点云语义分割通常需要大规模带注释的训练数据，但显然，逐点标记太繁琐而无法准备。虽然最近的一些方法建议用小百分比的点标签来训练3D网络，但我们将这种方法推向了极端，提出了“One Thing One Click”，这意味着注释器只需要为每个对象标记一个点。为了在网络训练中利用这些极其稀疏的标签，我们设计了一种新的自训练方法，在该方法中，我们迭代地进行训练和标签传播，并通过图形传播模块进行促进。此外，我们采用关系网络来生成每个类别的原型，并显式地建模图节点之间的相似性，以生成伪标签来指导迭代训练。在ScanNet-v2和S3 DIS上的实验结果表明，我们的自训练方法，具有极稀疏的注释，优于所有现有的弱监督方法的3D语义分割的大幅度，我们的结果也可以与完全监督的同行。
英文摘要：
Point cloud semantic segmentation often requires largescale annotated training data, but clearly, point-wise labels are too tedious to prepare. While some recent methods propose to train a 3D network with small percentages of point labels, we take the approach to an extreme and propose "One Thing One Click," meaning that the annotator only needs to label one point per object. To leverage these extremely sparse labels in network training, we design a novel self-training approach, in which we iteratively conduct the training and label propagation, facilitated by a graph propagation module. Also, we adopt a relation network to generate per-category prototype and explicitly model the similarity among graph nodes to generate pseudo labels to guide the iterative training. Experimental results on both ScanNet-v2 and S3DIS show that our self-training approach, with extremely-sparse annotations, outperforms all existing weakly supervised methods for 3D semantic segmentation by a large margin, and our results are also comparable to those of the fully supervised counterparts.
Seminar Learning for Click-Level Weakly Supervised Semantic Segmentation
Southern University of Science and Technology（南方科技大学）；University of Amsterdam（阿姆斯特丹大学）；Xiamen University（厦门大学）；Inception Institute of Artificial Intelligence（起源人工智能研究院）
WeClick: Weakly-Supervised Video Semantic Segmentation with Click Annotations
Tsinghua Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院）；Peng Cheng Laboratory（鹏城实验室）；Southern University of Science and Technology（南方科技大学）；Shenzhen Rejoice Sport Tech. Co., LTD（深圳悦动体育科技有限公司）
One Class One Click: Quasi Scene-level Weakly Supervised Point Cloud Semantic Segmentation with Active Learning
The Hong Kong Polytechnic University（香港理工大学）；The Hong Kong Polytechnic University Shenzhen Research Institute（香港理工大学深圳研究院）；Otto Poon Charitable Foundation Smart Cities Research Institute, The Hong Kong Polytechnic University（香港理工大学潘乐陶慈善基金会智慧城市研究院）
Weakly Supervised 3D Object Detection from Lidar Point Cloud
School of Computer Science, Beijing Institute of Technology（北京理工大学计算机学院）；ETH Zurich（苏黎世联邦理工学院）；Inception Institute of Artificial Intelligence（起源人工智能研究院）
Just a Hint: Point-Supervised Camouflaged Object Detection
Unmanned System Research Institute, Northwestern Polytechnical University（西北工业大学无人系统研究院）；National Key Laboratory of Unmanned Aerial Vehicle Technology（无人机技术国家重点实验室）
Rethinking the Encoding and Annotating of 3D Bounding Box: Corner-Aware 3D Object Detection from Point Clouds
School of Computer Science, Beijing Institute of Technology（计算机科学学院，北京理工大学）；Computer Science Program, Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division, Center of Excellence for Smart Health, and Center of Excellence for Generative AI, King Abdullah University of Science and Technology (KAUST)（计算机科学项目，计算机、电气和数学科学与工程（CEMSE）部门，智能健康卓越中心，生成人工智能卓越中心，国王阿卜杜勒·阿齐兹大学科学与技术（KAUST））；State Key Laboratory of Internet of Things for Smart City, Department of Computer and Information Science, University of Macau（智慧城市物联网国家重点实验室，澳门大学计算机与信息科学系）；Guangdong Provincial Key Laboratory of Machine Perception and Intelligent Computing, Shenzhen MSU-BIT University（广东省机器感知与智能计算重点实验室，深圳MSU-BIT大学）；Beijing Key Laboratory of Intelligent Information Technology, School of Computer Science, Beijing Institute of Technology（北京智能信息技术重点实验室，计算机科学学院，北京理工大学）
DExTeR: Weakly Semi-Supervised Object Detection with Class and Instance Experts for Medical Imaging
University of Strasbourg, CNRS, INSERM, ICube, UMR7357, France（斯特拉斯堡大学、法国国家科学研究中心、法国国家医学研究院、ICube、UMR7357、法国）；University Hospital of Strasbourg, France（斯特拉斯堡大学医院、法国）
