Weakly Supervised 3D Point Cloud Segmentation via Multi-Prototype Learning

被引:11
|
作者
Su, Yongyi [1 ]
Xu, Xun [2 ,3 ]
Jia, Kui [1 ]
机构
[1] South China Univ Technol, Sch Elect & Informat Engn, Guangzhou 510641, Peoples R China
[2] ASTAR, I2R, Singapore 138632, Singapore
[3] Southwest Jiaotong Univ, Sch Comp & Artificial Intelligence, Chengdu 611756, Peoples R China
基金
中国国家自然科学基金;
关键词
3D point cloud; weakly supervised learning; multi-prototype learning; SEMANTIC SEGMENTATION;
D O I
10.1109/TCSVT.2023.3281151
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
Addressing the annotation challenge in 3D Point Cloud segmentation has inspired research into weakly supervised learning. Existing approaches mainly focus on exploiting manifold and pseudo-labeling to make use of large unlabeled data points. A fundamental challenge here lies in the large intra-class variations of local geometric structure, resulting in subclasses within a semantic class. In this work, we leverage this intuition and opt for maintaining an individual classifier for each subclass. Technically, we design a multi-prototype classifier, each prototype serves as the classifier weights for one subclass. To enable effective updating of multi-prototype classifier weights, we propose two constraints respectively for updating the prototypes w.r.t. all point features and for encouraging the learning of diverse prototypes. Experiments on weakly supervised 3D point cloud segmentation tasks validate the efficacy of proposed method in particular at low-label regime. Our hypothesis is also verified given the consistent discovery of semantic subclasses at no cost of additional annotations.
引用
收藏
页码:7723 / 7736
页数:14
相关论文
共 50 条
  • [1] Image Understands Point Cloud: Weakly Supervised 3D Semantic Segmentation via Association Learning
    Sun, Tianfang
    Zhang, Zhizhong
    Tan, Xin
    Qu, Yanyun
    Xie, Yuan
    IEEE TRANSACTIONS ON IMAGE PROCESSING, 2024, 33 : 1838 - 1852
  • [2] A survey on weakly supervised 3D point cloud semantic segmentation
    Wang, Jingyi
    Liu, Yu
    Tan, Hanlin
    Zhang, Maojun
    IET COMPUTER VISION, 2024, 18 (03) : 329 - 342
  • [3] HybridCR: Weakly-Supervised 3D Point Cloud Semantic Segmentation via Hybrid Contrastive Regularization
    Li, Mengtian
    Xie, Yuan
    Shen, Yunhang
    Ke, Bo
    Qiao, Ruizhi
    Ren, Bo
    Lin, Shaohui
    Ma, Lizhuang
    2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2022), 2022, : 14910 - 14919
  • [4] PPDistiller: Weakly-supervised 3D point cloud semantic segmentation framework via point-to-pixel distillation
    Zhang, Yong
    Wu, Zhaolong
    Lan, Rukai
    Liang, Yingjie
    Liu, Yifan
    KNOWLEDGE-BASED SYSTEMS, 2024, 305
  • [5] WSDesc: Weakly Supervised 3D Local Descriptor Learning for Point Cloud Registration
    Li, Lei
    Fu, Hongbo
    Ovsjanikov, Maks
    IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS, 2023, 29 (07) : 3368 - 3379
  • [6] GECNN for Weakly Supervised Semantic Segmentation of 3D Point Clouds
    He, Zifen
    Zhu, Shouye
    Huang, Ying
    Zhang, Yinhui
    IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS, 2021, E104D (12) : 2237 - 2243
  • [7] Weakly Supervised Learning for Point Cloud Semantic Segmentation With Dual Teacher
    Yao, Baochen
    Xiao, Hui
    Zhuang, Jiayan
    Peng, Chengbin
    IEEE ROBOTICS AND AUTOMATION LETTERS, 2023, 8 (10) : 6347 - 6354
  • [8] Scribble-Based 3D Shape Segmentation via Weakly-Supervised Learning
    Shu, Zhenyu
    Shen, Xiaoyong
    Xin, Shiqing
    Chang, Qingjun
    Feng, Jieqing
    Kavan, Ladislav
    Liu, Ligang
    IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS, 2020, 26 (08) : 2671 - 2682
  • [9] Multi-Scale Classification and Contrastive Regularization: Weakly Supervised Large-Scale 3D Point Cloud Semantic Segmentation
    Wang, Jingyi
    He, Jingyang
    Liu, Yu
    Chen, Chen
    Zhang, Maojun
    Tan, Hanlin
    REMOTE SENSING, 2024, 16 (17)
  • [10] Weakly supervised 3D point cloud semantic segmentation for architectural heritage using teacher-guided consistency and contrast learning
    Huang, Shuowen
    Hu, Qingwu
    Ai, Mingyao
    Zhao, Pengcheng
    Li, Jian
    Cui, Hao
    Wang, Shaohua
    AUTOMATION IN CONSTRUCTION, 2024, 168