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

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.

PDF Abstract CVPR 2020 PDF CVPR 2020 Abstract

Results from the Paper


Ranked #6 on Panoptic Segmentation on Cityscapes test (using extra training data)

     Get a GitHub badge
Task Dataset Model Metric Name Metric Value Global Rank Uses Extra
Training Data
Result Benchmark
Semantic Segmentation Cityscapes test Panoptic-DeepLab Mean IoU (class) 84.2% # 11
Panoptic Segmentation Cityscapes test Panoptic-Deeplab PQ 65.5 # 6
Panoptic Segmentation Cityscapes val Panoptic-DeepLab (X71) PQ 64.1 # 17
mIoU 81.5 # 16
AP 38.5 # 18
Semantic Segmentation Cityscapes val Panoptic-DeepLab mIoU 81.5% # 38
Panoptic Segmentation COCO test-dev Panoptic-DeepLab (Xception-71) PQ 41.4 # 31
PQst 35.9 # 22
PQth 45.1 # 31
Panoptic Segmentation Mapillary val Panoptic-DeepLab (X71) PQ 40.5 # 8

Methods