An automotive case study on the limits of approximation for object detection
Authors: 
Martí Caro, Hamid Tabani, Jaume Abella, Francesc Moll, Enric Morancho, 
Ramon Canal, Josep Altet, Antonio Calomarde, 
Francisco J. Cazorla, Antonio Rubio, Pau Fontova, Jordi ForntAuthors Info & Claims
Martí Caro, Hamid Tabani, Jaume Abella, Francesc Moll, Enric Morancho, Ramon Canal, Josep Altet, Antonio Calomarde, Francisco J. Cazorla, Antonio Rubio, Pau Fontova, Jordi ForntAuthors Info & ClaimsReferences
[1]
J. Redmon, A. Farhadi, YOLO9000: Better, Faster, Stronger, in: IEEE Conference on Computer Vision and Pattern Recognition, CVPR, 2017, pp. 6517–6525.
[2]
Redmon Joseph, Farhadi Ali, YOLOv3: An incremental improvement, 2018, ArXiv, abs/1804.02767.
[3]
NVIDIA DRIVE - autonomous vehicle development platforms, 2022, https://developer.nvidia.com/drive. (Accessed October 2022).
[4]
Apollo, an open autonomous driving platform, 2018, https://apollo.auto/.
[5]
O’Shea Keiron, Nash Ryan, An introduction to convolutional neural networks, CoRR, 2015, arXiv:1511.08458.
[6]
Wang H., Jiang X., Ren H., Hu Y., Bai S., SwiftNet: Real-time video object segmentation, in: 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR, IEEE Computer Society, Los Alamitos, CA, USA, 2021, pp. 1296–1305.
[7]
Fang Chaowei, Tian Haibin, Zhang Dingwen, Zhang Qiang, Han Jungong, Han Junwei, Densely nested top-down flows for salient object detection, 2021.
[8]
Chen Guobin, Choi Wongun, Yu Xiang, Han Tony, Chandraker Manmohan, Learning efficient object detection models with knowledge distillation, in: Proceedings of the 31st International Conference on Neural Information Processing Systems, NIPS ’17, Curran Associates Inc., Red Hook, NY, USA, 2017, pp. 742–751.
[9]
Tianqi Tang, Shen Li, Yuan Xie, Norm Jouppi, MPLAT: A Power, Area, Timing Modeling Framework for Machine Learning Accelerators., in: DOSSA Workshop, New York, NY, USA, 2018.
[10]
Jouppi Norman P., et al., In-datacenter performance analysis of a tensor processing unit, in: Proceedings of the 44th Annual International Symposium on Computer Architecture, ISCA ’17, Association for Computing Machinery, New York, NY, USA, 2017, pp. 1–12.
[11]
Wu Chen, Wang Mingyu, Chu Xinyuan, Wang Kun, He Lei, Low-precision floating-point arithmetic for high-performance FPGA-based CNN acceleration, ACM Trans. Reconfigurable Technol. Syst. 15 (1) (2021).
[12]
Zhang Xiangyu, Zou Jianhua, He Kaiming, Sun Jian, Accelerating very deep convolutional networks for classification and detection, 2015.
[13]
Joseph Redmon, Santosh Divvala, Ross Girshick, Ali Farhadi, You Only Look Once: Unified, Real-Time Object Detection, in: 2016 IEEE Conference on Computer Vision and Pattern Recognition, CVPR, 2016, pp. 779–788.
[14]
Mellempudi Naveen, Srinivasan Sudarshan, Das Dipankar, Kaul Bharat, Mixed precision training with 8-bit floating point, 2019.
[15]
Yunji Chen, Tao Luo, Shaoli Liu, Shijin Zhang, Liqiang He, Jia Wang, Ling Li, Tianshi Chen, Zhiwei Xu, Ninghui Sun, Olivier Temam, DaDianNao: A Machine-Learning Supercomputer, in: 2014 47th Annual IEEE/ACM International Symposium on Microarchitecture, 2014, pp. 609–622.
[16]
Carmichael Zachariah, Langroudi Hamed F., Khazanov Char, Lillie Jeffrey, Gustafson John L., Kudithipudi Dhireesha, Performance-efficiency trade-off of low-precision numerical formats in deep neural networks, Proceedings of the Conference for Next Generation Arithmetic 2019 (2019).
