无需训练即可实现3D点云少样本增量学习，有效防止遗忘与过拟合。
Foundation Model-Powered 3D Few-Shot Class Incremental Learning via Training-free Adaptor
- 利用基础3D模型和双缓存机制动态适配新任务。
- 在ModelNet、ShapeNet等数据集上显著优于现有方法。
- 适合资源有限但需持续学习新类别的3D视觉场景。
近年来，深度学习在处理点云数据方面取得进展，推动了3D计算机视觉中少样本增量学习（FSCIL）的研究兴趣。本文提出一种新方法，解决3D点云环境下的少样本持续增量学习问题。我们采用在大量点云数据上预训练的基础3D模型，借鉴基础模型跨任务泛化能力强的优势，设计了一种无需额外训练的自适应策略。该方法采用双缓存机制：一是基于模型预测置信度保留过往测试样本以防止遗忘，二是引入少量新任务样本以避免过拟合。这种动态适应方式在不依赖大量微调的前提下，保持了不同学习任务中的强性能。我们在ModelNet、ShapeNet、ScanObjectNN和CO3D等数据集上进行了测试，结果表明该方法优于其他FSCIL方法，验证了其有效性与通用性。代码已公开于https://github.com/ahmadisahar/ACCV_FCIL3D。
原文摘要 · Abstract (English)
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}.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。