Method Details

Details for method 'Panoptic-DeepLab w/ SWideRNet [Mapillary Vistas + Pseudo-labels]'


Method overview

name Panoptic-DeepLab w/ SWideRNet [Mapillary Vistas + Pseudo-labels]
challenge pixel-level semantic labeling
details We revisit the architecture design of Wide Residual Networks. We design a baseline model by incorporating the simple and effective Squeeze-and-Excitation and Switchable Atrous Convolution to the Wide-ResNets. Its network capacity is further scaled up or down by adjusting the width (i.e., channel size) and depth (i.e., number of layers), resulting in a family of SWideRNets (short for Scaling Wide Residual Networks). We demonstrate that such a simple scaling scheme, coupled with grid search, identifies several SWideRNets that significantly advance state-of-the-art performance on panoptic segmentation datasets in both the fast model regime and strong model regime. Following Naive-Student, this model is additionally trained with pseudo-labels generated from Cityscapes Video and train-extra set (i.e., the coarse annotations are not used, but the images are).
publication Scaling Wide Residual Networks for Panoptic Segmentation
Liang-Chieh Chen, Huiyu Wang, Siyuan Qiao
project page / code
used Cityscapes data fine annotations, video
used external data ImageNet, Mapillary Vistas Research Edition. Cityscapes train-extra set (coarse labels are not used but only images).
runtime n/a
subsampling no
submission date January, 2021
previous submissions


Average results

Metric Value
IoU Classes 85.0904
iIoU Classes 71.1787
IoU Categories 93.0174
iIoU Categories 85.1102


Class results

Class IoU iIoU
road 98.8531 -
sidewalk 88.4417 -
building 94.6922 -
wall 68.2337 -
fence 68.6387 -
pole 76.0368 -
traffic light 81.2932 -
traffic sign 84.7314 -
vegetation 94.3966 -
terrain 74.106 -
sky 96.2176 -
person 89.725 79.3652
rider 79.7598 64.3385
car 96.7983 91.2996
truck 82.0896 60.0102
bus 94.1648 73.19
train 92.1153 68.1642
motorcycle 77.1805 64.5811
bicycle 79.2427 68.4808


Category results

Category IoU iIoU
flat 98.8265 -
nature 94.1095 -
object 80.8785 -
sky 96.2176 -
construction 94.9439 -
human 89.755 80.1211
vehicle 96.3908 90.0992



Download results as .csv file

Benchmark page