson-nano\/product-development\/."},{"key":"e_1_3_2_1_33_1","unstructured":"NVIDIA. 2022. NVIDIA Jetson Xavier. https:\/\/www.nvidia.com\/en-us\/autonomous-machines\/embedded-systems\/jetson-xavier-series\/."},{"key":"e_1_3_2_1_34_1","volume-title":"Pytorch: An imperative style, high-performance deep learning library. Advances in neural information processing systems 32","author":"Paszke Adam","year":"2019","unstructured":"Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, et al. 2019. Pytorch: An imperative style, high-performance deep learning library. Advances in neural information processing systems 32 (2019)."},{"key":"e_1_3_2_1_35_1","volume-title":"Do vision transformers see like convolutional neural networks? Advances in neural information processing systems 34","author":"Raghu Maithra","year":"2021","unstructured":"Maithra Raghu, Thomas Unterthiner, Simon Kornblith, Chiyuan Zhang, and Alexey Dosovitskiy. 2021. Do vision transformers see like convolutional neural networks? Advances in neural information processing systems 34 (2021), 12116--12128."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939778"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"crossref","unstructured":"Olga Russakovsky Jia Deng Hao Su Jonathan Krause Sanjeev Satheesh Sean Ma Zhiheng Huang Andrej Karpathy Aditya Khosla Michael Bernstein et al. 2015. Imagenet large scale visual recognition challenge. International journal of computer vision 115 (2015) 211--252.","DOI":"10.1007\/s11263-015-0816-y"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"e_1_3_2_1_40_1","volume-title":"Edge computing: Vision and challenges","author":"Shi Weisong","year":"2016","unstructured":"Weisong Shi, Jie Cao, Quan Zhang, Youhuizi Li, and Lanyu Xu. 2016. Edge computing: Vision and challenges. IEEE internet of things journal 3, 5 (2016), 637--646."},{"key":"e_1_3_2_1_41_1","volume-title":"International conference on machine learning. PMLR, 3319--3328","author":"Sundararajan Mukund","year":"2017","unstructured":"Mukund Sundararajan, Ankur Taly, and Qiqi Yan. 2017. Axiomatic attribution for deep networks. In International conference on machine learning. PMLR, 3319--3328."},{"key":"e_1_3_2_1_42_1","volume-title":"International conference on machine learning. PMLR, 10096--10106","author":"Tan Mingxing","year":"2021","unstructured":"Mingxing Tan and Quoc Le. 2021. Efficientnetv2: Smaller models and faster training. In International conference on machine learning. PMLR, 10096--10106."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2016.7900006"},{"key":"e_1_3_2_1_44_1","volume-title":"Path planning for autonomous driving: The state of the art and perspectives. arXiv preprint arXiv:2303.09824","author":"Teng Siyu","year":"2023","unstructured":"Siyu Teng, Peng Deng, Yuchen Li, Bai Li, Xuemin Hu, Zhe Xuanyuan, Long Chen, Yunfeng Ai, Lingxi Li, and Fei-Yue Wang. 2023. Path planning for autonomous driving: The state of the art and perspectives. arXiv preprint arXiv:2303.09824 (2023)."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2019.2907754"},{"key":"e_1_3_2_1_46_1","volume-title":"International conference on machine learning. PMLR, 10347--10357","author":"Touvron Hugo","year":"2021","unstructured":"Hugo Touvron, Matthieu Cord, Matthijs Douze, Francisco Massa, Alexandre Sablayrolles, and Herv\u00e9 J\u00e9gou. 2021. Training data-efficient image transformers & distillation through attention. In International conference on machine learning. PMLR, 10347--10357."},{"key":"e_1_3_2_1_47_1","volume-title":"Attention is all you need. Advances in neural information processing systems 30","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in neural information processing systems 30 (2017)."},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/RTSS59052.2023.00020"},{"key":"e_1_3_2_1_49_1","unstructured":"Wikipedia. 2024. Worst-Case Execution Time. https:\/\/en.wikipedia.org\/wiki\/Worst-case_execution_time."},{"key":"e_1_3_2_1_50_1","volume-title":"Unified visual transformer compression. arXiv preprint arXiv:2203.08243","author":"Yu Shixing","year":"2022","unstructured":"Shixing Yu, Tianlong Chen, Jiayi Shen, Huan Yuan, Jianchao Tan, Sen Yang, Ji Liu, and Zhangyang Wang. 2022. Unified visual transformer compression. arXiv preprint arXiv:2203.08243 (2022)."},{"key":"e_1_3_2_1_51_1","volume-title":"DVFO: Learning-Based DVFS for Energy-Efficient Edge-Cloud Collaborative Inference","author":"Zhang Ziyang","year":"2024","unstructured":"Ziyang Zhang, Yang Zhao, Huan Li, Changyao Lin, and Jie Liu. 2024. DVFO: Learning-Based DVFS for Energy-Efficient Edge-Cloud Collaborative Inference. IEEE Transactions on Mobile Computing (2024)."},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-48424-7_18"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01009"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1145\/3450268.3453520"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1016\/J.ENG.2017.05.015"},{"key":"e_1_3_2_1_56_1","volume-title":"2nd USENIX Workshop on Hot Topics in Edge Computing (HotEdge 19)","author":"Zhou Li","year":"2019","unstructured":"Li Zhou, Hao Wen, Radu Teodorescu, and David HC Du. 2019. Distributing deep neural networks with containerized partitions at the edge. In 2nd USENIX Workshop on Hot Topics in Edge Computing (HotEdge 19)."},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2019.2918951"}],"event":{"name":"SenSys '25: 23rd ACM Conference on Embedded Networked Sensor Systems","location":"UC Irvine Student Center. Irvine CA USA","acronym":"SenSys '25","sponsor":["SIGARCH ACM Special Interest Group on Computer Architecture","SIGMETRICS ACM Special Interest Group on Measurement and Evaluation","SIGOPS ACM Special Interest Group on Operating Systems","SIGMOBILE ACM Special Interest Group on Mobility of Systems, Users, Data and Computing","SIGBED ACM Special Interest Group on Embedded Systems"]},"container-title":["Proceedings of the 23rd ACM Conference on Embedded Networked Sensor Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3715014.3722076","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:56:52Z","timestamp":1750298212000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3715014.3722076"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,6]]},"references-count":57,"alternative-id":["10.1145\/3715014.3722076","10.1145\/3715014"],"URL":"https:\/\/doi.org\/10.1145\/3715014.3722076","relation":{},"subject":[],"published":{"date-parts":[[2025,5,6]]},"assertion":[{"value":"2025-05-06","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}