Papers
Topics
Authors
Recent
Search
2000 character limit reached

Optimizing Edge Offloading Decisions for Object Detection

Published 24 Oct 2024 in cs.DC, cs.LG, and cs.NI | (2410.18919v1)

Abstract: Recent advances in machine learning and hardware have produced embedded devices capable of performing real-time object detection with commendable accuracy. We consider a scenario in which embedded devices rely on an onboard object detector, but have the option to offload detection to a more powerful edge server when local accuracy is deemed too low. Resource constraints, however, limit the number of images that can be offloaded to the edge. Our goal is to identify which images to offload to maximize overall detection accuracy under those constraints. To that end, the paper introduces a reward metric designed to quantify potential accuracy improvements from offloading individual images, and proposes an efficient approach to make offloading decisions by estimating this reward based only on local detection results. The approach is computationally frugal enough to run on embedded devices, and empirical findings indicate that it outperforms existing alternatives in improving detection accuracy even when the fraction of offloaded images is small.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (48)
  1. S. Ren, K. He, R. Girshick, and J. Sun, “Faster r-cnn: Towards real-time object detection with region proposal networks,” in Advances in Neural Information Processing Systems, vol. 28.   Curran Associates, Inc., 2015.
  2. K. He, G. Gkioxari, P. Dollar, and R. Girshick, “Mask r-cnn,” in Proceedings of the IEEE International Conference on Computer Vision (ICCV), Oct 2017.
  3. T.-Y. Lin, P. Dollar, R. Girshick, K. He, B. Hariharan, and S. Belongie, “Feature pyramid networks for object detection,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), July 2017.
  4. J. Redmon and A. Farhadi, “Yolov3: An incremental improvement,” 2018. [Online]. Available: https://arxiv.org/abs/1804.02767
  5. W. Liu, D. Anguelov, D. Erhan, C. Szegedy, S. Reed, C.-Y. Fu, and A. C. Berg, “Ssd: Single shot multibox detector,” in Computer Vision – ECCV 2016.   Springer International Publishing, 2016, pp. 21–37.
  6. M. Tan, R. Pang, and Q. V. Le, “Efficientdet: Scalable and efficient object detection,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 2020.
  7. J.-H. Kim, N. Kim, and C. S. Won, “Deep edge computing for videos,” IEEE Access, vol. 9, pp. 123 348–123 357, 2021.
  8. K. Nalaie, R. Xu, and R. Zheng, “Deepscale: Online frame size adaptation for multi-object tracking on smart cameras and edge servers,” in 2022 IEEE/ACM Seventh International Conference on Internet-of-Things Design and Implementation (IoTDI).   IEEE, 2022, pp. 67–79.
  9. A. Ghosh, S. Iyengar, S. Lee, A. Rathore, and V. N. Padmanabhan, “React: Streaming video analytics on the edge with asynchronous cloud support,” in Proceedings of the 8th ACM/IEEE Conference on Internet of Things Design and Implementation, 2023, pp. 222–235.
  10. T. Tan and G. Cao, “Deep learning video analytics on edge computing devices,” in 2021 18th Annual IEEE International Conference on Sensing, Communication, and Networking (SECON).   IEEE, 2021, pp. 1–9.
  11. M. Hanyao, Y. Jin, Z. Qian, S. Zhang, and S. Lu, “Edge-assisted online on-device object detection for real-time video analytics,” in IEEE INFOCOM 2021-IEEE Conference on Computer Communications.   IEEE, 2021, pp. 1–10.
  12. Y. Deng, T. Han, and N. Ansari, “Fedvision: Federated video analytics with edge computing,” IEEE Open Journal of the Computer Society, vol. 1, pp. 62–72, 2020.
  13. H.-Y. Zhou, B.-B. Gao, and J. Wu, “Adaptive feeding: Achieving fast and accurate detections by adaptively combining object detectors,” in Proceedings of the IEEE International Conference on Computer Vision, 2017, pp. 3505–3513.
  14. Z. Cao, Z. Li, Y. Chen, H. Pan, Y. Hu, and J. Liu, “Edge-cloud collaborated object detection via difficult-case discriminator,” in 2023 IEEE 43rd International Conference on Distributed Computing Systems (ICDCS).   IEEE, 2023, pp. 259–270.
