English

Foundation Model-Powered 3D Few-Shot Class Incremental Learning via Training-free Adaptor

Computer Vision and Pattern Recognition 2024-10-15 v1

Abstract

Recent advances in deep learning for processing point clouds hold increased interest in Few-Shot Class Incremental Learning (FSCIL) for 3D computer vision. This paper introduces a new method to tackle the Few-Shot Continual Incremental Learning (FSCIL) problem in 3D point cloud environments. We leverage a foundational 3D model trained extensively on point cloud data. Drawing from recent improvements in foundation models, known for their ability to work well across different tasks, we propose a novel strategy that does not require additional training to adapt to new tasks. Our approach uses a dual cache system: first, it uses previous test samples based on how confident the model was in its predictions to prevent forgetting, and second, it includes a small number of new task samples to prevent overfitting. This dynamic adaptation ensures strong performance across different learning tasks without needing lots of fine-tuning. We tested our approach on datasets like ModelNet, ShapeNet, ScanObjectNN, and CO3D, showing that it outperforms other FSCIL methods and demonstrating its effectiveness and versatility. The code is available at \url{https://github.com/ahmadisahar/ACCV_FCIL3D}.

Keywords

Cite

@article{arxiv.2410.09237,
  title  = {Foundation Model-Powered 3D Few-Shot Class Incremental Learning via Training-free Adaptor},
  author = {Sahar Ahmadi and Ali Cheraghian and Morteza Saberi and Md. Towsif Abir and Hamidreza Dastmalchi and Farookh Hussain and Shafin Rahman},
  journal= {arXiv preprint arXiv:2410.09237},
  year   = {2024}
}

Comments

ACCV 2024

R2 v1 2026-06-28T19:18:31.310Z