{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T16:53:02Z","timestamp":1783097582011,"version":"3.54.6"},"reference-count":43,"publisher":"Association for Computing Machinery (ACM)","issue":"5","license":[{"start":{"date-parts":[[2022,9,30]],"date-time":"2022-09-30T00:00:00Z","timestamp":1664496000000},"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":[[2022,9,30]]},"abstract":"<jats:p>\n            In the Internet of Things era, where we see many interconnected and heterogeneous mobile and fixed smart devices, distributing the intelligence from the cloud to the edge has become a necessity. Due to limited computational and communication capabilities, low memory and limited energy budget, bringing artificial intelligence algorithms to peripheral devices, such as end-nodes of a sensor network, is a challenging task and requires the design of innovative solutions. In this work, we present\n            <jats:italic>PhiNets<\/jats:italic>\n            , a new scalable backbone optimized for deep-learning-based image processing on resource-constrained platforms.\n            <jats:italic>PhiNets<\/jats:italic>\n            are based on inverted residual blocks specifically designed to decouple the computational cost, working memory, and parameter memory, thus exploiting all available resources for a given platform. With a YoloV2 detection head and Simple Online and Realtime Tracking (SORT), the proposed architecture achieves state-of-the-art results in (i) detection on the COCO and VOC2012 benchmarks, and (ii) tracking on the MOT15 benchmark.\n            <jats:italic>PhiNets<\/jats:italic>\n            obtain a reduction in parameter count of around 90% with respect to previous state-of-the-art models (EfficientNetv1, MobileNetv2) and achieve better performance with lower computational cost. Moreover, we demonstrate our approach on a prototype node based on an STM32H743 microcontroller (MCU) with 2 MB of internal Flash and 1MB of RAM and achieve power requirements in the order of 10 mW. The code for the\n            <jats:italic>PhiNets<\/jats:italic>\n            is publicly available on GitHub.\n            <jats:xref ref-type=\"fn\">\n              <jats:sup>1<\/jats:sup>\n            <\/jats:xref>\n          <\/jats:p>","DOI":"10.1145\/3510832","type":"journal-article","created":{"date-parts":[[2022,2,3]],"date-time":"2022-02-03T17:31:11Z","timestamp":1643909471000},"page":"1-18","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":45,"title":["PhiNets: A Scalable Backbone for Low-power AI at the Edge"],"prefix":"10.1145","volume":"21","author":[{"given":"Francesco","family":"Paissan","sequence":"first","affiliation":[{"name":"E3DA Unit, Digital Society Center - Fondazione Bruno Kessler (FBK), Trento, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alberto","family":"Ancilotto","sequence":"additional","affiliation":[{"name":"E3DA Unit, Digital Society Center - Fondazione Bruno Kessler (FBK), Trento, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Elisabetta","family":"Farella","sequence":"additional","affiliation":[{"name":"E3DA Unit, Digital Society Center - Fondazione Bruno Kessler (FBK), Trento, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2022,12,9]]},"reference":[{"key":"e_1_3_2_2_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2016.7533003"},{"key":"e_1_3_2_3_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:2004.10934. Retrieved from https:\/\/arxiv.org\/abs\/2004.10934.","journal-title":"arXiv:2004.10934."},{"key":"e_1_3_2_4_2","article-title":"Xnor-net++: Improved binary neural networks","author":"Bulat Adrian","year":"2019","unstructured":"Adrian Bulat and Georgios Tzimiropoulos. 2019. Xnor-net++: Improved binary neural networks. arXiv:1909.13863. Retrieved from https:\/\/arxiv.org\/abs\/1909.13863.","journal-title":"arXiv:1909.13863."