Method Details

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


Method overview

name Panoptic-DeepLab w/ SWideRNet [Mapillary Vistas]
challenge instance-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.
publication Scaling Wide Residual Networks for Panoptic Segmentation
Liang-Chieh Chen, Huiyu Wang, Siyuan Qiao
project page / code
used Cityscapes data fine annotations
used external data ImageNet, Mapillary Vistas Research Edition
runtime n/a
subsampling no
submission date November, 2020
previous submissions


Average results

Metric Value
AP 42.1965
AP50% 67.4783
AP100m 57.761
AP50m 59.6182


Class results

Class AP AP50% AP100m AP50m
person 37.6868 69.8007 56.6193 56.7915
rider 34.5858 69.0087 49.9406 50.3866
car 58.1962 82.7709 77.9262 80.2629
truck 45.0575 56.9791 59.9592 63.3339
bus 54.762 68.9538 76.0943 83.7102
train 47.2136 69.0065 59.0393 58.7595
motorcycle 34.0216 65.1602 43.809 45.1061
bicycle 26.0487 58.1469 38.7 38.5947



Download results as .csv file

Benchmark page