Abstract
Data augmentation has been widely adopted for object detection in 3D point clouds. However, all previous related efforts have focused on manually designing specific data augmentation methods for individual architectures. In this work, we present the first attempt to automate the design of data augmentation policies for 3D object detection. We introduce the Progressive Population Based Augmentation (PPBA) algorithm, which learns to optimize augmentation strategies by narrowing down the search space and adopting the best parameters discovered in previous iterations. On the KITTI 3D detection test set, PPBA improves the StarNet detector by substantial margins on the moderate difficulty category of cars, pedestrians, and cyclists, outperforming all current state-of-the-art single-stage detection models. Additional experiments on the Waymo Open Dataset indicate that PPBA continues to effectively improve the StarNet and PointPillars detectors on a 20x larger dataset compared to KITTI. The magnitude of the improvements may be comparable to advances in 3D perception architectures and the gains come without an incurred cost at inference time. In subsequent experiments, we find that PPBA may be up to 10x more data efficient than baseline 3D detection models without augmentation, highlighting that 3D detection models may achieve competitive accuracy with far fewer labeled examples.
Z. Leng—Work done while at Google LLC.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
- 2.
- 3.
Our initial experiment on random search shows the performance distribution of augmentation policies is spread on the KITTI validation split. In order to save computation resources, the random search here is performed on a fine-grained search space.
References
Chen, X., Ma, H., Wan, J., Li, B., Xia, T.: Multi-view 3D object detection network for autonomous driving. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1907–1915 (2017)
Cho, H., Seo, Y.W., Kumar, B.V., Rajkumar, R.R.: A multi-sensor fusion system for moving object detection and tracking in urban driving environments. In: 2014 IEEE International Conference on Robotics and Automation (ICRA), pp. 1836–1843. IEEE (2014)
Ciregan, D., Meier, U., Schmidhuber, J.: Multi-column deep neural networks for image classification. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 3642–3649. IEEE (2012)
Cubuk, E.D., Zoph, B., Mane, D., Vasudevan, V., Le, Q.V.: Autoaugment: learning augmentation policies from data. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2019)
Cubuk, E.D., Zoph, B., Shlens, J., Le, Q.V.: Randaugment: practical data augmentation with no separate search. arXiv preprint arXiv:1909.13719 (2019)
DeVries, T., Taylor, G.W.: Improved regularization of convolutional neural networks with cutout. arXiv preprint arXiv:1708.04552 (2017)
Dwibedi, D., Misra, I., Hebert, M.: Cut, paste and learn: surprisingly easy synthesis for instance detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1301–1310 (2017)
Fang, H.S., Sun, J., Wang, R., Gou, M., Li, Y.L., Lu, C.: Instaboost: boosting instance segmentation via probability map guided copy-pasting. In: The IEEE International Conference on Computer Vision (2019)
Geiger, A., Lenz, P., Stiller, C., Urtasun, R.: Are we ready for autonomous driving? The Kitti vision benchmark suite. In: Conference on Computer Vision and Pattern Recognition (CVPR) (2012)
Girshick, R., Radosavovic, I., Gkioxari, G., Dollár, P., He, K.: Detectron (2018)
Ho, D., Liang, E., Stoica, I., Abbeel, P., Chen, X.: Population based augmentation: Efficient learning of augmentation policy schedules. In: International Conference on Machine Learning, pp. 2731–2741 (2019)
Jaderberg, M., et al.: Population based training of neural networks. arXiv preprint arXiv:1711.09846 (2017)
Jouppi, N.P., et al.: In-datacenter performance analysis of a tensor processing unit. In: Proceedings of the 44th Annual International Symposium on Computer Architecture, pp. 1–12 (2017)
Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems (2012)
Kumar, S., et al.: Scale MLPerf-0.6 models on Google TPU-v3 pods. arXiv preprint arXiv:1909.09756 (2019)