  15. R. Padilla, S. L. Netto, and E. 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.
  16. (2018) map (mean average precision) for object detection. [Online]. Available: https://jonathan-hui.medium.com/map-mean-average-precision-for-object-detection-45c121a31173
  17. S. Teerapittayanon, B. McDanel, and H.-T. Kung, “Branchynet: Fast inference via early exiting from deep neural networks,” in 2016 23rd international conference on pattern recognition (ICPR).   IEEE, 2016, pp. 2464–2469.
  18. ——, “Distributed deep neural networks over the cloud, the edge and end devices,” in 2017 IEEE 37th international conference on distributed computing systems (ICDCS).   IEEE, 2017, pp. 328–339.
  19. S. Laskaridis, S. I. Venieris, M. Almeida, I. Leontiadis, and N. D. Lane, “Spinn: synergistic progressive inference of neural networks over device and cloud,” in Proceedings of the 26th annual international conference on mobile computing and networking, 2020, pp. 1–15.
  20. L. Zeng, E. Li, Z. Zhou, and X. Chen, “Boomerang: On-demand cooperative deep neural network inference for edge intelligence on the industrial internet of things,” IEEE Network, vol. 33, no. 5, pp. 96–103, 2019.
  21. T.-Y. Lin, M. Maire, S. Belongie, J. Hays, P. Perona, D. Ramanan, P. Dollár, and C. L. Zitnick, “Microsoft coco: Common objects in context,” in Computer Vision–ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part V 13.   Springer, 2014, pp. 740–755.
  22. M. Everingham, L. Van Gool, C. K. Williams, J. Winn, and A. Zisserman, “The Pascal visual object classes (VOC) challenge,” International journal of computer vision, vol. 88, pp. 303–338, 2010.
  23. A. Chakrabarti, R. Guérin, C. Lu, and J. Liu, “Real-time edge classification: Optimal offloading under token bucket constraints,” in 2021 IEEE/ACM Symposium on Edge Computing (SEC).   IEEE, 2021, pp. 41–54.
  24. D. Bolya, S. Foley, J. Hays, and J. Hoffman, “Tide: A general toolbox for identifying object detection errors,” in Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part III 16.   Springer, 2020, pp. 558–573.
  25. G. Yoon, G.-Y. Kim, H. Yoo, S. C. Kim, and R. Kim, “Implementing practical dnn-based object detection offloading decision for maximizing detection performance of mobile edge devices,” IEEE Access, vol. 9, pp. 140 199–140 211, 2021.
  26. R. Girshick, “Fast r-cnn,” in Proceedings of the IEEE international conference on computer vision, 2015, pp. 1440–1448.
  27. J. Dai, Y. Li, K. He, and J. Sun, “R-fcn: Object detection via region-based fully convolutional networks,” Advances in neural information processing systems, vol. 29, 2016.
  28. J. Redmon, S. Divvala, R. Girshick, and A. Farhadi, “You only look once: Unified, real-time object detection,” in Proceedings of the IEEE conference on computer vision and pattern recognition, 2016, pp. 779–788.
  29. J. Redmon and A. Farhadi, “Yolo9000: better, faster, stronger,” in Proceedings of the IEEE conference on computer vision and pattern recognition, 2017, pp. 7263–7271.
  30. J. Terven and D. Cordova-Esparza, “A comprehensive review of yolo: From yolov1 to yolov8 and beyond,” arXiv preprint arXiv:2304.00501, 2023.
  31. Y.-M. Zhang, C.-C. Lee, J.-W. Hsieh, and K.-C. Fan, “Csl-yolo: A new lightweight object detection system for edge computing,” arXiv preprint arXiv:2107.04829, 2021.
  32. R. Kim, G. Kim, H. Kim, G. Yoon, and H. Yoo, “A method for optimizing deep learning object detection in edge computing,” in 2020 International Conference on Information and Communication Technology Convergence (ICTC).   IEEE, 2020, pp. 1164–1167.
  33. Y. Matsubara, M. Levorato, and F. Restuccia, “Split computing and early exiting for deep learning applications: Survey and research challenges,” ACM Computing Surveys, vol. 55, no. 5, pp. 1–30, 2022.
