In this paper, we present a conceptually simple, strong, and efficient
framework for panoptic segmentation, called Panoptic FCN. Our approach aims to
represent and predict foreground things and background stuff in a unified fully
convolutional pipeline. In particular, Panoptic FCN encodes each object
instance or stuff category into a specific kernel weight with the proposed
kernel generator and produces the prediction by convolving the high-resolution
feature directly. With this approach, instance-aware and semantically
consistent properties for things and stuff can be respectively satisfied in a
simple generate-kernel-then-segment workflow. Without extra boxes for
localization or instance separation, the proposed approach outperforms previous
box-based and -free models with high efficiency on COCO, Cityscapes, and
Mapillary Vistas datasets with single scale input. Our code is made publicly
available at this https URL

本文介绍了一种名为 Panoptic FCN 的概念简单、强大、高效的全景分割框架，该方法旨在以统一的卷积管道中表示和预测前景物体和背景杂物。通过提出的内核生成器，Panoptic FCN 将每个对象实例或杂物类别编码为特定的内核权重，并通过将高分辨率特征直接卷积来生成预测。通过这种方法，实例感知和语义一致的特性可以分别在一个简单的生成内核，然后进行分割的工作流中得以满足。在 COCO、Cityscapes 和 Mapillary Vistas 数据集上，不需要额外的定位框或实例分离，所提议的方法在单尺度输入上具有比以前的基于框和无框模型更高的效率。