Lang, A.H., Vora, S., Caesar, H., Zhou, L., Yang, J., Beijbom, O.: Pointpillars: fast encoders for object detection from point clouds. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 12697–12705 (2019)
Lemley, J., Bazrafkan, S., Corcoran, P.: Smart augmentation learning an optimal data augmentation strategy. IEEE Access 5, 5858–5869 (2017)
Li, R., Li, X., Heng, P.A., Fu, C.W.: Pointaugment: an auto-augmentation framework for point cloud classification. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 6378–6387 (2020)
Liang, M., Yang, B., Wang, S., Urtasun, R.: Deep continuous fusion for multi-sensor 3D object detection. In: Proceedings of the European Conference on Computer Vision, pp. 641–656 (2018)
Lim, S., Kim, I., Kim, T., Kim, C., Kim, S.: Fast autoaugment. In: Advances in Neural Information Processing Systems (2019)
Luo, W., Yang, B., Urtasun, R.: Fast and furious: real time end-to-end 3D detection, tracking and motion forecasting with a single convolutional net. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3569–3577 (2018)
Ngiam, J., et al.: Starnet: targeted computation for object detection in point clouds. arXiv preprint arXiv:1908.11069 (2019)
Ratner, A.J., Ehrenberg, H., Hussain, Z., Dunnmon, J., Ré, C.: Learning to compose domain-specific transformations for data augmentation. In: Advances in Neural Information Processing Systems, pp. 3239–3249 (2017)
Sato, I., Nishimura, H., Yokoi, K.: Apac: augmented pattern classification with neural networks. arXiv preprint arXiv:1505.03229 (2015)
Shi, S., et al.: PV-RCNN: point-voxel feature set abstraction for 3D object detection. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 10529–10538 (2020)
Simard, P.Y., Steinkraus, D., Platt, J.C., et al.: Best practices for convolutional neural networks applied to visual document analysis. In: Proceedings of International Conference on Document Analysis and Recognition (2003)
Sun, P., et al.: Scalability in perception for autonomous driving: Waymo open dataset. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 2446–2454 (2020)
Szegedy, C., et al.: Going deeper with convolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1–9 (2015)
Thrun, S., et al.: Stanley: the robot that won the Darpa grand challenge. J. Field Robot. 23(9), 661–692 (2006)
Wan, L., Zeiler, M., Zhang, S., Le Cun, Y., Fergus, R.: Regularization of neural networks using dropconnect. In: International Conference on Machine Learning, pp. 1058–1066 (2013)
Yan, Y., Mao, Y., Li, B.: Second: sparsely embedded convolutional detection. Sensors 18(10), 3337 (2018)
Yang, B., Liang, M., Urtasun, R.: Hdnet: exploiting HD maps for 3D object detection. In: Proceedings of the 2nd Conference on Robot Learning, pp. 146–155 (2018)
Yang, B., Luo, W., Urtasun, R.: Pixor: real-time 3D object detection from point clouds. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7652–7660 (2018)
Zhang, H., Cisse, M., Dauphin, Y.N., Lopez-Paz, D.: mixup: beyond empirical risk minimization. In: International Conference on Learning Representations (2018)
Zhou, D., et al.: IoU loss for 2D/3D object detection. In: International Conference on 3D Vision (3DV). IEEE (2019)
Zhou, Y., et al.: End-to-end multi-view fusion for 3D object detection in lidar point clouds. In: Proceedings of the Conference on Robot Learning (2019)
Zhou, Y., Tuzel, O.: Voxelnet: end-to-end learning for point cloud based 3D object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4490–4499 (2018)
Zoph, B., Cubuk, E.D., Ghiasi, G., Lin, T.Y., Shlens, J., Le, Q.V.: Learning data augmentation strategies for object detection. arXiv preprint arXiv:1906.11172 (2019)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
1 Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Cheng, S. et al. (2020). Improving 3D Object Detection Through Progressive Population Based Augmentation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, JM. (eds) Computer Vision – ECCV 2020. ECCV 2020. Lecture Notes in Computer Science(), vol 12366. Springer, Cham. https://doi.org/10.1007/978-3-030-58589-1_17
Download citation
DOI: https://doi.org/10.1007/978-3-030-58589-1_17
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-58588-4
Online ISBN: 978-3-030-58589-1
eBook Packages: Computer ScienceComputer Science (R0)