This paper presents a robust fine-tuning method designed for pre-trained 3D
point cloud models, to enhance feature robustness in downstream fine-tuned
models. We highlight the limitations of current fine-tuning methods and the
challenges of learning robust models. The proposed method, named Weight-Space
Ensembles for Fine-Tuning then Linear Probing (WiSE-FT-LP), integrates the
original pre-training and fine-tuning models through weight space integration
followed by Linear Probing. This approach significantly enhances the
performance of downstream fine-tuned models under distribution shifts,
improving feature robustness while maintaining high performance on the target
distribution. We apply this robust fine-tuning method to mainstream 3D point
cloud pre-trained models and evaluate the quality of model parameters and the
degradation of downstream task performance. Experimental results demonstrate
the effectiveness of WiSE-FT-LP in enhancing model robustness, effectively
balancing downstream task performance and model feature robustness without
altering the model structures.

该论文提出了一种针对预训练的 3D 点云模型的鲁棒微调方法，以增强下游微调模型中的特征鲁棒性。通过权重空间集成和线性探测相结合的方法，该方法显著提高了下游微调模型在分布变化情况下的性能，同时在目标分布上保持高性能，以提高特征鲁棒性。将这种鲁棒微调方法应用于主流的 3D 点云预训练模型，并评估模型参数的质量和下游任务性能的降低。实验结果表明，WiSE-FT-LP 方法有效提升了模型的鲁棒性，有效平衡了下游任务性能和模型特征的鲁棒性，而不改变模型结构。