# Fast Panoptic Segmentation Network

Source: [Fast Panoptic Segmentation Network](<https://www.sota2.com/research/paper/68fa667f1e209131cea10a51>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T21:51:21.649Z

Authors: Daan de Geus, Panagiotis Meletis, Gijs Dubbelman

Published: 2019-10-09T10:41:28.000Z

## Abstract

In this work, we present an end-to-end network for fast panoptic segmentation. This network, called Fast Panoptic Segmentation Network (FPSNet), does not require computationally costly instance mask predictions or merging heuristics. This is achieved by casting the panoptic task into a custom dense pixel-wise classification task, which assigns a class label or an instance id to each pixel. We evaluate FPSNet on the Cityscapes and Pascal VOC datasets, and find that FPSNet is faster than existing panoptic segmentation methods, while achieving better or similar panoptic segmentation performance. On the Cityscapes validation set, we achieve a Panoptic Quality score of 55.1%, at prediction times of 114 milliseconds for images with a resolution of 1024x2048 pixels. For lower resolutions of the Cityscapes dataset and for the Pascal VOC dataset, FPSNet runs at 22 and 35 frames per second, respectively.

## 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.

- [Panoptic Segmentation on Cityscapes (val)](<https://www.sota2.com/research/sota/panoptic-segmentation-on-cityscapes-val.md>): Panoptic Segmentation; Cityscapes (val); PQ: 55.1.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1910.03892>)

[PDF](<https://arxiv.org/pdf/1910.03892.pdf>)
