Instance-aware Dynamic Prompt Tuning for Pre-trained Point Cloud Models

Pre-trained point cloud models have found extensive applications in 3D understanding tasks like object classification and part segmentation. However, the prevailing strategy of full fine-tuning in downstream tasks leads to large per-task storage overhead for model parameters, which limits the efficiency when applying large-scale pre-trained models. Inspired by the recent success of visual prompt tuning (VPT), this paper attempts to explore prompt tuning on pre-trained point cloud models, to pursue an elegant balance between performance and parameter efficiency. We find while instance-agnostic static prompting, e.g. VPT, shows some efficacy in downstream transfer, it is vulnerable to the distribution diversity caused by various types of noises in real-world point cloud data. To conquer this limitation, we propose a novel Instance-aware Dynamic Prompt Tuning (IDPT) strategy for pre-trained point cloud models. The essence of IDPT is to develop a dynamic prompt generation module to perceive semantic prior features of each point cloud instance and generate adaptive prompt tokens to enhance the model's robustness. Notably, extensive experiments demonstrate that IDPT outperforms full fine-tuning in most tasks with a mere 7% of the trainable parameters, providing a promising solution to parameter-efficient learning for pre-trained point cloud models. Code is available at \url{https://github.com/zyh16143998882/ICCV23-IDPT}.

PDF Abstract ICCV 2023 PDF ICCV 2023 Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
3D Point Cloud Classification ModelNet40 IDPT Overall Accuracy 94.4 # 13
Few-Shot 3D Point Cloud Classification ModelNet40 10-way (10-shot) IDPT Overall Accuracy 92.8 # 8
Few-Shot 3D Point Cloud Classification ModelNet40 10-way (20-shot) IDPT Overall Accuracy 95.4 # 9
Few-Shot 3D Point Cloud Classification ModelNet40 5-way (10-shot) IDPT Overall Accuracy 97.3 # 4
Few-Shot 3D Point Cloud Classification ModelNet40 5-way (20-shot) IDPT Overall Accuracy 97.9 # 10
3D Point Cloud Classification ScanObjectNN IDPT Overall Accuracy 88.51 # 23
OBJ-BG (OA) 93.12 # 10

Methods


No methods listed for this paper. Add relevant methods here