Joint Homophily and Heterophily Relational Knowledge Distillation for Efficient and Compact 3D Object Detection
Pages 2127 - 2135
Abstract
3D Object Detection (3DOD) aims to accurately locate and identify 3D objects in point clouds, facing the challenge of balancing model performance with computational efficiency. Knowledge distillation emerges as a vital method for model compression in 3DOD, transferring knowledge from complex, larger models to smaller, efficient ones. However, the effectiveness of these methods is constrained by the intrinsic sparsity and structural complexity of point clouds. In this paper, we propose a novel methodology termed Joint Homophily and Heterophily Relational Knowledge Distillation (H2RKD) to distill robust relational knowledge in point clouds, thereby enhancing intra-object similarity and refining inter-object distinction. This unified strategy encompasses the integration of Collaborative Global Distillation (CGD) for distilling global relational knowledge across both distance and angular dimensions, and Separate Local Distillation (SLD) for a focused distillation of local relational dynamics. By seamlessly leveraging the relational dynamics within point clouds, the H2RKD facilitates a comprehensive knowledge transfer, significantly advancing 3D object detection capabilities. Extensive experiments on KITTI and unScenes datasets demonstrate the effectiveness of the proposed H2RKD.
References
[1]
Cristian Buciluǎ, Rich Caruana, and Alexandru Niculescu-Mizil. 2006. Model compression. In Proceedings of the 12th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 535--541.
[2]
Holger Caesar, Varun Bankiti, Alex H Lang, Sourabh Vora, Venice Erin Liong, Qiang Xu, Anush Krishnan, Yu Pan, Giancarlo Baldan, and Oscar Beijbom. 2020. nuscenes: A multimodal dataset for autonomous driving. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 11621--11631.
[3]
Yilun Chen, Shu Liu, Xiaoyong Shen, and Jiaya Jia. 2019. Fast point r-cnn. In Proceedings of the IEEE/CVF international Conference on Computer Vision. 9775--9784.
[4]
Hyeon Cho, Junyong Choi, Geonwoo Baek, and Wonjun Hwang. 2023. itkd: Interchange transfer-based knowledge distillation for 3d object detection. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 13540--13549.
[5]
MMDetection3D Contributors. 2020. MMDetection3D: OpenMMLab next-generation platform for general 3D object detection.
[6]
Xing Dai, Zeren Jiang, Zhao Wu, Yiping Bao, Zhicheng Wang, Si Liu, and Erjin Zhou. 2021. General instance distillation for object detection. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 7842--7851.
[7]
Jiajun Deng, Shaoshuai Shi, Peiwei Li, Wengang Zhou, Yanyong Zhang, and Houqiang Li. 2021. Voxel r-cnn: Towards high performance voxel-based 3d object detection. In Proceedings of the AAAI conference on artificial intelligence, Vol. 35. 1201--1209.
[8]
Andreas Geiger, Philip Lenz, Christoph Stiller, and Raquel Urtasun. 2013. Vision meets robotics: The kitti dataset. The International Journal of Robotics Research, Vol. 32, 11 (2013), 1231--1237.
[9]
Byeongho Heo, Jeesoo Kim, Sangdoo Yun, Hyojin Park, Nojun Kwak, and Jin Young Choi. 2019. A comprehensive overhaul of feature distillation. In Proceedings of the IEEE/CVF International Conference on Computer Vision. 1921--1930.
[10]
Peter J Huber. 1992. Robust estimation of a location parameter. In Breakthroughs in statistics: Methodology and distribution. Springer, 492--518.
[11]
Marvin Klingner, Shubhankar Borse, Varun Ravi Kumar, Behnaz Rezaei, Venkatraman Narayanan, Senthil Yogamani, and Fatih Porikli. 2023. X3KD: Knowledge Distillation Across Modalities, Tasks and Stages for Multi-Camera 3D Object Detection. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 13343--13353.
[12]
Alex H Lang, Sourabh Vora, Holger Caesar, Lubing Zhou, Jiong Yang, and Oscar Beijbom. 2019. Pointpillars: Fast encoders for object detection from point clouds. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 12697--12705.
[13]
Yanjing Li, Sheng Xu, Mingbao Lin, Jihao Yin, Baochang Zhang, and Xianbin Cao. 2023. Representation Disparity-aware Distillation for 3D Object Detection. In Proceedings of the IEEE/CVF International Conference on Computer Vision. 6715--6724.