},{"key":"e_1_3_2_5_2","unstructured":"Han Cai Chuang Gan and Song Han. 2019. Once for all: Train one network and specialize it for efficient deployment. arXiv:1908.09791. Retrieved from https:\/\/arxiv.org\/abs\/1908.09791."},{"key":"e_1_3_2_6_2","unstructured":"Han Cai Chuang Gan Ligeng Zhu and Song Han. 2020. Tiny transfer learning: Towards memory-efficient on-device learning. arXiv:2007.11622. Retrieved from https:\/\/arxiv.org\/abs\/2007.11622."},{"key":"e_1_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2394"},{"key":"e_1_3_2_8_2","unstructured":"Xiaoliang Dai Peizhao Zhang Bichen Wu Hongxu Yin Fei Sun Yanghan Wang Marat Dukhan Yunqing Hu Yiming Wu Yangqing Jia Peter Vajda Matt Uyttendaele and Niraj K. Jha. 2018. ChamNet: Towards efficient network design through platform-aware model adaptation. arXiv:1812.08934. Retrieved from https:\/\/arxiv.org\/abs\/1812.08934."},{"key":"e_1_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00667"},{"key":"e_1_3_2_10_2","article-title":"The PASCAL Visual Object Classes Challenge 2012 (VOC2012) Results","author":"Everingham M.","unstructured":"M. Everingham, L. Van Gool, C. K. I. Williams, J. Winn, and A. Zisserman. [n. d.]. The PASCAL Visual Object Classes Challenge 2012 (VOC2012) Results. Retrieved from http:\/\/www.pascal-network.org\/challenges\/VOC\/voc2012\/ workshop\/index.html.","journal-title":"Retrieved from http:\/\/www.pascal-network.org\/challenges\/VOC\/voc2012\/ workshop\/index.html."},{"key":"e_1_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.1109\/ASAP.2018.8445101"},{"key":"e_1_3_2_12_2","unstructured":"Raspberry Pi Foundation. [n. d.]. Raspberry Pi Hardware. Retrieved from https:\/\/www.raspberrypi.org\/documen-tation\/hardware\/raspberrypi\/."},{"key":"e_1_3_2_13_2","unstructured":"FriendlyARM. [n. d.]. NanoPi NEO-LTS. Retrieved from https:\/\/www.friendlyarm.com."},{"key":"e_1_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.1098\/rsta.2019.0155"},{"key":"e_1_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/MDAT.2021.3069952"},{"key":"e_1_3_2_16_2","unstructured":"Shayan Hassantabar Prerit Terway and Niraj K. Jha. 2020. TUTOR: Training neural networks using decision rules as model priors. arXiv:2010.05429. Retrieved from https:\/\/arxiv.org\/abs\/2010.05429."},{"key":"e_1_3_2_17_2","unstructured":"Shayan Hassantabar Zeyu Wang and Niraj K. Jha. 2019. SCANN: Synthesis of compact and accurate neural networks. arXiv:1904.09090. Retrieved from https:\/\/arxiv.org\/abs\/1904.09090."},{"key":"e_1_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"e_1_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_20_2","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:1704.04861. Retrieved from https:\/\/arxiv.org\/abs\/1704.04861."},{"key":"e_1_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"e_1_3_2_22_2","doi-asserted-by":"crossref","unstructured":"Arlene John Barry Cardiff and Deepu John. 2021. A 1D-CNN based deep learning technique for sleep apnea detection in IoT sensors. arXiv:2105.00528. Retrieved from https:\/\/arxiv.org\/abs\/2105.00528.","DOI":"10.1109\/ISCAS51556.2021.9401300"},{"key":"e_1_3_2_23_2","unstructured":"Liangzhen Lai Naveen Suda and Vikas Chandra. 2018. Cmsis-nn: Efficient neural network kernels for arm cortex-m cpus. arXiv:1801.06601. Retrieved from https:\/\/arxiv.org\/abs\/1801.06601."},{"key":"e_1_3_2_24_2","unstructured":"Laura Leal-Taix\u00e9 Anton Milan Ian Reid Stefan Roth and Konrad Schindler. 2015. Motchallenge 2015: Towards a benchmark for multi-target tracking. arXiv:504.01942. Retrieved from https:\/\/arxiv.org\/abs\/504.01942."},{"key":"e_1_3_2_25_2","unstructured":"Ji Lin Wei-Ming Chen Yujun Lin John Cohn Chuang Gan and Song Han. 2020. Mcunet: Tiny deep learning on iot devices. arXiv:2007.10319. Retrieved from https:\/\/arxiv.org\/abs\/2007.10319."},{"key":"e_1_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"e_1_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"e_1_3_2_28_2","unstructured":"Arm Ltd.