Semantic segmentation of point cloud usually relies on dense annotation that is exhausting and costly, so it attracts wide attention to investigate solutions for the weakly supervised scheme with only sparse points annotated. Existing works start from the given labels and propagate them to highly-related but unlabeled points, with the guidance of data, e.g. intra-point relation. However, it suffers from (i) the inefficient exploitation of data information, and (ii) the strong reliance on labels thus is easily suppressed when given much fewer annotations. Therefore, we propose a novel framework, PointMatch, that stands on both data and label, by applying consistency regularization to sufficiently probe information from data itself and leveraging weak labels as assistance at the same time. By doing so, meaningful information can be learned from both data and label for better representation learning, which also enables the model more robust to the extent of label sparsity. Simple yet effective, the proposed PointMatch achieves the state-of-the-art performance under various weakly-supervised schemes on both ScanNet-v2 and S3DIS datasets, especially on the settings with extremely sparse labels, e.g. surpassing SQN by 21.2% and 17.2% on the 0.01% and 0.1% setting of ScanNet-v2, respectively.
HisynSeg: Weakly-Supervised Histopathological Image Segmentation via Image-Mixing Synthesis and Consistency Regularization
Tsinghua Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院）；School of Science, Harbin Institute of Technology (Shenzhen)（哈尔滨工业大学（深圳）理学院）；School of Computer Science and Technology, Harbin Institute of Technology (Shenzhen)（哈尔滨工业大学（深圳）计算机科学与技术学院）
Uncertainty-Aware Extreme Point Tracing for Weakly Supervised Ultrasound Image Segmentation
College of Computer Science, Inner Mongolia University（内蒙古大学计算机学院）；Baotou Medical College（包头医学院）；Department of Ultrasound Medicine, The Second Affiliated Hospital of Baotou Medical College（包头医学院第二附属医院超声医学科）
Self-supervised Image-specific Prototype Exploration for Weakly Supervised Semantic Segmentation
Sun Yat-Sen University（中山大学）；Guangdong Province Key Laboratory of Information Security Technology（广东省信息安全技术重点实验室）；Key Laboratory of Machine Intelligence and Advanced Computing, Ministry of Education（教育部机器智能与先进计算重点实验室）
Weakly Supervised Segmentation Framework for Thyroid Nodule Based on High-confidence Labels and High-rationality Losses
Faculty of Robot Science and Engineering, Northeastern University（机器人科学与工程学院，东北大学）；Harbin Institute of Technology（哈尔滨工业大学）；Department of Ultrasound, Shengjing Hospital of China Medical University（中国医科大学附属盛京医院超声科）
MambaEviScrib: Mamba and Evidence-Guided Consistency Enhance CNN Robustness for Scribble-Based Weakly Supervised Ultrasound Image Segmentation
School of Communication and Information Engineering, Shanghai University（上海大学通信与信息工程学院）；The SMART (Smart Medicine and AI-based Radiology Technology) Lab, Shanghai Institute for Advanced Communication and Data Science, Shanghai University（上海大学先进通信与数据科学研究院智能医学与AI放射技术实验室）；School of Health Science and Engineering, University of Shanghai for Science and Technology（上海科技大学健康科学与工程学院）；Department of Pediatric Cardiology, Shanghai Children's Medical Center, Shanghai Jiao Tong University School of Medicine（上海交通大学医学院儿童心脏科部）；School of Medical Instruments, Shanghai University of Medicine and Health Sciences（医学仪器学院，上海医学院与健康科学大学）
Weakly-supervised 3D Human Pose Estimation with Cross-view U-shaped Graph Convolutional Network
Peking University Shenzhen Graduate School（北京大学深圳研究生院）；National University of Defense Technology（国防科技大学）
虽然单目三维人体姿态估计方法已经取得了显著的进展，但由于固有的深度模糊性，它远未得到解决。相反，利用多视图信息是实现绝对3D人体姿态估计的实用方法。在本文中，我们提出了一个简单而有效的管道弱监督交叉视图三维人体姿态估计。通过仅使用两个相机视图，我们的方法可以以弱监督的方式实现最先进的性能，不需要3D地面实况，而只需要2D注释。具体来说，我们的方法包括两个步骤：三角剖分和细化。首先，给定可以通过任何经典的2D检测方法获得的2D关键点，跨两个视图执行三角测量以将2D关键点提升到粗略的3D姿态。然后，一种新的交叉视图U形图卷积网络（CV-UGCN），它可以探索的空间配置和交叉视图的相关性，被设计用于细化粗略的3D姿态。特别是，细化的进展是通过弱监督学习，其中几何和结构感知的一致性检查进行。我们在标准基准数据集Human3.6M上评估了我们的方法。基准数据集上的平均每关节位置误差为27.4 mm，显著优于现有的最先进方法（27.4 mm vs 30.2 mm）。
PatchMVSNet: Patch-wise Unsupervised Multi-View Stereo for Weakly-Textured Surface Reconstruction
Wuhan University（武汉大学）
基于学习的多视图立体视觉（MVS）在流行的数据集上获得了良好的重建效果。然而，监督学习方法需要用于训练的基础事实，这是难以收集的，特别是对于大规模数据集。虽然目前已经提出了无监督学习方法并取得了令人满意的结果，但这些方法仍然无法在具有挑战性的场景中重建完整的结果，例如弱纹理表面，因为这些方法主要依赖于受到各种光照的像素级光度一致性。为了减少这些具有挑战性的场景中的匹配模糊性，本文提出了鲁棒的损失函数，利用多视图图像下的约束：1）逐块光度一致性损失，这扩大了多视图相似性测量中的特征的感受野，2）鲁棒的两视图几何一致性，这包括最小遮挡的跨视图深度一致性检查。我们的无监督策略可以用任意的深度估计框架来实现，并且可以用任意的大规模MVS数据集来训练。实验结果表明，该方法能有效降低匹配二义性，特别是提高弱纹理重建的完整性。此外，我们的方法在流行的基准测试中达到了最先进方法的性能，如DTU，Tanks and Temples和ETH3D。代码将很快发布。
Weakly Supervised Visible-Infrared Person Re-Identification via Heterogeneous Expert Collaborative Consistency Learning
Faculty of Information Engineering and Automation, Kunming University of Science and Technology（昆明理工大学信息工程与自动化学院）；School of Computer Science and Technology, Harbin Institute of Technology（哈尔滨工业大学计算机科学与技术学院）
Topology-aware Pathological Consistency Matching for Weakly-Paired IHC Virtual Staining
Guangdong Research Center of Polarization Imaging and Measurement Engineering Technology（广东极化成像与测量工程研究中心）；Shenzhen Key Laboratory for Minimal Invasive Medical Technologies（深圳微创医疗技术重点实验室）；Institute of Biopharmaceutical and Health Engineering（生物制药与健康工程研究院）；Tsinghua Shenzhen International Graduate School（清华大学深圳国际 Graduate School）；Tsinghua University（清华大学）
Foreground-Action Consistency Network for Weakly Supervised Temporal Action Localization
Multimedia Laboratory, The Chinese University of Hong Kong（香港中文大学多媒体实验室）；Centre for Perceptual and Interactive Intelligence, Hong Kong（香港感知与交互智能中心）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）
3D Face Modeling via Weakly-supervised Disentanglement Network joint Identity-consistency Prior
School of Computer Science and Engineering, Beihang University（北京航空航天大学计算机科学与工程学院）；Institute of Artificial Intelligence, Beihang University（北京航空航天大学人工智能研究院）；Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）
