SRKD: Towards Efficient 3D Point Cloud Segmentation via Structure- and Relation-aware Knowledge Distillation
This addresses efficiency challenges for deploying 3D segmentation models in real-world applications, but it is incremental as it builds on existing knowledge distillation techniques.
The paper tackled the computational complexity and deployment limitations of large transformer-based models for 3D point cloud segmentation by proposing SRKD, a knowledge distillation framework that transfers knowledge from a large teacher model (>100M) to a lightweight student model (<15M), achieving state-of-the-art performance with significantly reduced model complexity.
3D point cloud segmentation faces practical challenges due to the computational complexity and deployment limitations of large-scale transformer-based models. To address this, we propose a novel Structure- and Relation-aware Knowledge Distillation framework, named SRKD, that transfers rich geometric and semantic knowledge from a large frozen teacher model (>100M) to a lightweight student model (<15M). Specifically, we propose an affinity matrix-based relation alignment module, which distills structural dependencies from the teacher to the student through point-wise similarity matching, enhancing the student's capability to learn contextual interactions. Meanwhile, we introduce a cross-sample mini-batch construction strategy that enables the student to perceive stable and generalized geometric structure. This aligns across diverse point cloud instances of the teacher, rather than within a single sample. Additionally, KL divergence is applied to align semantic distributions, and ground-truth supervision further reinforces accurate segmentation. Our method achieves state of the art performance with significantly reduced model complexity, demonstrating its effectiveness and efficiency in real-world deployment scenarios. Our Code is available at https://github.com/itsnotacie/SRKD.