提出STAG方法，让3D点云Transformer微调更高效
Token Adaptation via Side Graph Convolution for Efficient Fine-tuning of 3D Point Cloud Transformers
- 用并行图卷积侧网络动态适配令牌
- 参数仅0.43M，计算时间和内存大幅降低
- 适合资源有限场景下3D点云任务微调
预训练3D点云Transformer的参数高效微调已成为点云分析的重要技术。现有方法虽减少可调参数，但微调时仍存在高时空开销问题。本文提出新型参数高效微调算法STAG（Side Token Adaptation on a neighborhood Graph），通过与冻结主干Transformer并行运行的图卷积侧网络，实现对令牌的下游任务适配。该方法利用高效的图卷积、参数共享和减少梯度计算，显著降低微调的时空成本。我们还构建了新基准PCC13，包含多个公开3D点云数据集，用于全面评估。大量实验表明，STAG在保持与现有方法相当分类精度的同时，将可调参数降至0.43M，大幅降低微调时间和内存消耗。代码与基准将在https://github.com/takahikof/STAG发布。
原文摘要 · Abstract (English)
Parameter-efficient fine-tuning (PEFT) of pre-trained 3D point cloud Transformers has emerged as a promising technique for 3D point cloud analysis. While existing PEFT methods attempt to minimize the number of tunable parameters, they often suffer from high temporal and spatial computational costs during fine-tuning. This paper proposes a novel PEFT algorithm called Side Token Adaptation on a neighborhood Graph (STAG) to achieve superior temporal and spatial efficiency. STAG employs a graph convolutional side network operating in parallel with a frozen backbone Transformer to adapt tokens to downstream tasks. Through efficient graph convolution, parameter sharing, and reduced gradient computation, STAG significantly reduces both temporal and spatial costs for fine-tuning. We also present Point Cloud Classification 13 (PCC13), a new benchmark comprising diverse publicly available 3D point cloud datasets to facilitate comprehensive evaluation. Extensive experiments using multiple pre-trained models and PCC13 demonstrates the effectiveness of STAG. Specifically, STAG maintains classification accuracy comparable to existing methods while reducing tunable parameters to only 0.43M and achieving significant reductions in both computation time and memory consumption for fine-tuning. Code and benchmark will be available at: https://github.com/takahikof/STAG.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。