Token Adaptation via Side Graph Convolution for Efficient Fine-tuning of 3D Point Cloud Transformers

TL;DR

This paper introduces STAG, a side token adaptation method using graph convolution for efficient fine-tuning of 3D point cloud Transformers, reducing computational costs while maintaining accuracy.

Contribution

The paper proposes a novel PEFT algorithm called STAG that improves efficiency in fine-tuning 3D point cloud Transformers through graph convolution and parameter sharing.

Findings

STAG reduces fine-tuning parameters to 0.43M.

STAG significantly cuts down computation time and memory usage.

Maintains classification accuracy comparable to existing methods.

Abstract

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.