Joint Homophily and Heterophily Relational Knowledge Distillation for Efficient and Compact 3D Object Detection

Shidi Chen, Lili Wei, Liqian Liang, Congyan Lang

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.

Primary Subject Area: [Content] Vision and Language

Secondary Subject Area: [Content] Vision and Language

Relevance To Conference: Lidar-based 3D object detection (3DOD), which utilizes point clouds for precise object identification and localization, is a fundamental task in computer vision. It is critical for applications in robotics, autonomous driving, and augmented reality. With the demand for computational accuracy, 3DOD also faces these challenges: (1) high computational costs, (2) large parameters are difficult to deploy. Our work accelerates comprehensive knowledge transfer and significantly improves the capabilities of lighter 3D object detectors, effectively alleviating the above issues.

Submission Number: 1398