Method Details

Details for method 'Panoptic-DeepLab [Mapillary Vistas]'


Method overview

name Panoptic-DeepLab [Mapillary Vistas]
challenge instance-level semantic labeling
details Our proposed bottom-up Panoptic-DeepLab is conceptually simple yet delivers state-of-the-art results. The Panoptic-DeepLab adopts dual-ASPP and dual-decoder modules, specific to semantic segmentation and instance segmentation respectively. The semantic segmentation prediction follows the typical design of any semantic segmentation model (e.g., DeepLab), while the instance segmentation prediction involves a simple instance center regression, where the model learns to predict instance centers as well as the offset from each pixel to its corresponding center.
publication Panoptic-DeepLab
Bowen Cheng, Maxwell D. Collins, Yukun Zhu, Ting Liu, Thomas S. Huang, Hartwig Adam, Liang-Chieh Chen
project page / code
used Cityscapes data fine annotations
used external data ImageNet, Mapillary Vistas Research Edition.
runtime n/a
subsampling no
submission date September, 2019
previous submissions


Average results

Metric Value
AP 38.1753
AP50% 62.9296
AP100m 54.3259
AP50m 56.5383


Class results

Class AP AP50% AP100m AP50m
person 34.1594 64.1538 54.039 54.1891
rider 29.2743 62.6921 44.4755 45.1253
car 53.8333 76.8706 76.0892 78.7526
truck 41.0271 51.8601 56.8202 61.4602
bus 50.7589 66.4101 72.7875 81.4518
train 42.5273 65.3359 53.7295 54.0681
motorcycle 30.5365 60.6508 40.8325 41.4108
bicycle 23.2852 55.4632 35.8336 35.8483



Download results as .csv file

Benchmark page