[17]
Lin Darryl D., Talathi Sachin S., Annapureddy V. Sreekanth, Fixed point quantization of deep convolutional networks, in: Proceedings of the 33rd International Conference on International Conference on Machine Learning - Volume 48, ICML ’16, JMLR.org, 2016, pp. 2849–2858.
[18]
Gupta Suyog, Agrawal Ankur, Gopalakrishnan Kailash, Narayanan Pritish, Deep learning with limited numerical precision, in: Proceedings of the 32nd International Conference on International Conference on Machine Learning - Volume 37, ICML ’15, JMLR.org, 2015, pp. 1737–1746.
[19]
Hammad Issam, Li Ling, El-Sankary Kamal, Snelgrove W. Martin, CNN inference using a preprocessing precision controller and approximate multipliers with various precisions, IEEE Access 9 (2021) 7220–7232.
[20]
Karen Simonyan, Andrew Zisserman, Very Deep Convolutional Networks for Large-Scale Image Recognition, in: 3rd International Conference on Learning Representations, ICLR2015, 2015.
[21]
Chollet F., Xception: Deep learning with depthwise separable convolutions, in: 2017 IEEE Conference on Computer Vision and Pattern Recognition, CVPR, IEEE Computer Society, Los Alamitos, CA, USA, 2017, pp. 1800–1807.
[22]
Wang Shuihua, Zhang Yu-Dong, DenseNet-201-based deep neural network with composite learning factor and precomputation for multiple sclerosis classification, ACM Trans. Multimed. Comput. Commun. Appl. 16 (2020) 1–19.
[23]
Recht Benjamin, Roelofs Rebecca, Schmidt Ludwig, Shankar Vaishaal, Do ImageNet classifiers generalize to ImageNet?, 2019.
[24]
Ali Ibrahim, Mario Osta, Mohamad Alameh, Moustafa Saleh, Hussein Chible, Maurizio Valle, Approximate Computing Methods for Embedded Machine Learning, in: 2018 25th IEEE International Conference on Electronics, Circuits and Systems, ICECS, 2018, pp. 845–848.
[25]
Manikandan N., Approximation computing techniques to accelerate CNN based image processing applications – A survey in hardware/software perspective, Int. J. Adv. Trends Comput. Sci. Eng. 9 (3) (2020).
[26]
Doochul Shin, Sandeep K. Gupta, A Re-design Technique for Datapath Modules in Error Tolerant Applications, in: 2008 17th Asian Test Symposium, 2008, pp. 431–437.
[27]
Parag Kulkarni, Puneet Gupta, Milos Ercegovac, Trading Accuracy for Power with an Underdesigned Multiplier Architecture, in: 2011 24th Internatioal Conference on VLSI Design, 2011, pp. 346–351.
[28]
Behzad Salami, Erhan Baturay Onural, Ismail Emir Yuksel, Fahrettin Koc, Oguz Ergin, Adrian Cristal Kestelman, Osman Unsal, Hamid Sarbazi-Azad, Onur Mutlu, An Experimental Study of Reduced-Voltage Operation in Modern FPGAs for Neural Network Acceleration, in: 2020 50th Annual IEEE/IFIP International Conference on Dependable Systems and Networks, DSN, 2020, pp. 138–149.
[29]
Nandhini Chandramoorthy, Karthik Swaminathan, Martin Cochet, Arun Paidimarri, Schuyler Eldridge, Rajiv V. Joshi, Matthew M. Ziegler, Alper Buyuktosunoglu, Pradip Bose, Resilient Low Voltage Accelerators for High Energy Efficiency, in: 2019 IEEE International Symposium on High Performance Computer Architecture, HPCA, 2019, pp. 147–158.
[30]
Annachiara Ruospo, Alberto Bosio, Alessandro Ianne, Ernesto Sanchez, Evaluating Convolutional Neural Networks Reliability depending on their Data Representation, in: 2020 23rd Euromicro Conference on Digital System Design, DSD, 2020, pp. 672–679.
