Topology-Guided Knowledge Distillation for Efficient Point Cloud Processing

• URL: http://arxiv.org/abs/2505.08101v1
• Date: Mon, 12 May 2025 22:15:54 GMT
• Title: Topology-Guided Knowledge Distillation for Efficient Point Cloud Processing
• Authors: Luu Tung Hai, Thinh D. Le, Zhicheng Ding, Qing Tian, Truong-Son Hy,
• Abstract summary: This work introduces a novel distillation framework to transfer knowledge from a high-capacity teacher to a lightweight student model.<n>Our approach captures the underlying geometric structures of point clouds while selectively guiding the student model's learning process.<n>Our method achieves state-of-the-art performance among knowledge distillation techniques trained solely on LiDAR data.
• Score: 3.3903891679981593
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Point cloud processing has gained significant attention due to its critical role in applications such as autonomous driving and 3D object recognition. However, deploying high-performance models like Point Transformer V3 in resource-constrained environments remains challenging due to their high computational and memory demands. This work introduces a novel distillation framework that leverages topology-aware representations and gradient-guided knowledge distillation to effectively transfer knowledge from a high-capacity teacher to a lightweight student model. Our approach captures the underlying geometric structures of point clouds while selectively guiding the student model's learning process through gradient-based feature alignment. Experimental results in the Nuscenes, SemanticKITTI, and Waymo datasets demonstrate that the proposed method achieves competitive performance, with an approximately 16x reduction in model size and a nearly 1.9x decrease in inference time compared to its teacher model. Notably, on NuScenes, our method achieves state-of-the-art performance among knowledge distillation techniques trained solely on LiDAR data, surpassing prior knowledge distillation baselines in segmentation performance. Our implementation is available publicly at: https://github.com/HySonLab/PointDistill

Related papers

• Learning from Stochastic Teacher Representations Using Student-Guided Knowledge Distillation [64.15918654558816]
  Self-distillation (SSD) training strategy is introduced for filtering and weighting teacher representation to distill from task-relevant representations only.<n> Experimental results on real-world affective computing, wearable/biosignal datasets from the UCR Archive, the HAR dataset, and image classification datasets show that the proposed SSD method can outperform state-of-the-art methods.
  arXiv  Detail & Related papers  (2025-04-19T14:08:56Z)
• Efficient Point Cloud Classification via Offline Distillation Framework and Negative-Weight Self-Distillation Technique [46.266960248570086]
  We introduce an innovative offline recording strategy that avoids the simultaneous loading of both teacher and student models. This approach feeds a multitude of augmented samples into the teacher model, recording both the data augmentation parameters and the corresponding logit outputs. Experimental results demonstrate that the proposed distillation strategy enables the student model to achieve performance comparable to state-of-the-art models.
  arXiv  Detail & Related papers  (2024-09-03T16:12:12Z)
• TSCM: A Teacher-Student Model for Vision Place Recognition Using Cross-Metric Knowledge Distillation [6.856317526681759]
  Visual place recognition plays a pivotal role in autonomous exploration and navigation of mobile robots.<n>Existing methods overcome this by exploiting powerful yet large networks.<n>We propose a high-performance teacher and lightweight student distillation framework called TSCM.
  arXiv  Detail & Related papers  (2024-04-02T02:29:41Z)
• Bidirectional Knowledge Reconfiguration for Lightweight Point Cloud Analysis [74.00441177577295]
  Point cloud analysis faces computational system overhead, limiting its application on mobile or edge devices. This paper explores feature distillation for lightweight point cloud models. We propose bidirectional knowledge reconfiguration to distill informative contextual knowledge from the teacher to the student.
  arXiv  Detail & Related papers  (2023-10-08T11:32:50Z)
• Learning Lightweight Object Detectors via Multi-Teacher Progressive Distillation [56.053397775016755]
  We propose a sequential approach to knowledge distillation that progressively transfers the knowledge of a set of teacher detectors to a given lightweight student. To the best of our knowledge, we are the first to successfully distill knowledge from Transformer-based teacher detectors to convolution-based students.
  arXiv  Detail & Related papers  (2023-08-17T17:17:08Z)
• Point-to-Voxel Knowledge Distillation for LiDAR Semantic Segmentation [74.67594286008317]
  This article addresses the problem of distilling knowledge from a large teacher model to a slim student network for LiDAR semantic segmentation. We propose the Point-to-Voxel Knowledge Distillation (PVD), which transfers the hidden knowledge from both point level and voxel level.
  arXiv  Detail & Related papers  (2022-06-05T05:28:32Z)
• PointDistiller: Structured Knowledge Distillation Towards Efficient and Compact 3D Detection [15.79799516495951]
  This paper proposes PointDistiller, a structured knowledge distillation framework for point clouds-based 3D detection. PointDistiller includes local distillation which extracts and distills the local geometric structure of point clouds with dynamic graph convolution and reweighted learning strategy. Our 4X compressed PointPillars student achieves 2.8 and 3.4 mAP improvements on BEV and 3D object detection, outperforming its teacher by 0.9 and 1.8 mAP, respectively.
  arXiv  Detail & Related papers  (2022-05-23T07:40:07Z)
• Pixel Distillation: A New Knowledge Distillation Scheme for Low-Resolution Image Recognition [124.80263629921498]
  We propose Pixel Distillation that extends knowledge distillation into the input level while simultaneously breaking architecture constraints. Such a scheme can achieve flexible cost control for deployment, as it allows the system to adjust both network architecture and image quality according to the overall requirement of resources.
  arXiv  Detail & Related papers  (2021-12-17T14:31:40Z)
• Powerpropagation: A sparsity inducing weight reparameterisation [65.85142037667065]
  We introduce Powerpropagation, a new weight- parameterisation for neural networks that leads to inherently sparse models. Models trained in this manner exhibit similar performance, but have a distribution with markedly higher density at zero, allowing more parameters to be pruned safely. Here, we combine Powerpropagation with a traditional weight-pruning technique as well as recent state-of-the-art sparse-to-sparse algorithms, showing superior performance on the ImageNet benchmark.
  arXiv  Detail & Related papers  (2021-10-01T10:03:57Z)
• Self-Feature Regularization: Self-Feature Distillation Without Teacher Models [0.0]
  Self-Feature Regularization(SFR) is proposed, which uses features in the deep layers to supervise feature learning in the shallow layers. We firstly use generalization-l2 loss to match local features and a many-to-one approach to distill more intensively in the channel dimension.
  arXiv  Detail & Related papers  (2021-03-12T15:29:00Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.