Abstract
With the advancement of AI technology, deep learning-based intelligent driving assistance systems have seen substantial growth. However, 3D object detection remains a significant challenge due to LiDAR’s characteristics, such as sparse point clouds, varying point cloud density, and object occlusion, resulting in incomplete data. To enhance accuracy, models must be more robust. Past approaches emphasized model design, feature extraction, and obtaining finer features. In contrast, our approach introduces a novel perspective, addressing 3D object detection by focusing on sample processing without altering the model architecture. We found that point cloud variations can be substantial even within the same category. Adding such incomplete/corrupted samples to training does not improve performance; it can lead to model confusion and reduced generalization. This study proposed inferring the importance of samples based on the sample dispersed ratio and model reflection, encompassing classification and regression loss caused by sample variations. We utilize our Important Sample Selection (ISS) module to predict the sample’s importance for training and adjust the loss function to prioritize informative samples. We train and evaluate our detectors using the KITTI dataset. The experimental results show that our selection approach enhances overall detection performance without increasing parameter count.
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
References
Xu, Q., Zhong, Y., Neumann, U.: Behind the curtain: learning occluded shapes for 3D object detection. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 36, pp. 2893–2901 (2022)
Shi, S., et al.: PV-Rcnn: point-voxelfeature set abstraction for 3D object detection. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2020)
Deng, J., Shi, S., Li, P., Zhou, W., Zhang, Y., Li, H.: Voxel R-CNN: towards highperformance voxel-based 3D object detection. arXiv:2012.15712 (2020)
Vora, S., Lang, A.H., Helou, B., Beijbom, O.: Pointpainting: sequential fusion for 3Dobject detection. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2020)
Mahmoud, A., Hu, J.S., Waslander, S.L.: Dense voxel fusion for 3D object detection. In:Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, pp. 663–672 (2023)
Huang, T., Liu, Z., Chen, X., Bai, X.: Epnet: enhancing point features with image semantics for 3D object detection. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.M. (eds.) Computer Vision–ECCV 2020, pp. 35–52. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58555-6_3
Pang, S., Morris, D., Radha, H.: CLOCs: camera-LiDAR object candidates fusion for 3Dobject detection. In: 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 10386–10393 (2020). IEEE
Wang, C.-H., Chen, H.-W., Fu, L.-C.: Vpfnet: voxel-pixel fusion network for multi-class3D object detection. arXiv preprint arXiv:2111.00966 (2021)
Zhu, H., et al.: VPFNet: improving 3Dobject detection with virtual point based LiDAR and stereo data fusion. IEEE Trans. Multimedia (2022)
Chen, Y., Li, Y., Zhang, X., Sun, J., Jia, J.: Focal sparse convolutional networks for3D object detection. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 5428–5437 (2022)
Wu, X., et al.: Sparse fusedense: towards high quality 3D detection with depth completion. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 5418–5427 (2022)
Li, Y., et al.: Voxel field fusion for 3Dobject detection. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 1120–1129 (2022)
Geiger, A., Lenz, P., Stiller, C., Urtasun, R.: Vision meets robotics: the kitti dataset. Int. J. Robot. Res. 32(11), 1231–1237 (2013)
Geiger, A., Lenz, P., Urtasun, R.: Are we ready for autonomous driving? The kittivision benchmark suite. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition, pp. 3354–3361 (2012). IEEE
Qi, C.R., Su, H., Mo, K., Guibas, L.J.: Pointnet: deep learning on point sets for 3Dclassification and segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)
Qi, C.R., Yi, L., Su, H., Guibas, L.J.: Pointnet++: deep hierarchical feature learningon point sets in a metric space. In: Guyon, I., Luxburg, U.V., Bengio, S., Wallach, H., Fergus, R., Vishwanathan, S., Garnett, R. (eds.) Advances in Neural Information Processing Systems, vol. 30. Curran Associates, Inc. (2017)