[31]
Lecun Y., Bottou L., Bengio Y., Haffner P., Gradient-based learning applied to document recognition, Proc. IEEE 86 (11) (1998) 2278–2324.
[32]
Deng Li, The mnist database of handwritten digit images for machine learning research, IEEE Signal Process. Mag. 29 (6) (2012) 141–142.
[33]
Libano F., Rech P., Neuman B., Leavitt J., Wirthlin M., Brunhaver J., How reduced data precision and degree of parallelism impact the reliability of convolutional neural networks on FPGAs, IEEE Trans. Nucl. Sci. 68 (5) (2021) 865–872.
[34]
Saurabh Jha, Shengkun Cui, Timothy Tsai, Siva Kumar Sastry Hari, Michael B. Sullivan, Zbigniew T. Kalbarczyk, Stephen W. Keckler, Ravishankar K. Iyer, Exploiting Temporal Data Diversity for Detecting Safety-critical Faults in AV Compute Systems, in: 2022 52nd Annual IEEE/IFIP International Conference on Dependable Systems and Networks, DSN, 2022, pp. 88–100.
[35]
Draghetti Lucas Klein, Santos Fernando Fernandes dos, Carro Luigi, Rech Paolo, Detecting errors in convolutional neural networks using inter frame spatio-temporal correlation, in: 2019 IEEE 25th International Symposium on on-Line Testing and Robust System Design, IOLTS, 2019, pp. 310–315.
[36]
Perception Apollo 3.0, 2018, https://github.com/ApolloAuto/apollo/blob/master/docs/specs/perception_apollo_3.0.md.
[37]
Autoware. An open autonomous driving platform, 2022, https://github.com/Autoware-AI/autoware.ai. (Accessed in October 2022).
[38]
Gong Yunchao, et al., Compressing deep convolutional networks using vector quantization, 2014.
[39]
Jiang Honglan, Santiago Francisco Javier Hernandez, Mo Hai, Liu Leibo, Han Jie, Approximate arithmetic circuits: A survey, characterization, and recent applications, Proc. IEEE 108 (12) (2020) 2108–2135.
[40]
Tabani Hamid, Pujol Roger, Abella Jaume, Cazorla Francisco J, A cross-layer review of deep learning frameworks to ease their optimization and reuse, in: 2020 IEEE 23rd International Symposium on Real-Time Distributed Computing, ISORC, IEEE, 2020, pp. 144–145.
[41]
Borkar Shekhar, Karnik Tanay, Narendra Siva, Tschanz Jim, Keshavarzi Ali, De Vivek, Parameter variations and impact on circuits and microarchitecture, in: Proceedings of the 40th Annual Design Automation Conference, DAC ’03, Association for Computing Machinery, New York, NY, USA, 2003, pp. 338–342.
[42]
Li Guanpeng, Hari Siva Kumar Sastry, Sullivan Michael, Tsai Timothy, Pattabiraman Karthik, Emer Joel, Keckler Stephen W., Understanding error propagation in deep learning neural network (DNN) accelerators and applications, in: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis, SC ’17, Association for Computing Machinery, New York, NY, USA, 2017.
[43]
Alberto Bosio, Paolo Bernardi, Annachiara Ruospo, Ernesto Sanchez, A Reliability Analysis of a Deep Neural Network, in: 2019 IEEE Latin American Test Symposium, LATS, 2019, pp. 1–6.
[44]
Ernst D., Das S., Lee S., Blaauw D., Austin T., Mudge T., Kim Nam Sung, Flautner K., Razor: circuit-level correction of timing errors for low-power operation, IEEE Micro 24 (6) (2004) 10–20.
[45]
Redmon Joseph, Farhadi Ali, Darknet framework for YOLOv3, 2018, https://github.com/pjreddie/darknet.
[46]
Lin Tsung-Yi, Maire Michael, Belongie Serge, Hays James, Perona Pietro, Ramanan Deva, Dollár Piotr, Zitnick C. Lawrence, Microsoft COCO: Common objects in context, in: Fleet David, Pajdla Tomas, Schiele Bernt, Tuytelaars Tinne (Eds.), Computer Vision – ECCV 2014, Springer International Publishing, Cham, 2014, pp. 740–755.
