Advertisement

Simulating Content Consistent Vehicle Datasets with Attribute Descent

Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 12351)

Abstract

This paper uses a graphic engine to simulate a large amount of training data with free annotations. Between synthetic and real data, there is a two-level domain gap, i.e., content level and appearance level. While the latter has been widely studied, we focus on reducing the content gap in attributes like illumination and viewpoint. To reduce the problem complexity, we choose a smaller and more controllable application, vehicle re-identification (re-ID). We introduce a large-scale synthetic dataset VehicleX. Created in Unity, it contains 1,362 vehicles of various 3D models with fully editable attributes. We propose an attribute descent approach to let VehicleX approximate the attributes in real-world datasets. Specifically, we manipulate each attribute in VehicleX, aiming to minimize the discrepancy between VehicleX and real data in terms of the Fréchet Inception Distance (FID). This attribute descent algorithm allows content domain adaptation (DA) orthogonal to existing appearance DA methods. We mix the optimized VehicleX data with real-world vehicle re-ID datasets, and observe consistent improvement. With the augmented datasets, we report competitive accuracy. We make the dataset, engine and our codes available at https://github.com/yorkeyao/VehicleX.

Keywords

Vehicle retrieval Domain adaptation Synthetic data 

Notes

Acknowledgement

Dr. Liang Zheng is the recipient of Australian Research Council Discovery Early Career Award (DE200101283) funded by the Australian Government.

