Advertisement

Adapting Object Detectors with Conditional Domain Normalization

Conference paper
  • 560 Downloads
Part of the Lecture Notes in Computer Science book series (LNCS, volume 12356)

Abstract

Real-world object detectors are often challenged by the domain gaps between different datasets. In this work, we present the Conditional Domain Normalization (CDN) to bridge the domain distribution gap. CDN is designed to encode different domain inputs into a shared latent space, where the features from different domains carry the same domain attribute. To achieve this, we first disentangle the domain-specific attribute out of the semantic features from source domain via a domain embedding module, which learns a domain-vector to characterize the domain attribute information. Then this domain-vector is used to encode the features from target domain through a conditional normalization, resulting in different domains’ features carrying the same domain attribute. We incorporate CDN into various convolution stages of an object detector to adaptively address the domain shifts of different level’s representation. In contrast to existing adaptation works that conduct domain confusion learning on semantic features to remove domain-specific factors, CDN aligns different domain distributions by modulating the semantic features of target domains conditioned on the learned domain-vector of the source domain. Extensive experiments show that CDN outperforms existing methods remarkably on both real-to-real and synthetic-to-real adaptation benchmarks, including 2D image detection and 3D point cloud detection.

Supplementary material

504452_1_En_24_MOESM1_ESM.pdf (66.1 mb)
Supplementary material 1 (pdf 67648 KB)

