Combinatorics

Physics

Panopticon

Pattern recognition (psychology)

Mathematics

Pipeline (software)

Kernel (algebra)

Politics

Epistemology

Philosophy

Workflow

Political science

Artificial intelligence

Power (physics)

Set (abstract data type)

Programming language

Code (set theory)

Font

Computer science

Simple (philosophy)

Quantum mechanics

Generator (circuit theory)

Object (grammar)

Database

Segmentation

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 prosperties 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 https://github.com/Jia-Research-Lab/PanopticFCN. <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</sup>

Fully Convolutional Networks for Panoptic Segmentation