[n. d.]. Cortex-M. Retrieved from https:\/\/developer.arm.com\/ip-products\/processors\/cortex-m."},{"key":"e_1_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.1109\/IWASI.2019.8791337"},{"key":"e_1_3_2_30_2","unstructured":"Francesco Paissan Massimo Gottardi and Elisabetta Farella. 2021. Enabling energy efficient machine learning on a Ultra-Low-Power vision sensor for IoT. arXiv:2102.01340. Retrieved from https:\/\/arxiv.org\/abs\/2102.01340."},{"key":"e_1_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.690"},{"key":"e_1_3_2_32_2","unstructured":"Shaoqing Ren Kaiming He Ross Girshick and Jian Sun. 2015. Faster r-cnn: Towards real-time object detection with region proposal networks. arXiv:1506.01497. Retrieved from https:\/\/arxiv.org\/abs\/1506.01497."},{"key":"e_1_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.1145\/3371157"},{"key":"e_1_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.1145\/3203217.3204463"},{"key":"e_1_3_2_35_2","doi-asserted-by":"publisher","DOI":"10.3390\/s20092638"},{"key":"e_1_3_2_36_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"e_1_3_2_37_2","first-page":"6105","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Tan Mingxing","year":"2019","unstructured":"Mingxing Tan and Quoc Le. 2019. Efficientnet: Rethinking model scaling for convolutional neural networks. In Proceedings of the International Conference on Machine Learning. PMLR, 6105\u20136114."},{"key":"e_1_3_2_38_2","unstructured":"Mingxing Tan and Quoc V. Le. 2021. Efficientnetv2: Smaller models and faster training. arXiv:2104.00298. Retrieved from https:\/\/arxiv.org\/abs\/2104.00298."},{"key":"e_1_3_2_39_2","doi-asserted-by":"crossref","unstructured":"Ganesh Venkatesh Alagappan Valliappan Jay Mahadeokar Yuan Shangguan Christian Fuegen Michael L. Seltzer and Vikas Chandra. 2021. Memory-efficient speech recognition on smart devices. arXiv:2102.11531. Retrieved from https:\/\/arxiv.org\/abs\/2102.11531.","DOI":"10.1109\/ICASSP39728.2021.9414502"},{"key":"e_1_3_2_40_2","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2020.2970550"},{"key":"e_1_3_2_41_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2017.8296962"},{"key":"e_1_3_2_42_2","unstructured":"Dianlei Xu Tong Li Yong Li Xiang Su Sasu Tarkoma Tao Jiang Jon Crowcroft and Pan Hui. 2020. Edge intelligence: Architectures challenges and applications. arXiv:2003.12172. Retrieved from https:\/\/arxiv.org\/abs\/2003.12172."},{"key":"e_1_3_2_43_2","unstructured":"Yifu Zhang Chunyu Wang Xinggang Wang Wenjun Zeng and Wenyu Liu. 2020. FairMOT: On the fairness of detection and re-identification in multiple object tracking. arXiv:2004.01888. Retrieved from https:\/\/arxiv.org\/abs\/2004.01888."},{"key":"e_1_3_2_44_2","unstructured":"Andy Zhou Rikky Muller and Jan M. Rabaey. 2021. Memory-efficient limb position-aware hand gesture recognition using hyperdimensional computing. arXiv:2103.05267. Retrieved from https:\/\/arxiv.org\/abs\/2103.05267."}],"container-title":["ACM Transactions on Embedded Computing Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3510832","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3510832","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T19:02:11Z","timestamp":1750186931000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3510832"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,9,30]]},"references-count":43,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2022,9,30]]}},"alternative-id":["10.1145\/3510832"],"URL":"https:\/\/doi.org\/10.1145\/3510832","relation":{},"ISSN":["1539-9087","1558-3465"],"issn-type":[{"value":"1539-9087","type":"print"},{"value":"1558-3465","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,9,30]]},"assertion":[{"value":"2021-07-27","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-01-07","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-12-09","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}