{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,2]],"date-time":"2026-02-02T14:38:06Z","timestamp":1770043086669,"version":"3.49.0"},"reference-count":50,"publisher":"Association for Computing Machinery (ACM)","issue":"3","license":[{"start":{"date-parts":[[2024,5,11]],"date-time":"2024-05-11T00:00:00Z","timestamp":1715385600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"ACCESS AI Chip Center for Emerging Smart Systems"},{"name":"Stanford Graduate Fellowship in Science & Engineering"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Embed. Comput. Syst."],"published-print":{"date-parts":[[2024,5,31]]},"abstract":"<jats:p>\n            This article studies the merits of applying log-gradient input images to convolutional neural networks (CNNs) for tinyML computer vision (CV). We show that log gradients enable: (i) aggressive 1-bit quantization of first-layer inputs, (ii) potential CNN resource reductions, (iii) inherent insensitivity to illumination changes (1.7% accuracy loss across 2\n            <jats:sup>-5<\/jats:sup>\n            \u2026 2\n            <jats:sup>3<\/jats:sup>\n            brightness variation vs. up to 10% for JPEG), and (iv) robustness to adversarial attacks (&gt;10% higher accuracy than JPEG-trained models). We establish these results using the PASCAL RAW image dataset and through a combination of experiments using quantization threshold search, neural architecture search, and a fixed three-layer network. The latter reveals that training on log-gradient images leads to higher filter similarity, making the CNN more prunable. The combined benefits of aggressive first-layer quantization, CNN resource reductions, and operation without tight exposure control and image signal processing (ISP) are helpful for pushing tinyML CV toward its ultimate efficiency limits.\n          <\/jats:p>","DOI":"10.1145\/3591466","type":"journal-article","created":{"date-parts":[[2023,4,8]],"date-time":"2023-04-08T10:32:16Z","timestamp":1680949936000},"page":"1-20","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":9,"title":["Enhancing the Energy Efficiency and Robustness of tinyML Computer Vision Using Coarsely-quantized Log-gradient Input Images"],"prefix":"10.1145","volume":"23","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0466-5072","authenticated-orcid":false,"given":"Qianyun","family":"Lu","sequence":"first","affiliation":[{"name":"Stanford University, Stanford, United States"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3417-8782","authenticated-orcid":false,"given":"Boris","family":"Murmann","sequence":"additional","affiliation":[{"name":"Stanford University, Stanford, United States"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,5,11]]},"reference":[{"key":"e_1_3_2_2_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2958358"},{"key":"e_1_3_2_3_2","first-page":"284","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Athalye Anish","year":"2018","unstructured":"Anish Athalye, Logan Engstrom, Andrew Ilyas, and Kevin Kwok. 2018. Synthesizing robust adversarial examples. In Proceedings of the International Conference on Machine Learning. PMLR, 284\u2013293."},{"key":"e_1_3_2_4_2","unstructured":"Colby Banbury Vijay Janapa Reddi Peter Torelli Jeremy Holleman Nat Jeffries Csaba Kiraly Pietro Montino David Kanter Sebastian Ahmed Danilo Pau Urmish Thakker Antonio Torrini Peter Warden Jay Cordaro Giuseppe Di Guglielmo Javier Duarte Stephen Gibellini Videet Parekh Honson Tran Nhan Tran Niu Wenxu and Xu Xuesong. 2021. MLPerf Tiny Benchmark. arXiv:2106.07597. Retrieved from https:\/\/arxiv.org\/abs\/2106.07597."},{"key":"e_1_3_2_5_2","first-page":"517","article-title":"MicroNets: Neural network architectures for deploying tinyml applications on commodity microcontrollers","volume":"3","author":"Banbury Colby","year":"2021","unstructured":"Colby Banbury, Chuteng Zhou, Igor Fedorov, Ramon Matas, Urmish Thakker, Dibakar Gope, Vijay Janapa Reddi, Matthew Mattina, and Paul Whatmough. 2021. MicroNets: Neural network architectures for deploying tinyml applications on commodity microcontrollers. Proceedings of Machine Learning and Systems 3 (2021), 517\u2013532.","journal-title":"Proceedings of Machine Learning and Systems"},{"key":"e_1_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.1109\/JSSC.2018.2869150"},{"key":"e_1_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1016\/B978-0-12-813894-6.00010-7"},{"key":"e_1_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.111"},{"key":"e_1_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2017.49"},{"key":"e_1_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.1145\/3128572.3140448"},{"key":"e_1_3_2_11_2","doi-asserted-by":"crossref","unstructured":"Yu Cheng Duo Wang Pan Zhou and Tao Zhang. 