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 | panoptic 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 https://arxiv.org/abs/2011.11675 |
| 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 | All | Things | Stuff |
|---|---|---|---|
| PQ | 68.4776 | 61.8574 | 73.2923 |
| SQ | 83.9452 | 81.7263 | 85.559 |
| RQ | 80.8933 | 75.585 | 84.7539 |
Class results
| Class | PQ | SQ | RQ |
|---|---|---|---|
| road | 98.6698 | 98.7675 | 99.9011 |
| sidewalk | 80.7878 | 86.5672 | 93.3238 |
| building | 90.6426 | 92.1585 | 98.3552 |
| wall | 46.876 | 79.7945 | 58.7459 |
| fence | 53.687 | 78.5958 | 68.3077 |
| pole | 70.6017 | 74.9011 | 94.2598 |
| traffic light | 59.989 | 80.4086 | 74.6053 |
| traffic sign | 74.6193 | 83.9233 | 88.9136 |
| vegetation | 91.8501 | 92.576 | 99.2158 |
| terrain | 47.6403 | 79.66 | 59.8046 |
| sky | 90.8516 | 93.7968 | 96.86 |
| person | 60.611 | 78.1914 | 77.5161 |
| rider | 57.4188 | 75.6693 | 75.8812 |
| car | 72.6004 | 85.3896 | 85.0226 |
| truck | 61.7383 | 88.8509 | 69.4853 |
| bus | 72.1235 | 88.9986 | 81.039 |
| train | 62.1548 | 85.3312 | 72.8395 |
| motorcycle | 56.5269 | 77.4033 | 73.029 |
| bicycle | 51.6853 | 73.976 | 69.8676 |