[14]
Jiaming Liu, Yue Wu, Maoguo Gong, Qiguang Miao, Wenping Ma, Cai Xu, and Can Qin. 2024. M3SOT: Multi-Frame, Multi-Field, Multi-Space 3D Single Object Tracking. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 38. 3630--3638.
[15]
Ilya Loshchilov and Frank Hutter. 2018. Fixing weight decay regularization in adam. (2018).
[16]
Wonpyo Park, Dongju Kim, Yan Lu, and Minsu Cho. 2019. Relational knowledge distillation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 3967--3976.
[17]
Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, et al. 2019. Pytorch: An imperative style, high-performance deep learning library. Advances in neural information processing systems, Vol. 32 (2019).
[18]
Charles R Qi, Hao Su, Kaichun Mo, and Leonidas J Guibas. 2017. Pointnet: Deep learning on point sets for 3d classification and segmentation. In Proceedings of the IEEE conference on computer vision and pattern recognition. 652--660.
[19]
Charles Ruizhongtai Qi, Li Yi, Hao Su, and Leonidas J Guibas. 2017. Pointnet: Deep hierarchical feature learning on point sets in a metric space. Advances in neural information processing systems, Vol. 30 (2017).
[20]
Adriana Romero, Nicolas Ballas, Samira Ebrahimi Kahou, Antoine Chassang, Carlo Gatta, and Yoshua Bengio. 2014. Fitnets: Hints for thin deep nets. arXiv preprint arXiv:1412.6550 (2014).
[21]
Shaoshuai Shi, Chaoxu Guo, Li Jiang, Zhe Wang, Jianping Shi, Xiaogang Wang, and Hongsheng Li. 2020. Pv-rcnn: Point-voxel feature set abstraction for 3d object detection. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 10529--10538.
[22]
Shaoshuai Shi, Xiaogang Wang, and Hongsheng Li. 2019. Pointrcnn: 3d object proposal generation and detection from point cloud. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 770--779.
[23]
Yonglong Tian, Dilip Krishnan, and Phillip Isola. 2019. Contrastive representation distillation. arXiv preprint arXiv:1910.10699 (2019).
[24]
Tao Wang, Li Yuan, Xiaopeng Zhang, and Jiashi Feng. 2019. Distilling object detectors with fine-grained feature imitation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 4933--4942.
[25]
Tao Wang, Li Yuan, Xiaopeng Zhang, and Jiashi Feng. 2019. Distilling object detectors with fine-grained feature imitation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 4933--4942.
[26]
Yue Wang, Alireza Fathi, Abhijit Kundu, David A Ross, Caroline Pantofaru, Tom Funkhouser, and Justin Solomon. 2020. Pillar-based object detection for autonomous driving. In Computer Vision-ECCV 2020: 16th European Conference, Glasgow, UK, August 23-28, 2020, Proceedings, Part XXII 16. Springer, 18--34.
[27]
Yue Wang, Alireza Fathi, Jiajun Wu, Thomas Funkhouser, and Justin Solomon. 2020. Multi-frame to single-frame: Knowledge distillation for 3d object detection. arXiv preprint arXiv:2009.11859 (2020).
[28]
Yue Wu, Jiaming Liu, Maoguo Gong, Peiran Gong, Xiaolong Fan, A Kai Qin, Qiguang Miao, and Wenping Ma. 2023. Self-supervised intra-modal and cross-modal contrastive learning for point cloud understanding. IEEE Transactions on Multimedia, Vol. 26 (2023), 1626--1638.
[29]
Jihan Yang, Shaoshuai Shi, Runyu Ding, Zhe Wang, and Xiaojuan Qi. 2022. Towards efficient 3d object detection with knowledge distillation. Advances in Neural Information Processing Systems, Vol. 35 (2022), 21300--21313.
[30]
Zhendong Yang, Zhe Li, Xiaohu Jiang, Yuan Gong, Zehuan Yuan, Danpei Zhao, and Chun Yuan. 2022. Focal and global knowledge distillation for detectors. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 4643--4652.
[31]
Zetong Yang, Yanan Sun, Shu Liu, Xiaoyong Shen, and Jiaya Jia. 2019. Std: Sparse-to-dense 3d object detector for point cloud. In Proceedings of the IEEE/CVF International Conference on Computer Vision. 1951--1960.
