No Time to Train: Empowering Non-Parametric Networks for Few-shot 3D Scene Segmentation

arXiv:2404.04050v1 Announce Type: new
Abstract: To reduce the reliance on large-scale datasets, recent works in 3D segmentation resort to few-shot learning. Current 3D few-shot segmentation methods first pre-train models on 'seen' classes, and then evaluate their generalization performance on 'unseen' classes. However, the prior pre-training stage not only introduces excessive time overhead but also incurs a significant domain gap on 'unseen' classes. To tackle these issues, we propose a Non-parametric Network for few-shot 3D Segmentation, Seg-NN, and its Parametric variant, …

abstract arxiv cs.cv current datasets few-shot few-shot learning however networks non-parametric parametric performance pre-training prior reduce reliance scale segmentation stage train training type