  34. Y. Kang, J. Hauswald, C. Gao, A. Rovinski, T. Mudge, J. Mars, and L. Tang, “Neurosurgeon: Collaborative intelligence between the cloud and mobile edge,” ACM SIGARCH Computer Architecture News, vol. 45, no. 1, pp. 615–629, 2017.
  35. A. E. Eshratifar, M. S. Abrishami, and M. Pedram, “Jointdnn: An efficient training and inference engine for intelligent mobile cloud computing services,” IEEE Transactions on Mobile Computing, vol. 20, no. 2, pp. 565–576, 2019.
  36. A. E. Eshratifar, A. Esmaili, and M. Pedram, “Bottlenet: A deep learning architecture for intelligent mobile cloud computing services,” in 2019 IEEE/ACM International Symposium on Low Power Electronics and Design (ISLPED).   IEEE, 2019, pp. 1–6.
  37. J. Shao and J. Zhang, “Bottlenet++: An end-to-end approach for feature compression in device-edge co-inference systems,” in 2020 IEEE International Conference on Communications Workshops (ICC Workshops).   IEEE, 2020, pp. 1–6.
  38. Y. Matsubara, S. Baidya, D. Callegaro, M. Levorato, and S. Singh, “Distilled split deep neural networks for edge-assisted real-time systems,” in Proceedings of the 2019 Workshop on Hot Topics in Video Analytics and Intelligent Edges, 2019, pp. 21–26.
  39. Y. Matsubara, D. Callegaro, S. Baidya, M. Levorato, and S. Singh, “Head network distillation: Splitting distilled deep neural networks for resource-constrained edge computing systems,” IEEE Access, vol. 8, pp. 212 177–212 193, 2020.
  40. P. Hu, J. Im, Z. Asgar, and S. Katti, “Starfish: Resilient image compression for aiot cameras,” in Proceedings of the 18th Conference on Embedded Networked Sensor Systems, 2020, pp. 395–408.
  41. R. Wang, H. Liu, J. Qiu, M. Xu, R. Guérin, and C. Lu, “Progressive neural compression for adaptive image offloading under timing constraints,” in 2023 IEEE Real-Time Systems Symposium (RTSS).   IEEE, 2023, pp. 118–130.
  42. X. Wang, Y. Luo, D. Crankshaw, A. Tumanov, F. Yu, and J. E. Gonzalez, “Idk cascades: Fast deep learning by learning not to overthink,” arXiv preprint arXiv:1706.00885, 2017.
  43. J. Qiu, R. Wang, A. Chakrabarti, R. Guérin, and C. Lu, “Adaptive edge offloading for image classification under rate limit,” IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, vol. 41, no. 11, pp. 3886–3897, 2022.
  44. T. Y.-H. Chen, L. Ravindranath, S. Deng, P. Bahl, and H. Balakrishnan, “Glimpse: Continuous, real-time object recognition on mobile devices,” in Proceedings of the 13th ACM Conference on Embedded Networked Sensor Systems, 2015, pp. 155–168.
  45. L. Liu, H. Li, and M. Gruteser, “Edge assisted real-time object detection for mobile augmented reality,” in The 25th annual international conference on mobile computing and networking, 2019, pp. 1–16.
  46. Q. Liu and T. Han, “Dare: Dynamic adaptive mobile augmented reality with edge computing,” in 2018 IEEE 26th International Conference on Network Protocols (ICNP).   IEEE, 2018, pp. 1–11.
  47. Y.-J. Ku, S. Baidya, and S. Dey, “Adaptive computation partitioning and offloading in real-time sustainable vehicular edge computing,” IEEE Transactions on Vehicular Technology, vol. 70, no. 12, pp. 13 221–13 237, 2021.
  48. X. Chen, H. Zhang, C. Wu, S. Mao, Y. Ji, and M. Bennis, “Optimized computation offloading performance in virtual edge computing systems via deep reinforcement learning,” IEEE Internet of Things Journal, vol. 6, no. 3, pp. 4005–4018, 2018.

Summary

No one has generated a summary of this paper yet.

Sign Up to Summarize

Paper to Video (Beta)

No one has generated a video about this paper yet.

Sign Up to Generate All Videos Subscribe on YouTube

Whiteboard

No one has generated a whiteboard explanation for this paper yet.

Sign Up to Generate

Open Problems

We haven't generated a list of open problems mentioned in this paper yet.

Generate Now

Continue Learning

We haven't generated follow-up questions for this paper yet.

Generate Now

Collections

Sign up for free to add this paper to one or more collections.

Sign Up

Tweets

Sign up for free to view the 1 tweet with 0 likes about this paper.

Sign Up for Free