# Single Network Panoptic Segmentation for Street Scene Understanding

## TL;DR

This paper introduces a single neural network that performs joint semantic and instance segmentation for street scenes, achieving high accuracy and faster prediction times by combining tasks in one pass.

## Contribution

The novel approach integrates semantic and instance segmentation into one network, reducing computation and sharing information to improve performance on street scene datasets.

## Key findings

- Achieves 23.9 PQ on Mapillary Vistas validation
- Achieves 45.9 PQ on Cityscapes validation
- Reduces prediction time by a factor of 2

## Abstract

In this work, we propose a single deep neural network for panoptic segmentation, for which the goal is to provide each individual pixel of an input image with a class label, as in semantic segmentation, as well as a unique identifier for specific objects in an image, following instance segmentation. Our network makes joint semantic and instance segmentation predictions and combines these to form an output in the panoptic format. This has two main benefits: firstly, the entire panoptic prediction is made in one pass, reducing the required computation time and resources; secondly, by learning the tasks jointly, information is shared between the two tasks, thereby improving performance. Our network is evaluated on two street scene datasets: Cityscapes and Mapillary Vistas. By leveraging information exchange and improving the merging heuristics, we increase the performance of the single network, and achieve a score of 23.9 on the Panoptic Quality (PQ) metric on Mapillary Vistas validation, with an input resolution of 640 x 900 pixels. On Cityscapes validation, our method achieves a PQ score of 45.9 with an input resolution of 512 x 1024 pixels. Moreover, our method decreases the prediction time by a factor of 2 with respect to separate networks.