# Point2Mask: Point-supervised Panoptic Segmentation via Optimal Transport Source: [Point2Mask: Point-supervised Panoptic Segmentation via Optimal Transport]() Collection index: [llms.txt]() Data updated: 2025-10-26T01:35:15.802Z Authors: Wentong Li, Yuqian Yuan, Song Wang, Jianke Zhu, Jianshu Li, Jian Liu, Lei Zhang Published: 2023-08-03T14:11:56.000Z ## Abstract 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. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Oriented Object Detection on DIOR v1.0 (test)](): Oriented Object Detection; DIOR v1.0 (test); AP50: 13.77. - [Oriented Object Detection on DIOR-R (test)](): Oriented Object Detection; DIOR-R (test); mAP50: 13.77. - [Oriented Object Detection on DOTA v1.0 (test)](): Oriented Object Detection; DOTA v1.0 (test); SV: 15.1. - [Oriented Object Detection on HRSC 2016 (test)](): Oriented Object Detection; HRSC 2016 (test); mAP: not recorded. ## Original sources and implementation [Original paper]() [PDF]()