Weakly-supervised image segmentation has recently attracted increasing research attentions, aiming to avoid the expensive pixel-wise labeling. In this paper, we present an effective method, namely Point2Mask, to achieve high-quality panoptic prediction using only a single random point annotation per target for training. Specifically, we formulate the panoptic pseudo-mask generation as an Optimal Transport (OT) problem, where each ground-truth (gt) point label and pixel sample are defined as the label supplier and consumer, respectively. The transportation cost is calculated by the introduced task-oriented maps, which focus on the category-wise and instance-wise differences among the various thing and stuff targets. Furthermore, a centroid-based scheme is proposed to set the accurate unit number for each gt point supplier. Hence, the pseudo-mask generation is converted into finding the optimal transport plan at a globally minimal transportation cost, which can be solved via the Sinkhorn-Knopp Iteration. Experimental results on Pascal VOC and COCO demonstrate the promising performance of our proposed Point2Mask approach to point-supervised panoptic segmentation. Source code is available at: https://github.com/LiWentomng/Point2Mask.

翻译：弱监督图像分割近年来受到越来越多的研究关注，旨在避免昂贵的像素级标注。本文提出一种有效方法——Point2Mask，仅需为每个目标提供单个随机点标注进行训练，即可实现高质量的全景预测。具体而言，我们将全景伪掩码生成定义为最优传输问题，其中每个标注点标签和像素样本分别被定义为标签供应商和消费者。传输成本通过引入的任务导向图计算，该图聚焦于不同物体和内容目标在类别间和实例间的差异。此外，提出一种基于质心的方案来为每个标注点供应商设定精确的单位数量。因此，伪掩码生成被转化为在全局最小传输成本下寻找最优传输计划，可通过Sinkhorn-Knopp迭代求解。在Pascal VOC和COCO上的实验结果表明，我们提出的Point2Mask方法在点监督全景分割中具有令人期待的性能。源代码见：https://github.com/LiWentomng/Point2Mask。