A Unified Approach to Interpreting Self-supervised Pre-training Methods for 3D Point Clouds via Interactions

作者：Qiang Li, Jian Ruan, Fanghao Wu, Yuchi Chen, Zhihua Wei, Wen Shen · 年份：2025 · DOI：10.1109/cvpr52734.2025.02544 · 被引用次数：1 · 研究领域：3D Shape Modeling and Analysis、3D Surveying and Cultural Heritage、Image Processing and 3D Reconstruction

Recently, many self-supervised pre-training methods have been proposed to improve the performance of deep neural networks (DNNs) for 3D point clouds processing. However, the common mechanism underlying the effectiveness of different pre-training methods remains unclear. In this paper, we use game-theoretic interactions as a unified approach to explore the common mechanism of pre-training methods. Specifically, we decompose the output score of a DNN into the sum of numerous effects of interactions, with each interaction representing a distinct 3D substructure of the input point cloud. Based on the decomposed interactions, we draw the following conclusions. (1) The common mechanism across different pre-training methods is that they enhance the strength of high-order interactions encoded by DNNs, which represent complex and global 3D structures, while reducing the strength of low-order interactions, which represent simple and local 3D structures. (2) Sufficient pre-training and adequate fine-tuning data for downstream tasks further reinforce the mechanism described above. (3) Pre-training methods carry a potential risk of reducing the transferability of features encoded by DNNs. Inspired by the observed common mechanism, we propose a new method to directly enhance the strength of high-order interactions and reduce the strength of low-order interactions encoded by DNNs, improving performance without the need for pre-training on large-scale datasets. Experiments show that our meth...