Panoptic-DeepLab: A Simple, Strong, and Fast Baseline for Bottom-Up Panoptic Segmentation

TL;DR

Panoptic-DeepLab is a new bottom-up panoptic segmentation system that achieves state-of-the-art results with fast inference, combining semantic and instance segmentation in a simple, unified framework.

Contribution

This work introduces Panoptic-DeepLab, a novel bottom-up approach that outperforms existing methods in accuracy and speed, establishing a new strong baseline for panoptic segmentation.

Findings

Achieves 84.2% mIoU on Cityscapes test set

Attains 39.0% AP and 65.5% PQ on Cityscapes

Runs nearly in real-time at 15.8 fps with MobileNetV3

Abstract

In this work, we introduce Panoptic-DeepLab, a simple, strong, and fast system for panoptic segmentation, aiming to establish a solid baseline for bottom-up methods that can achieve comparable performance of two-stage methods while yielding fast inference speed. In particular, Panoptic-DeepLab adopts the dual-ASPP and dual-decoder structures specific to semantic, and instance segmentation, respectively. The semantic segmentation branch is the same as the typical design of any semantic segmentation model (e.g., DeepLab), while the instance segmentation branch is class-agnostic, involving a simple instance center regression. As a result, our single Panoptic-DeepLab simultaneously ranks first at all three Cityscapes benchmarks, setting the new state-of-art of 84.2% mIoU, 39.0% AP, and 65.5% PQ on test set. Additionally, equipped with MobileNetV3, Panoptic-DeepLab runs nearly in real-time with a single 1025x2049 image (15.8 frames per second), while achieving a competitive performance on Cityscapes (54.1 PQ% on test set). On Mapillary Vistas test set, our ensemble of six models attains 42.7% PQ, outperforming the challenge winner in 2018 by a healthy margin of 1.5%. Finally, our Panoptic-DeepLab also performs on par with several top-down approaches on the challenging COCO dataset. For the first time, we demonstrate a bottom-up approach could deliver state-of-the-art results on panoptic segmentation.