[32]
Tianwei Yin, Xingyi Zhou, and Philipp Krahenbuhl. 2021. Center-based 3d object detection and tracking. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 11784--11793.
[33]
Sergey Zagoruyko and Nikos Komodakis. 2016. Paying more attention to attention: Improving the performance of convolutional neural networks via attention transfer. arXiv preprint arXiv:1612.03928 (2016).
[34]
Linfeng Zhang, Runpei Dong, Hung-Shuo Tai, and Kaisheng Ma. 2023. Pointdistiller: Structured knowledge distillation towards efficient and compact 3d detection. In Proceedings of the IEEE/CVF conference on Computer Vision and Pattern Recognition. 21791--21801.
[35]
Linfeng Zhang and Kaisheng Ma. 2020. Improve object detection with feature-based knowledge distillation: Towards accurate and efficient detectors. In International Conference on Learning Representations.
[36]
Linfeng Zhang and Kaisheng Ma. 2020. Improve object detection with feature-based knowledge distillation: Towards accurate and efficient detectors. In International Conference on Learning Representations.
[37]
Wu Zheng, Li Jiang, Fanbin Lu, Yangyang Ye, and Chi-Wing Fu. 2022. Boosting Single-Frame 3D Object Detection by Simulating Multi-Frame Point Clouds. In Proceedings of the 30th ACM International Conference on Multimedia. 4848--4856.
[38]
Wu Zheng, Weiliang Tang, Li Jiang, and Chi-Wing Fu. 2021. SE-SSD: Self-ensembling single-stage object detector from point cloud. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 14494--14503.
[39]
Shengchao Zhou, Weizhou Liu, Chen Hu, Shuchang Zhou, and Chao Ma. 2023. UniDistill: A Universal Cross-Modality Knowledge Distillation Framework for 3D Object Detection in Bird's-Eye View. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 5116--5125.
[40]
Yin Zhou and Oncel Tuzel. 2018. Voxelnet: End-to-end learning for point cloud based 3d object detection. In Proceedings of the IEEE conference on computer vision and pattern recognition. 4490--4499.
Index Terms
- Joint Homophily and Heterophily Relational Knowledge Distillation for Efficient and Compact 3D Object Detection
Recommendations
VRDistill: Vote Refinement Distillation for Efficient Indoor 3D Object Detection
MM '24: Proceedings of the 32nd ACM International Conference on MultimediaRecently, indoor 3D object detection has shown impressive progress. However, these improvements have come at the cost of increased memory consumption and longer inference times, making it difficult to apply these methods in practical scenarios. To ...
Structured Knowledge Distillation for Accurate and Efficient Object Detection
Knowledge distillation, which aims to transfer the knowledge learned by a cumbersome teacher model to a lightweight student model, has become one of the most popular and effective techniques in computer vision. However, many previous knowledge ...
Cross-Weighting Knowledge Distillation for Object Detection
Rough SetsAbstractKnowledge distillation(KD) has been widely utilized for compressing object detection models and enhancing their accuracy. However, most current knowledge distillation methods have not adequately addressed common issues in object detection, ...
Comments
Information & Contributors
Information
Published In
October 2024
11719 pages
ISBN:9798400706868
DOI:10.1145/3664647
- General Chairs:
- Jianfei Cai,
- Mohan Kankanhalli,
- Balakrishnan Prabhakaran,
- Susanne Boll,
- Program Chairs:
- Ramanathan Subramanian,
- Liang Zheng,
- Vivek K. Singh,
- Pablo Cesar,
- Lexing Xie,
- Dong Xu
Copyright © 2024 ACM.
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].
Sponsors
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 28 October 2024
Check for updates
Author Tags
Qualifiers
- Research-article
Conference
MM '24
Sponsor:
MM '24: The 32nd ACM International Conference on Multimedia
October 28 - November 1, 2024
Melbourne VIC, Australia
Acceptance Rates
MM '24 Paper Acceptance Rate 1,150 of 4,385 submissions, 26%;
Overall Acceptance Rate 2,145 of 8,556 submissions, 25%
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 53Total Downloads
- Downloads (Last 12 months)53
- Downloads (Last 6 weeks)9
Reflects downloads up to 27 Jan 2025
Other Metrics
Citations
View Options
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in