References

  1. 1.
    Bai, Y., Lou, Y., Gao, F., Wang, S., Wu, Y., Duan, L.Y.: Group-sensitive triplet embedding for vehicle reidentification. IEEE Trans. Multimed. 20(9), 2385–2399 (2018)CrossRefGoogle Scholar
  2. 2.
    Bak, S., Carr, P., Lalonde, J.F.: Domain adaptation through synthesis for unsupervised person re-identification. In: ECCV (2018)Google Scholar
  3. 3.
    Bergstra, J., Bengio, Y.: Random search for hyper-parameter optimization. J. Mach. Learn. Res. 13(Feb), 281–305 (2012)MathSciNetzbMATHGoogle Scholar
  4. 4.
    Binkowski, M., Sutherland, D.J., Arbel, M., Gretton, A.: Demystifying mmd gans. In: ICLR (2018)Google Scholar
  5. 5.
    Chang, A.X., et al.: Shapenet: an information-rich 3D model repository. arXiv preprint arXiv:1512.03012 (2015)
  6. 6.
    Chu, R., Sun, Y., Li, Y., Liu, Z., Zhang, C., Wei, Y.: Vehicle re-identification with viewpoint-aware metric learning. In: ICCV (2019)Google Scholar
  7. 7.
    Deng, W., Zheng, L., Ye, Q., Kang, G., Yang, Y., Jiao, J.: Image-image domain adaptation with preserved self-similarity and domain-dissimilarity for person re-identification. In: CVPR (2018)Google Scholar
  8. 8.
    Gaidon, A., Wang, Q., Cabon, Y., Vig, E.: Virtual worlds as proxy for multi-object tracking analysis. In: CVPR (2016)Google Scholar
  9. 9.
    Hermans, A., Beyer, L., Leibe, B.: In defense of the triplet loss for person re-identification. arXiv preprint arXiv:1703.07737 (2017)
  10. 10.
    Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B., Hochreiter, S.: Gans trained by a two time-scale update rule converge to a local nash equilibrium. In: NeurIPS (2017)Google Scholar
  11. 11.
    Hoffman, J., et al.: Cycada: cycle-consistent adversarial domain adaptation. In: ICML (2018)Google Scholar
  12. 12.
    Hou, Y., Zheng, L., Gould, S.: Multiview detection with feature perspective transformation. arXiv preprint arXiv:2007.07247 (2020)
  13. 13.
    Juliani, A., et al.: Unity: a general platform for intelligent agents. arXiv preprint arXiv:1809.02627 (2018)
  14. 14.
    Kar, A., et al.: Meta-sim: Learning to generate synthetic datasets. In: ICCV (2019)Google Scholar
  15. 15.
    Khorramshahi, P., Kumar, A., Peri, N., Rambhatla, S.S., Chen, J.C., Chellappa, R.: A dual path modelwith adaptive attention for vehicle re-identification. In: ICCV (2019)Google Scholar
  16. 16.
    Kolve, E., Mottaghi, R., Gordon, D., Zhu, Y., Gupta, A., Farhadi, A.: Ai2-thor: an interactive 3D environment for visual AI. arXiv preprint arXiv:1712.05474 (2017)
  17. 17.
    Kumar, R., Weill, E., Aghdasi, F., Sriram, P.: Vehicle re-identification: an efficient baseline using triplet embedding. arXiv preprint arXiv:1901.01015 (2019)
  18. 18.
    Liu, H., Tian, Y., Yang, Y., Pang, L., Huang, T.: Deep relative distance learning: tell the difference between similar vehicles. In: CVPR (2016)Google Scholar
  19. 19.
    Liu, X., Zhang, S., Huang, Q., Gao, W.: Ram: a region-aware deep model for vehicle re-identification. In: ICME (2018)Google Scholar
  20. 20.
    Liu, X., Liu, W., Ma, H., Fu, H.: Large-scale vehicle re-identification in urban surveillance videos. In: ICME (2016)Google Scholar
  21. 21.
    Lloyd, S.: Least squares quantization in PCM. IEEE Trans. Inf. Theory 28(2), 129–137 (1982)MathSciNetCrossRefGoogle Scholar
  22. 22.
    Luo, H., Gu, Y., Liao, X., Lai, S., Jiang, W.: Bag of tricks and a strong baseline for deep person re-identification. In: CVPR Workshops (2019)Google Scholar
  23. 23.
    Naphade, M., et al.: The 4th AI city challenge. In: CVPR Workshops, pp. 626–627 (2020)Google Scholar
  24. 24.
    Peng, X., Bai, Q., Xia, X., Huang, Z., Saenko, K., Wang, B.: Moment matching for multi-source domain adaptation. In: ICCV (2019)Google Scholar
  25. 25.
    Richter, S.R., Vineet, V., Roth, S., Koltun, V.: Playing for data: ground truth from computer games. In: ECCV (2016)Google Scholar
  26. 26.
    Ristani, E., Solera, F., Zou, R., Cucchiara, R., Tomasi, C.: Performance measures and a data set for multi-target, multi-camera tracking. In: Hua, G., Jégou, H. (eds.) ECCV 2016. LNCS, vol. 9914, pp. 17–35. Springer, Cham (2016).  https://doi.org/10.1007/978-3-319-48881-3_2CrossRefGoogle Scholar
  27. 27.
    Ruiz, N., Schulter, S., Chandraker, M.: Learning to simulate. In: ICLR (2019)Google Scholar
  28. 28.
    Sakaridis, C., Dai, D., Van Gool, L.: Semantic foggy scene understanding with synthetic data. Int. J. Comput. Vis. 126(9), 973–992 (2018).  https://doi.org/10.1007/s11263-018-1072-8CrossRefGoogle Scholar
  29. 29.
    Shrivastava, A., Pfister, T., Tuzel, O., Susskind, J., Wang, W., Webb, R.: Learning from simulated and unsupervised images through adversarial training. In: CVPR (2017)Google Scholar
  30. 30.
    Sun, X., Zheng, L.: Dissecting person re-identification from the viewpoint of viewpoint. In: CVPR (2019)Google Scholar
  31. 31.
    Sun, Y., Zheng, L., Yang, Y., Tian, Q., Wang, S.: Beyond part models: person retrieval with refined part pooling (and a strong convolutional baseline). In: ECCV (2018)Google Scholar
  32. 32.
    Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. In: CVPR (2016)Google Scholar
  33. 33.
    Tang, Z., et al.: Pamtri: pose-aware multi-task learning for vehicle re-identification using highly randomized synthetic data. In: ICCV (2019)Google Scholar
  34. 34.
    Tang, Z., et al.: Cityflow: a city-scale benchmark for multi-target multi-camera vehicle tracking and re-identification. In: CVPR (2019)Google Scholar
  35. 35.
    Tremblay, J., et al.: Training deep networks with synthetic data: bridging the reality gap by domain randomization. In: CVPR Workshops (2018)Google Scholar
  36. 36.
    Wang, Z., et al.: Orientation invariant feature embedding and spatial temporal regularization for vehicle re-identification. In: ICCV (2017)Google Scholar
  37. 37.
    Wright, S.J.: Coordinate descent algorithms. Math. Programm. 151(1), 3–34 (2015)MathSciNetCrossRefGoogle Scholar
  38. 38.
    Xue, Z., Mao, W., Zheng, L.: Learning to simulate complex scenes. arXiv preprint arXiv:2006.14611 (2020)
  39. 39.
    Yang, L., Luo, P., Change Loy, C., Tang, X.: A large-scale car dataset for fine-grained categorization and verification. In: CVPR (2015)Google Scholar
  40. 40.
    Yao, Y., Plested, J., Gedeon, T.: Information-preserving feature filter for short-term eeg signals. Neurocomputing 408, 91–99 (2020)CrossRefGoogle Scholar
  41. 41.
    Zheng, L., et al.: MARS: a video benchmark for large-scale person re-identification. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9910, pp. 868–884. Springer, Cham (2016).  https://doi.org/10.1007/978-3-319-46466-4_52CrossRefGoogle Scholar
  42. 42.
    Zheng, Z., Ruan, T., Wei, Y., Yang, Y.: Vehiclenet: learning robust feature representation for vehicle re-identification. In: CVPR Workshops (2019)Google Scholar
  43. 43.
    Zheng, Z., Zheng, L., Yang, Y.: Unlabeled samples generated by gan improve the person re-identification baseline in vitro. In: CVPR, pp. 3754–3762 (2017)Google Scholar
  44. 44.
    Zhong, Z., Zheng, L., Zheng, Z., Li, S., Yang, Y.: Camera style adaptation for person re-identification. In: CVPR (2018)Google Scholar
  45. 45.
    Zhong, Z., Zheng, L., Zheng, Z., Li, S., Yang, Y.: Camstyle: a novel data augmentation method for person re-identification. IEEE Trans. Image Process. 28(3), 1176–1190 (2018)MathSciNetCrossRefGoogle Scholar
  46. 46.
    Zhou, Y., Shao, L.: Aware attentive multi-view inference for vehicle re-identification. In: CVPR (2018)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  1. 1.Australian National UniversityCanberraAustralia
  2. 2.NVIDIASanta ClaraUSA

Personalised recommendations