论文标题
明确监督的全景分段
Pointly-Supervised Panoptic Segmentation
论文作者
论文摘要
在本文中，我们提出了一种新的方法，用于应用点级注释来进行弱监督的全景分段。点级标签不是由完全有监督的方法使用的密集像素级标签，而是为每个目标提供一个点作为监督，从而大大减轻了注释负担。我们通过同时从点级标签生成全景伪面罩并向它们学习，从而在端到端框架中提出了问题。为了应对核心挑战，即庞景伪面具的生成，我们提出了一种原则性的方法来解析像素，通过最大程度地降低像素到点的遍历成本，这些成本是模拟语义相似性，低级纹理提示和高级歧管知识以区分泛型目标。我们对Pascal VOC和MS可可数据集进行了实验，以证明该方法的有效性，并在弱监督的综合分割问题中显示出最先进的性能。代码可在https://github.com/bravegroup/psps.git上找到。
In this paper, we propose a new approach to applying point-level annotations for weakly-supervised panoptic segmentation. Instead of the dense pixel-level labels used by fully supervised methods, point-level labels only provide a single point for each target as supervision, significantly reducing the annotation burden. We formulate the problem in an end-to-end framework by simultaneously generating panoptic pseudo-masks from point-level labels and learning from them. To tackle the core challenge, i.e., panoptic pseudo-mask generation, we propose a principled approach to parsing pixels by minimizing pixel-to-point traversing costs, which model semantic similarity, low-level texture cues, and high-level manifold knowledge to discriminate panoptic targets. We conduct experiments on the Pascal VOC and the MS COCO datasets to demonstrate the approach's effectiveness and show state-of-the-art performance in the weakly-supervised panoptic segmentation problem. Codes are available at https://github.com/BraveGroup/PSPS.git.
