通过动态图特征提升点云分析效率，参数量少却性能不降。
GFT: Graph Feature Tuning for Efficient Point Cloud Analysis
- 用轻量图卷积生成动态图，通过跨注意力传递特征
- 训练参数减少，分类与分割任务性能接近现有方法
- 适合资源受限场景下的点云模型快速适配
参数高效微调（PEFT）通过仅更新模型中少量参数，显著降低计算与内存开销，实现新任务的快速适应且性能损失小。已有针对点云数据设计的PEFT方法，但通用方法仍不理想。本文提出一种面向点云的新型PEFT——图特征调优（GFT），利用轻量图卷积网络从Transformer的初始输入中学习动态图，并通过跳跃连接与高效交叉注意力模块将图特征传递至深层。在物体分类与分割任务上的大量实验表明，GFT在保持同等性能的同时进一步减少了可训练参数量。代码已开源：https://github.com/manishdhakal/GFT。
原文摘要 · Abstract (English)
Parameter-efficient fine-tuning (PEFT) significantly reduces computational and memory costs by updating only a small subset of the model's parameters, enabling faster adaptation to new tasks with minimal loss in performance. Previous studies have introduced PEFTs tailored for point cloud data, as general approaches are suboptimal. To further reduce the number of trainable parameters, we propose a point-cloud-specific PEFT, termed Graph Features Tuning (GFT), which learns a dynamic graph from initial tokenized inputs of the transformer using a lightweight graph convolution network and passes these graph features to deeper layers via skip connections and efficient cross-attention modules. Extensive experiments on object classification and segmentation tasks show that GFT operates in the same domain, rivalling existing methods, while reducing the trainable parameters. Code is available at https://github.com/manishdhakal/GFT.
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。