Robust Fine-tuning for Pre-trained 3D Point Cloud Models

arXiv:2404.16422v1 Announce Type: new
Abstract: 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 …

abstract arxiv challenges cloud cs.cv current feature fine-tuning highlight limitations linear paper robust robust models robustness space type