2018. Model compression and acceleration for deep neural networks: The principles progress and challenges. IEEE Signal Processing Magazine 35 1 (2018) 126\u2013136.","DOI":"10.1109\/MSP.2017.2765695"},{"key":"e_1_3_2_12_2","unstructured":"Aakanksha Chowdhery Pete Warden Jonathon Shlens Andrew Howard and Rocky Rhodes. 2019. Visual Wake Words Dataset. arXiv:1906.05721. Retrieved from https:\/\/arxiv.org\/abs\/1906.05721."},{"key":"e_1_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2020.2976475"},{"key":"e_1_3_2_15_2","first-page":"119","volume-title":"Proceedings of the NIPS Workshop on EMDNN","author":"Fengfu Li","year":"2016","unstructured":"Li Fengfu, Zhang Bo, and Liu Bin. 2016. Ternary weight networks. In Proceedings of the NIPS Workshop on EMDNN. 119."},{"key":"e_1_3_2_16_2","doi-asserted-by":"crossref","unstructured":"Amir Gholami Sehoon Kim Zhen Dong Zhewei Yao Michael W. Mahoney and Kurt Keutzer. 2022. A survey of quantization methods for efficient neural network inference. Low-Power Computer Vision Chapman and Hall\/CRC 291\u2013326. 10.1201%2F9781003162810-13","DOI":"10.1201\/9781003162810-13"},{"key":"e_1_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.2352\/J.ImagingSci.Technol.2021.65.4.040404"},{"key":"e_1_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9411985"},{"key":"e_1_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1145\/3411808"},{"key":"e_1_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.1109\/VLSIC.2016.7573545"},{"key":"e_1_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC42613.2021.9365788"},{"key":"e_1_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC19947.2020.9063063"},{"key":"e_1_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.1109\/IOLTS.2019.8854377"},{"key":"e_1_3_2_24_2","unstructured":"Alex Krizhevsky and Geoffrey Hinton. 2009. Learning Multiple Layers of Features from Tiny Images. Toronto ON."},{"key":"e_1_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1201\/9781351251389-8"},{"key":"e_1_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.1080\/00031305.2021.2006781"},{"key":"e_1_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.1145\/3437984.3458836"},{"key":"e_1_3_2_28_2","unstructured":"Ji Lin Wei-Ming Chen John Cohn Chuang Gan and Song Han. 2020. MCUNet: Tiny deep learning on iot devices. Annual Conference on Neural Information Processing Systems (NeurIPS) 33 (2020) 11711\u201311722. https:\/\/mcunet.mit.edu\/."},{"key":"e_1_3_2_29_2","unstructured":"Ji Lin Chuang Gan and Song Han. 2019. Defensive quantization: When efficiency meets robustness. International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=ryetZ20ctX."},{"key":"e_1_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.56"},{"key":"e_1_3_2_31_2","unstructured":"Qianyun Lu and Boris Murmann. 2022. Improving the energy efficiency and robustness of tinyML computer vision using log-gradient input images. Proceedings of tinyML Research Symposium (2022)."},{"key":"e_1_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2019.8803645"},{"key":"e_1_3_2_33_2","unstructured":"Aleksander Madry Aleksandar Makelov Ludwig Schmidt Dimitris Tsipras and Adrian Vladu. 2018. Towards deep learning models resistant to adversarial attacks. International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=rJzIBfZAb."},{"key":"e_1_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.13340"},{"key":"e_1_3_2_35_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00141"},{"key":"e_1_3_2_36_2","unstructured":"Markus Nagel Marios Fournarakis Rana Ali Amjad Yelysei Bondarenko Mart Van Baalen and Tijmen Blankevoort. 2021. A white paper on neural network quantization. arXiv:2106.08295. Retrieved from https:\/\/arxiv.org\/abs\/2106.08295."},{"key":"e_1_3_2_37_2","unstructured":"Alex Omid-Zohoor David Ta and Boris Murmann. 2014\u20132015. PASCALRAW: Raw Image Database for Object Detection. Retrieved from http:\/\/purl.stanford.edu\/hq050zr7488. Accessed 04-16-2021."},{"key":"e_1_3_2_38_2","unstructured":"Nicolas Papernot Fartash Faghri Nicholas Carlini Ian Goodfellow Reuben Feinman Alexey Kurakin Cihang Xie Yash Sharma Tom Brown Aurko Roy Alexander Matyasko Vahid Behzadan Karen Hambardzumyan Zhishuai Zhang Yi-Lin Juang Zhi Li Ryan Sheatsley Abhibhav Garg Jonathan Uesato Willi Gierke Yinpeng Dong David Berthelot Paul Hendricks Jonas Rauber Rujun Long and Patrick McDaniel. 