[47]
Utah J., Rio 4K - copacabana beach - morning drive, [time: 2:50 - 3:20], [frames: 5094 - 5971], 2020, https://www.youtube.com/watch?v=_hWCN1yV9TY.
[48]
Utah J., San francisco 4K - night drive, [time: 2:20 - 2:50], frames: 4214 - 5091], 2020, https://www.youtube.com/watch?v=jJ08h2cgWjI.
[49]
Utah J., San francisco 4K - driving downtown, [time: 2:00 - 2:30], [frames: 3639 - 4516], 2020, https://www.youtube.com/watch?v=E7t3QyEfyLA.
[50]
Utah J., Los angeles 4K - skyscraper Metropolis - wilshire boulevard, [time: 18:30 - 19:00], [frames: 33237 - 34114], 2020, https://www.youtube.com/watch?v=zfblxgasy-0.
[51]
Utah J., Miami 4K - Gold Coast - Scenic Drive, [time: 13:25 - 13:55], [frames: 24142 - 25019], 2020, https://www.youtube.com/watch?v=xj7abSp07w0.
[52]
Utah J., Las vegas 4K - sunset drive, [time: 1:10 - 1:40], [frame: 2097 - 2974], 2020, https://www.youtube.com/watch?v=X9U5DafT0d4.
[53]
Zhang Shanshan, Benenson Rodrigo, Schiele Bernt, CityPersons: A diverse dataset for pedestrian detection, 2017.
[54]
Andreas Geiger, Philip Lenz, Raquel Urtasun, Are we ready for Autonomous Driving? The KITTI Vision Benchmark Suite, in: Conference on Computer Vision and Pattern Recognition, CVPR, 2012.
[55]
Huang Xinyu, Wang Peng, Cheng Xinjing, Zhou Dingfu, Geng Qichuan, Yang Ruigang, The ApolloScape open dataset for autonomous driving and its application, IEEE Trans. Pattern Anal. Mach. Intell. 42 (10) (2020) 2702–2719.
[56]
Hauser John, Berkeley SoftFloat, 2018.
[57]
Rafael Padilla, Sergio L. Netto, Eduardo A. B. da Silva, A Survey on Performance Metrics for Object-Detection Algorithms, in: 2020 International Conference on Systems, Signals and Image Processing, IWSSIP, 2020, pp. 237–242.
[58]
Everingham M., Van Gool L., Williams C.K.I., Winn J., Zisserman A., The pascal visual object classes (voc) challenge, Int. J. Comput. Vis. 88 (2) (2010).
Recommendations
CODA: A Real-World Road Corner Case Dataset for Object Detection in Autonomous Driving
Computer Vision – ECCV 2022AbstractContemporary deep-learning object detection methods for autonomous driving usually presume fixed categories of common traffic participants, such as pedestrians and cars. Most existing detectors are unable to detect uncommon objects and corner ...
High-Resolution Object Detection with SAR Imaging for Autonomous Driving
ICCDA '21: Proceedings of the 2021 5th International Conference on Compute and Data AnalysisThe development of autonomous driving technology has been rapidly developing for the past decades. One key task in autonomous driving technology is the detection of objects around the vehicle. Radars are now more and more widely equipped by autonomous ...
Numerical Analysis of Tractor Accidents using Driving Simulator for Autonomous Driving Tractor
ICMRE'19: Proceedings of the 5th International Conference on Mechatronics and Robotics EngineeringAutonomous driving of automobiles is a hot research topic in recent years. The autonomous driving tractor also has been studied in the agricultural field as well as an autonomous driving automobile. On the other hand, tractor accidents frequently occur ...
Comments
Information & Contributors
Information
Published In
Elsevier B.V.
Publisher
Elsevier North-Holland, Inc.
United States
Publication History
Published: 01 May 2023
Author Tags
Qualifiers
- Research-article
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 0Total Downloads
- Downloads (Last 12 months)0
- Downloads (Last 6 weeks)0
Reflects downloads up to 12 Nov 2024
Other Metrics
Citations
View Options
View options
Get Access
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in