Advertisement

Small, Accurate, and Fast Re-ID on the Edge: The SAFR Approach

Conference paper
  • 223 Downloads
Part of the Lecture Notes in Computer Science book series (LNCS, volume 12407)

Abstract

We propose a Small, Accurate, and Fast Re-ID (SAFR) design for flexible vehicle re-id under a variety of compute environments such as cloud, mobile, edge, or embedded devices by only changing the re-id model backbone. Through best-fit design choices, feature extraction, training tricks, global attention, and local attention, we create a re-id model design that optimizes multi-dimensionally along model size, speed, & accuracy for deployment under various memory and compute constraints. We present several variations of our flexible SAFR model: SAFR-Large for cloud-type environments with large compute resources, SAFR-Small for mobile devices with some compute constraints, and SAFR-Micro for edge devices with severe memory & compute constraints.

SAFR-Large delivers state-of-the-art results with mAP 81.34 on the VeRi-776 vehicle re-id dataset (15% better than related work). SAFR-Small trades a 5.2% drop in performance (mAP 77.14 on VeRi-776) for over 60% model compression and 150% speedup. SAFR-Micro, at only 6 MB and 130 MFLOPS, trades 6.8% drop in accuracy (mAP 75.80 on VeRi-776) for 95% compression and 33x speedup compared to SAFR-Large .