2018. Technical report on the cleverhans v2. 1.0 adversarial examples library. arXiv preprint arXiv:1610.00768. Retrieved from https:\/\/arxiv.org\/abs\/1610.00768."},{"key":"e_1_3_2_39_2","doi-asserted-by":"publisher","DOI":"10.1145\/3052973.3053009"},{"key":"e_1_3_2_40_2","unstructured":"Adnan Siraj Rakin Jinfeng Yi Boqing Gong and Deliang Fan. 2018. Defend deep neural networks against adversarial examples via fixed and dynamic quantized activation functions. arXiv:1807.06714. Retrieved from https:\/\/arxiv.org\/abs\/1807.06714."},{"key":"e_1_3_2_41_2","unstructured":"Vijay Janapa Reddi Christine Cheng David Kanter Peter Mattson Guenther Schmuelling Carole-Jean Wu Brian Anderson Maximilien Breughe Mark Charlebois William Chou Ramesh Chukka Cody Coleman Sam Davis Pan Deng Greg Diamos Jared Duke Dave Fick J. Scott Gardner Itay Hubara Sachin Idgunji Thomas B. Jablin Jeff Jiao Tom St. John Pankaj Kanwar David Lee Jeffery Liao Anton Lokhmotov Francisco Massa Peng Meng Paulius Micikevicius Colin Osborne Gennady Pekhimenko Arun Tejusve Raghunath Rajan Dilip Sequeira Ashish Sirasao Fei Sun Hanlin Tang Michael Thomson Frank Wei Ephrem Wu Lingjie Xu Koichi Yamada Bing Yu George Yuan Aaron Zhong Peizhao Zhang and Yuchen Zhou. 2020. MLPerf Inference Benchmark. arXiv:1911.02549. Retrieved from https:\/\/arxiv.org\/abs\/1911.02549."},{"key":"e_1_3_2_42_2","volume-title":"Proceedings of the NIPS Workshop on Deep Learning: Bridging Theory and Practice","author":"Chowdhury Aruni Roy","year":"2017","unstructured":"Aruni Roy Chowdhury, Prakhar Sharma, and Erik G. Learned-Miller. 2017. Reducing duplicate filters in deep neural networks. In Proceedings of the NIPS Workshop on Deep Learning: Bridging Theory and Practice."},{"key":"e_1_3_2_43_2","doi-asserted-by":"publisher","DOI":"10.1109\/DAC18074.2021.9586232"},{"key":"e_1_3_2_44_2","first-page":"4767","volume-title":"Proceedings of the 2020 IEEE International Conference on Robotics and Automation (ICRA\u201920)","year":"2020","unstructured":"Qi She, Fan Feng, Xinyue Hao, Qihan Yang, Chuanlin Lan, Vincenzo Lomonaco, Xuesong Shi, Zhengwei Wang, Yao Guo, Yimin Zhang, Fei Qiao, and Rosa H. M. Chan. 2020. OpenLORIS-Object: A robotic vision dataset and benchmark for lifelong deep learning. In Proceedings of the 2020 IEEE International Conference on Robotics and Automation (ICRA\u201920). IEEE, 4767\u20134773."},{"key":"e_1_3_2_45_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.374"},{"key":"e_1_3_2_46_2","unstructured":"Bram-Ernst Verhoef Nathan Laubeuf Stefan Cosemans Peter Debacker Ioannis Papistas Arindam Mallik and Diederik Verkest. 2019. FQ-Conv: Fully Quantized Convolution for Efficient and Accurate Inference. arXiv:1912.09356. Retrieved from https:\/\/arxiv.org\/abs\/1912.09356."},{"key":"e_1_3_2_47_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-019-1211-x"},{"key":"e_1_3_2_48_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00748"},{"key":"e_1_3_2_49_2","doi-asserted-by":"publisher","DOI":"10.1109\/JSSC.2019.2937437"},{"key":"e_1_3_2_50_2","unstructured":"Chenzhuo Zhu Song Han Huizi Mao and William J. Dally. 2017. Trained ternary quantization. International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=S1_pAu9xl."},{"key":"e_1_3_2_51_2","doi-asserted-by":"publisher","unstructured":"Yuhao Zhu Anand Samajdar Matthew Mattina and Paul Whatmough. 2018. Euphrates: Algorithm-SoC Co-design for low-power mobile continuous vision. Proceedings of the 45th Annual International Symposium on Computer Architecture (ISCA\u201918) IEEE Press Los Angeles CA 547\u2013560. 10.1109\/ISCA.2018.00052","DOI":"10.1109\/ISCA.2018.00052"}],"container-title":["ACM Transactions on Embedded Computing Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3591466","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3591466","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T22:48:47Z","timestamp":1750286927000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3591466"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,11]]},"references-count":50,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2024,5,31]]}},"alternative-id":["10.1145\/3591466"],"URL":"https:\/\/doi.org\/10.1145\/3591466","relation":{},"ISSN":["1539-9087","1558-3465"],"issn-type":[{"value":"1539-9087","type":"print"},{"value":"1558-3465","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,5,11]]},"assertion":[{"value":"2022-10-30","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-04-03","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-05-11","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}