Saved in:
Bibliographic Details
Main Authors: Zhu, Xiangyang, Zhang, Renrui, He, Bowei, Guo, Ziyu, Liu, Jiaming, Xiao, Han, Fu, Chaoyou, Dong, Hao, Gao, Peng
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2404.04050
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914742074867712
author Zhu, Xiangyang
Zhang, Renrui
He, Bowei
Guo, Ziyu
Liu, Jiaming
Xiao, Han
Fu, Chaoyou
Dong, Hao
Gao, Peng
author_facet Zhu, Xiangyang
Zhang, Renrui
He, Bowei
Guo, Ziyu
Liu, Jiaming
Xiao, Han
Fu, Chaoyou
Dong, Hao
Gao, Peng
contents 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, Seg-PN. Without training, Seg-NN extracts dense representations by hand-crafted filters and achieves comparable performance to existing parametric models. Due to the elimination of pre-training, Seg-NN can alleviate the domain gap issue and save a substantial amount of time. Based on Seg-NN, Seg-PN only requires training a lightweight QUEry-Support Transferring (QUEST) module, which enhances the interaction between the support set and query set. Experiments suggest that Seg-PN outperforms previous state-of-the-art method by +4.19% and +7.71% mIoU on S3DIS and ScanNet datasets respectively, while reducing training time by -90%, indicating its effectiveness and efficiency.
format Preprint
id arxiv_https___arxiv_org_abs_2404_04050
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle No Time to Train: Empowering Non-Parametric Networks for Few-shot 3D Scene Segmentation
Zhu, Xiangyang
Zhang, Renrui
He, Bowei
Guo, Ziyu
Liu, Jiaming
Xiao, Han
Fu, Chaoyou
Dong, Hao
Gao, Peng
Computer Vision and Pattern Recognition
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, Seg-PN. Without training, Seg-NN extracts dense representations by hand-crafted filters and achieves comparable performance to existing parametric models. Due to the elimination of pre-training, Seg-NN can alleviate the domain gap issue and save a substantial amount of time. Based on Seg-NN, Seg-PN only requires training a lightweight QUEry-Support Transferring (QUEST) module, which enhances the interaction between the support set and query set. Experiments suggest that Seg-PN outperforms previous state-of-the-art method by +4.19% and +7.71% mIoU on S3DIS and ScanNet datasets respectively, while reducing training time by -90%, indicating its effectiveness and efficiency.
title No Time to Train: Empowering Non-Parametric Networks for Few-shot 3D Scene Segmentation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2404.04050