Shi, S., Wang, X., Li, H.: Pointrcnn: 3D object proposal generation and detection frompoint cloud. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2019)
Yang, Z., Sun, Y., Liu, S., Jia, J.: 3DSSD: point-based 3D single stage object detector. In:Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2020)
Zhou, Y., Tuzel, O.: Voxelnet: end-to-end learning for point cloud based 3D objectdetection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2018)
Yan, Y., Mao, Y., Li, B.: Second: sparsely embedded convolutional detection. Sensors18(10) (2018) https://doi.org/10.3390/s18103337
Shi, S., Wang, Z., Shi, J., Wang, X., Li, H.: From points to parts: 3D object detection from point cloud with part-aware and part-aggregation network. arXiv preprintarXiv:1907.03670 (2019)
Lang, A.H., Vora, S., Caesar, H., Zhou, L., Yang, J., Beijbom, O.: Pointpillars: fastencoders for object detection from point clouds. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2019)
Lin, T.-Y., Goyal, P., Girshick, R., He, K., Dollár, P.: Focal loss for dense objectdetection. In: 2017 IEEE International Conference on Computer Vision (ICCV), pp. 2999–3007 (2017). https://doi.org/10.1109/ICCV.2017.324
Tian, Z., Shen, C., Chen, H., He, T.: FCOS: fully convolutional one-stage objectdetection. In: Proceedings of International Conference on Computer Vision (ICCV) (2019)
Zhang, S., Chi, C., Yao, Y., Lei, Z., Li, S.Z.: Bridging the gap between anchor-basedand anchor-free detection via adaptive training sample selection. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2020)
Kim, K., Lee, H.S.: Probabilistic anchor assignment with IOU prediction for objectdetection. In: ECCV (2020)
Ma, Y., Liu, S., Li, Z., Sun, J.: IQDet: instance-wise quality distribution sampling forobject detection. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1717–1725 (2021)
Shrivastava, A., Gupta, A., Girshick, R.: Training region-based object detectors withonline hard example mining. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016)
Li, X., et al.: Generalized focal loss: Learning qualified and distributed bounding boxes for dense object detection. Adv. Neural. Inf. Process. Syst. 33, 21002–21012 (2020)
Zhu, C., Chen, F., Shen, Z., Savvides, M.: Soft anchor-point object detection. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.M. (eds.) Computer Vision–ECCV 2020, pp. 91–107. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58545-7_6
Cai, Q., Pan, Y., Wang, Y., Liu, J., Yao, T., Mei, T.: Learning a unified sample weightingnetwork for object detection. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2020)
Li, S., He, C., Li, R., Zhang, L.: A dual weighting label assignment scheme for objectdetection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2022)
Kim, M., Jain, A.K., Liu, X.: Adaface: quality adaptive margin for face recognition. In:Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 18750–18759 (2022)
Acknowledgments
This work was financially supported in part (project number: 112UA10019) by the Co-creation Platform of the Industry Academia Innovation School, NYCU, under the framework of the National Key Fields Industry-University Cooperation and Skilled Personnel Training Act, from the Ministry of Education (MOE) and industry partners in Taiwan. It also supported in part by the National Science and Technology Council, Taiwan, under Grant NSTC-112-2221-E-A49-089-MY3, Grant NSTC-110-2221-E-A49-066-MY3, Grant NSTC-111- 2634-F-A49-010, Grant NSTC-112-2425-H-A49-001-, and in part by the Higher Education Sprout Project of the National Yang Ming Chiao Tung University and the Ministry of Education (MOE), Taiwan.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Chang, C.C. et al. (2024). Optimizing 3D Object Detection with Data Importance-Based Loss Reweighting. In: Lee, CY., Lin, CL., Chang, HT. (eds) Technologies and Applications of Artificial Intelligence. TAAI 2023. Communications in Computer and Information Science, vol 2075. Springer, Singapore. https://doi.org/10.1007/978-981-97-1714-9_15
Download citation
DOI: https://doi.org/10.1007/978-981-97-1714-9_15
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-97-1713-2
Online ISBN: 978-981-97-1714-9
eBook Packages: Computer ScienceComputer Science (R0)