References

  1. 1.
    Ananthanarayanan, G., et al.: Real-time video analytics: the killer app for edge computing. Computer 50(10), 58–67 (2017)CrossRefGoogle Scholar
  2. 2.
    Wan, Y., Huang, Y., Buckles, B.: Camera calibration and vehicle tracking: highway traffic video analytics. Transp. Res. Part C Emerg. Technol. 44, 202–213 (2014)CrossRefGoogle Scholar
  3. 3.
    Chang, M.C., Wei, Y., Song, N., Lyu, S.: Video analytics in smart transportation for the AIC’18 challenge. In: CVPR Workshops (2018)Google Scholar
  4. 4.
    Liu, X., Zhang, S., Huang, Q., Gao, W.: Ram: a region-aware deep model for vehicle re-identification. In: IEEE International Conference on Multimedia and Expo, pp. 1–6. IEEE (2018)Google Scholar
  5. 5.
    Wang, Z., et al.: Orientation invariant feature embedding and spatial temporal regularization for vehicle re-identification. In: ICCVGoogle Scholar
  6. 6.
    Zhou, Y., Shao, L.: Aware attentive multi-view inference for vehicle re-ID. In: CVPRGoogle Scholar
  7. 7.
    Lou, Y., Bai, Y., Liu, J., Wang, S., Duan, L.Y.: Embedding adversarial learning for vehicle re-ID. IEEE Trans. Image Process. (2019)Google Scholar
  8. 8.
    Bai, Y., Lou, Y., Gao, F., Wang, S., Wu, Y., Duan, L.Y.: Group-sensitive triplet embedding for vehicle reidentification. IEEE Trans. Multimedia 20(9), 2385–2399 (2018)CrossRefGoogle Scholar
  9. 9.
    Jiang, J., Ananthanarayanan, G., Bodik, P., Sen, S., Stoica, I.: Chameleon: scalable adaptation of video analytics. In: ACM SIG Data Communication, pp. 253–266 (2018)Google Scholar
  10. 10.
    Chen, T., et al.: MXNet: a flexible and efficient machine learning library for heterogeneous distributed systems. arXiv:1512.01274 (2015)
  11. 11.
    Ma, N., Zhang, X., Zheng, H.-T., Sun, J.: ShuffleNet V2: practical guidelines for efficient CNN architecture design. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) Computer Vision – ECCV 2018. LNCS, vol. 11218, pp. 122–138. Springer, Cham (2018).  https://doi.org/10.1007/978-3-030-01264-9_8CrossRefGoogle Scholar
  12. 12.
    Howard, A.G., et al.: Mobilenets: efficient convolutional neural networks for mobile vision applications. arXiv:1704.04861 (2017)
  13. 13.
    He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR, pp. 770–778 (2016)Google Scholar
  14. 14.
    Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: unified, real-time object detection. In: CVPR (2016)Google Scholar
  15. 15.
    Cheng, Y., Wang, D., Zhou, P., Zhang, T.: Survey of model compression and acceleration for deep neural networks. arXiv:1710.09282
  16. 16.
    Shen, Y., Xiao, T., Li, H., Yi, S., Wang, X.: Learning DNNs for vehicle re-id with visual-spatio-temporal path proposals. In: ICCVGoogle Scholar
  17. 17.
    Kanaci, A., Li, M., Gong, S., Rajamanoharan, G.: Multi-task mutual learning for vehicle re-ID. In: CVPR Workshops, pp. 62–70Google Scholar
  18. 18.
    Zhu, J., et al.: Vehicle re-identification using quadruple directional deep learning features. IEEE Trans. Intell. Transp. Syst. (2019)Google Scholar
  19. 19.
    Luo, H., Gu, Y., Liao, X., Lai, S., Jiang, W.: Bag of tricks and a strong baseline for deep person re-identification. In: CVPR WorkshopsGoogle Scholar
  20. 20.
    Liu, H., Tian, Y., Yang, Y., Pang, L., Huang, T.: Deep relative distance learning: tell the difference between similar vehicles. In: CVPR, pp. 2167–2175 (2016)Google Scholar
  21. 21.
    Liu, X., Liu, W., Mei, T., Ma, H.: A deep learning-based approach to progressive vehicle re-identification for urban surveillance. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9906, pp. 869–884. Springer, Cham (2016).  https://doi.org/10.1007/978-3-319-46475-6_53CrossRefGoogle Scholar
  22. 22.
    Lou, Y., Bai, Y., Liu, J., Wang, S., Duan, L.: VERI-wild: a large dataset and a new method for vehicle re-identification in the wild. In: CVPRGoogle Scholar
  23. 23.
    Kanacı, A., Zhu, X., Gong, S.: Vehicle re-identification in context. In: Brox, T., Bruhn, A., Fritz, M. (eds.) GCPR 2018. LNCS, vol. 11269, pp. 377–390. Springer, Cham (2019).  https://doi.org/10.1007/978-3-030-12939-2_26CrossRefGoogle Scholar
  24. 24.
    Gale, T., Elsen, E., Hooker, S.: The state of sparsity in deep neural networks. arXiv:1902.09574 (2019)
  25. 25.
    Narang, S., Elsen, E., Diamos, G., Sengupta, S.: Exploring sparsity in recurrent neural networks. arXiv:1704.05119
  26. 26.
    Woo, S., Park, J., Lee, J.-Y., Kweon, I.S.: CBAM: convolutional block attention module. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11211, pp. 3–19. Springer, Cham (2018).  https://doi.org/10.1007/978-3-030-01234-2_1CrossRefGoogle Scholar
  27. 27.
    He, B., Li, J., Zhao, Y., Tian, Y.: Part-regularized near-duplicate vehicle re-identification. In: CVPR, pp. 3997–4005Google Scholar
  28. 28.
    Basha, S., Dubey, S.R., Pulabaigari, V., Mukherjee, S.: Impact of fully connected layers on performance of CNNs for image classification. arXiv:1902.02771 (2019)
  29. 29.
    Alfasly, S., Hu, Y., Li, H., Liang, T., Jin, X., Liu, B., Zhao, Q.: Multi-label-based similarity learning for vehicle re-identification. IEEE Access 7, 162605–162616 (2019)CrossRefGoogle Scholar
  30. 30.
    Zhang, X., Zhou, X., Lin, M., Sun, J.: Shufflenet: an extremely efficient CNN for mobile devices. In: CVPR (2018)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  1. 1.School of Computer ScienceGeorgia Institute of TechnologyAtlantaUSA
  2. 2.Department of Mathematics and StatisticsUniversity of Sao PauloSao PauloBrazil

Personalised recommendations