References

  1. 1.
    Ben-David, S., Blitzer, J., Crammer, K., Kulesza, A., Pereira, F., Vaughan, J.W.: A theory of learning from different domains. Mach. Learn. 79, 151–175 (2010).  https://doi.org/10.1007/s10994-009-5152-4MathSciNetCrossRefGoogle Scholar
  2. 2.
    Bousmalis, K., Silberman, N., Dohan, D., Erhan, D., Krishnan, D.: Unsupervised pixel-level domain adaptation with generative adversarial networks. In: CVPR (2017)Google Scholar
  3. 3.
    Chen, X., et al.: 3D object proposals for accurate object class detection. In: Advances in Neural Information Processing Systems (2015)Google Scholar
  4. 4.
    Chen, Y., Li, W., Sakaridis, C., Dai, D., Van Gool, L.: Domain adaptive faster R-CNN for object detection in the wild. In: CVPR (2018)Google Scholar
  5. 5.
    Cordts, M., et al.: The cityscapes dataset for semantic urban scene understanding. In: CVPR (2016)Google Scholar
  6. 6.
    Dumoulin, V., Shlens, J., Kudlur, M.: A learned representation for artistic style. arXiv preprint arXiv:1610.07629 (2016)
  7. 7.
    Gaidon, A., Wang, Q., Cabon, Y., Vig, E.: Virtual worlds as proxy for multi-object tracking analysis. In: CVPR (2016)Google Scholar
  8. 8.
    Ganin, Y., Lempitsky, V.: Unsupervised domain adaptation by backpropagation. In: ICML (2015)Google Scholar
  9. 9.
    Geiger, A., Lenz, P., Urtasun, R.: Are we ready for autonomous driving? The KITTI vision benchmark suite. In: CVPR (2012)Google Scholar
  10. 10.
    Girshick, R.: Fast R-CNN. In: ICCV (2015)Google Scholar
  11. 11.
    Girshick, R., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: CVPR (2014)Google Scholar
  12. 12.
    He, K., Gkioxari, G., Dollár, P., Girshick, R.: Mask R-CNN. In: ICCV (2017)Google Scholar
  13. 13.
    He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR (2016)Google Scholar
  14. 14.
    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: Advances in Neural Information Processing Systems (2017)Google Scholar
  15. 15.
    Hoffman, J., et al.: CyCADA: cycle-consistent adversarial domain adaptation. arXiv preprint arXiv:1711.03213 (2017)
  16. 16.
    Huang, X., Belongie, S.: Arbitrary style transfer in real-time with adaptive instance normalization. In: ICCV (2017)Google Scholar
  17. 17.
    Hurl, B., Czarnecki, K., Waslander, S.: Precise synthetic image and LiDAR (PreSIL) dataset for autonomous vehicle perception. In: 2019 IEEE Intelligent Vehicles Symposium (IV) (2019)Google Scholar
  18. 18.
    Inoue, N., Furuta, R., Yamasaki, T., Aizawa, K.: Cross-domain weakly-supervised object detection through progressive domain adaptation. In: CVPR (2018)Google Scholar
  19. 19.
    Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. arXiv preprint arXiv:1502.03167 (2015)
  20. 20.
    James, S., et al.: Sim-to-real via sim-to-sim: data-efficient robotic grasping via randomized-to-canonical adaptation networks. In: CVPR (2019)Google Scholar
  21. 21.
    Johnson-Roberson, M., Barto, C., Mehta, R., Sridhar, S.N., Rosaen, K., Vasudevan, R.: Driving in the matrix: can virtual worlds replace human-generated annotations for real world tasks? arXiv preprint arXiv:1610.01983 (2016)
  22. 22.
    Kim, T., Jeong, M., Kim, S., Choi, S., Kim, C.: Diversify and match: a domain adaptive representation learning paradigm for object detection. In: CVPR (2019)Google Scholar
  23. 23.
    Liu, Z., et al.: Open compound domain adaptation. In: CVPR (2020)Google Scholar
  24. 24.
    Long, M., Cao, Z., Wang, J., Jordan, M.I.: Conditional adversarial domain adaptation. In: Advances in Neural Information Processing Systems (2018)Google Scholar
  25. 25.
    Park, T., Liu, M.Y., Wang, T.C., Zhu, J.Y.: Semantic image synthesis with spatially-adaptive normalization. arXiv preprint arXiv:1903.07291 (2019)
  26. 26.
    Peng, C., et al.: MegDet: a large mini-batch object detector. In: CVPR (2018)Google Scholar
  27. 27.
    Peng, X., Bai, Q., Xia, X., Huang, Z., Saenko, K., Wang, B.: Moment matching for multi-source domain adaptation. In: ICCV (2019)Google Scholar
  28. 28.
    Peng, X.B., Andrychowicz, M., Zaremba, W., Abbeel, P.: Sim-to-real transfer of robotic control with dynamics randomization. In: ICRA. IEEE (2018)Google Scholar
  29. 29.
    Qi, C.R., Yi, L., Su, H., Guibas, L.J.: PointNet++: deep hierarchical feature learning on point sets in a metric space. In: Advances in Neural Information Processing Systems (2017)Google Scholar
  30. 30.
    Qin, C., You, H., Wang, L., Kuo, C.C.J., Fu, Y.: PointDAN: a multi-scale 3D domain adaption network for point cloud representation. In: Advances in Neural Information Processing Systems (2019)Google Scholar
  31. 31.
    Quionero-Candela, J., Sugiyama, M., Schwaighofer, A., Lawrence, N.D.: Dataset Shift in Machine Learning. The MIT Press, Cambridge (2009)Google Scholar
  32. 32.
    Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems (2015)Google Scholar
  33. 33.
    Saito, K., Ushiku, Y., Harada, T., Saenko, K.: Strong-weak distribution alignment for adaptive object detection. In: CVPR (2019)Google Scholar
  34. 34.
    Sakaridis, C., Dai, D., Van Gool, L.: Semantic foggy scene understanding with synthetic data. Int. J. Comput. Vis. 126, 973–992 (2018).  https://doi.org/10.1007/s11263-018-1072-8CrossRefGoogle Scholar
  35. 35.
    Saleh, K., et al.: Domain adaptation for vehicle detection from bird’s eye view lidar point cloud data. In: ICCV Workshops (2019)Google Scholar
  36. 36.
    Sankaranarayanan, S., Balaji, Y., Jain, A., Nam Lim, S., Chellappa, R.: Learning from synthetic data: addressing domain shift for semantic segmentation. In: CVPR (2018)Google Scholar
  37. 37.
    Shi, S., Wang, X., Li, H.: PointRCNN: 3D object proposal generation and detection from point cloud. In: CVPR (2019)Google Scholar
  38. 38.
    Tobin, J., Fong, R., Ray, A., Schneider, J., Zaremba, W., Abbeel, P.: Domain randomization for transferring deep neural networks from simulation to the real world. In: IROS. IEEE (2017)Google Scholar
  39. 39.
    Tsai, Y.H., Sohn, K., Schulter, S., Chandraker, M.: Domain adaptation for structured output via discriminative representations. arXiv preprint arXiv:1901.05427 (2019)
  40. 40.
    Tzeng, E., Hoffman, J., Saenko, K., Darrell, T.: Adversarial discriminative domain adaptation. In: CVPR (2017)Google Scholar
  41. 41.
    Wang, X., Yu, K., Dong, C., Change Loy, C.: Recovering realistic texture in image super-resolution by deep spatial feature transform. In: CVPR (2018)Google Scholar
  42. 42.
    Wrenninge, M., Unger, J.: Synscapes: a photorealistic synthetic dataset for street scene parsing. arXiv preprint arXiv:1810.08705 (2018)
  43. 43.
    Yosinski, J., Clune, J., Nguyen, A., Fuchs, T., Lipson, H.: Understanding neural networks through deep visualization. arXiv preprint arXiv:1506.06579 (2015)
  44. 44.
    Yu, F., et al.: BDD100K: a diverse driving video database with scalable annotation tooling. arXiv preprint arXiv:1805.04687 (2018)
  45. 45.
    Yue, X., Wu, B., Seshia, S.A., Keutzer, K., Sangiovanni-Vincentelli, A.L.: A LiDAR point cloud generator: from a virtual world to autonomous driving. In: Proceedings of the 2018 ACM on International Conference on Multimedia Retrieval (2018)Google Scholar
  46. 46.
    Zhu, X., Pang, J., Yang, C., Shi, J., Lin, D.: Adapting object detectors via selective cross-domain alignment. In: CVPR (2019)Google Scholar
  47. 47.
    Zou, Y., Yu, Z., Vijaya Kumar, B.V.K., Wang, J.: Unsupervised domain adaptation for semantic segmentation via class-balanced self-training. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11207, pp. 297–313. Springer, Cham (2018).  https://doi.org/10.1007/978-3-030-01219-9_18CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  1. 1.The Chinese University of Hong KongSha TinHong Kong
  2. 2.SenseTime ResearchSha TinHong Kong

Personalised recommendations