笔记：半监督的3D语义分割

半监督的意义：解决三维点云标注的时间和成本代价。
基于点云的深度学习问题
- voxel-based method 需要大量的memory cost
- view-based method 对3D数据的密度敏感
- point-based method 表现比较好，但是需要大量的标注信息
paper1:Guided Point Contrastive Learning for Semi-supervised Point Cloud Semantic Segmentation
- It demonstrates unlabeled point clouds can help to enhance the feature learning in both indoor and outdoor scenes.
- It extends contrastive learning to 3D point cloud semi-supervised semantic segmentation with pseudo-label guidance and confidence guidance.
  - It accordingly proposes the Guided Point Contrastive Learning framework for SSL-based point cloud segmentation and leverage the semantic predictions as pseudo guidance for improving the contrastive learning on unlabeled point clouds
- It proposes a category-balanced sampling strategy to alleviate the point class imbalance issue and to increase the embedding diversity.
  - Category-balanced sampling for positive pairs: CBS evenly samples positive pairs from each category. 对于类别C，选中的positive pairs 数为：
  - Category-balanced sampling for negative point set: CBS collects negative samples from scenes in the entire training set instead of just from the current scene.(因为在在具体场景可能确实一些class)
paper2:SSPC-Net: Semi-supervised Semantic 3D Point Cloud Segmentation Network
- Superpoint Graph Embedding

1.leverage the gated GNN to extract superpoints features. (由GNN网络提取到superpoint)
2.conduct the dynamic label propagation based on the superpoint graph strategy to generate pseudo labels.(进行动态标签传播，只考虑临近点，来产生伪标签点或者舍弃点)
3.perform a coupled attention mechanism to further boost the extraction of discriminative contextual features in the point cloud based on the supervised superpoints and the extended superpoints.(增强标签点和伪标签点的耦合关系)

paper3:Perturbed Self-Distillation: Weakly Supervised Large-Scale Point Cloud

Semantic Segmentation

It propose a perturbed self-distillation (PSD) framework.(可以有效建立标签点和无标签点的拓扑关系)
context-aware module(整合到PSD来改进拓扑结构)
paper4:Sparse-to-dense Feature Matching: Intra and Inter domain Cross-modal Learning in Domain Adaptation for 3D Semantic Segmentation

DsCML(动态稀疏到密集交叉模态学习策略): It enables the sparse point cloud features and dense pixel features can sufficiently interact with each other.(稀疏点云特征和密集像素特征能够充分交互)
CMAL（跨模态对抗学习）: It is mainly utilized to narrow the domain gap by reducing the distribution difference between source and target domain.(利用对抗学习同时拉近模态间数据和域间数据的距离)

笔记：半监督的3D语义分割相关推荐

标注成本降低5倍！LaserMix：通用半监督LiDAR点云分割框架(新加坡南洋理工大学)...
点击下方卡片,关注"自动驾驶之心"公众号 ADAS巨卷干货,即可获取后台回复[LMix]获取论文! 后台回复[ECCV2022]获取ECCV2022所有自动驾驶方向论文! 后台回 ...
凸面镜反射场景无监督域适应语义分割的一些问题
凸面镜反射场景无监督域适应语义分割的一些问题大家好,我是来自北京大学的石永杰同学,最近我们组的工作<Unsupervised Domain Adaptation for Semantic Se ...
基于RGB和LiDAR融合的自动驾驶3D语义分割
基于RGB和LiDAR融合的自动驾驶3D语义分割论文 RGB and LiDAR fusion based 3D Semantic Segmentationfor Autonomous Drivin ...
论文笔记（FCN网络，语义分割）：Fully Convolutional Networks for Semantic Segmentation
FCN论文笔记:Fully Convolutional Networks for Semantic Segmentation 语义分割模型结构时序: FCN SegNet Dilated Convol ...
【NLP】博士笔记 | 深入理解深度学习语义分割
点击上方"小白学视觉",选择加"星标"或"置顶" 重磅干货,第一时间送达本文转自|机器学习初学者引言:最近自动驾驶项目需要学习一些语义分 ...
笔记 | 深入理解深度学习语义分割
点击上方"小白学视觉",选择加"星标"或"置顶" 重磅干货,第一时间送达本文转自:计算机视觉联盟本文内容概述王博Kings最近的语义分割 ...
博士笔记 | 深入理解深度学习语义分割
点击上方"小白学视觉",选择加"星标"或"置顶" 重磅干货,第一时间送达本文转自|机器学习初学者本文内容概述王博Kings最近的语义分割学 ...
3D 语义分割——2DPASS
3D 语义分割——Cylinder3D

笔记：半监督的3D语义分割

笔记：半监督的3D语义分割

paper1:Guided Point Contrastive Learning for Semi-supervised Point Cloud Semantic Segmentation

paper2:SSPC-Net: Semi-supervised Semantic 3D Point Cloud Segmentation Network

paper3:Perturbed Self-Distillation: Weakly Supervised Large-Scale Point Cloud

paper4:Sparse-to-dense Feature Matching: Intra and Inter domain Cross-modal Learning in Domain Adaptation for 3D Semantic Segmentation

笔记：半监督的3D语义分割相关推荐

最新文章

热门文章