.png){kind=icon}
返回
Class agnostic and specific consistency learning for weakly-supervised point cloud semantic segmentation
.png){kind=icon}
PRE
AI
DOI：10.1016/j.patcog.2024.111067.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
This paper focuses on Weakly Supervised 3D Point Cloud Semantic Segmentation (WS3DSS), which involves annotating only a few points while leaving a large number of points unlabeled in the training sample. Existing methods roughly force point-to-point predictions across different augmented versions of inputs close to each other. While this paper introduces a carefully-designed approach for learning class agnostic and specific consistency, based on the teacher-student framework. The proposed class-agnostic consistency learning, to bring the features of student and teacher models closer together, enhances the model robustness by replacing the traditional point-to-point prediction consistency with the group-to-group consistency based on the perturbed local neighboring points' features. Furthermore, to facilitate learning under class-wise supervisions, we propose a class-specific consistency learning method, pulling the feature of the unlabeled point towards its corresponding class-specific memory bank feature. Such a class of the unlabeled point is determined as the one with the highest probability predicted by the classifier. Extensive experimental results demonstrate that our proposed method surpasses the SOTA method SQN (Huet al., 2022) by 2.5% and 8.3% on S3DIS dataset, and 4.4% and 13.9% on ScanNetV2 dataset, on the 0.1% and 0.01% settings, respectively. Code is available at https://github.com/jasonwjw/CASC.
Keyword:
3d point cloud
Weakly-supervised learning
Consistency learning
期刊
IF:
7.6
论文数:
1.3W
被引数:
4.5W
机构
引用论文
Context-based local-global fusion network for 3D point cloud classification and segmentation基于上下文的局部-全局融合网络的三维点云分类与分割
PREAI
分享收藏RoMP-transformer: Rotational bounding box with multi-level feature pyramid transformer for object detectionRoMP-transformer: 具有用于对象检测的多级特征金字塔变压器的旋转边界框.png)
PATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
分享收藏
查看更多内容