Method Details


Details for method 'AdapNet++'

 

Method overview

name AdapNet++
challenge pixel-level semantic labeling
details In this work, we propose the AdapNet++ architecture for semantic segmentation that aims to achieve the right trade-off between performance and computational complexity of the model. AdapNet++ incorporates a new encoder with multiscale residual units and an efficient atrous spatial pyramid pooling (eASPP) module that has a larger effective receptive field with more than 10x fewer parameters compared to the standard ASPP, complemented with a strong decoder with a multi-resolution supervision scheme that recovers high-resolution details. Comprehensive empirical evaluations on the challenging Cityscapes, Synthia, SUN RGB-D, ScanNet and Freiburg Forest datasets demonstrate that our architecture achieves state-of-the-art performance while simultaneously being efficient in terms of both the number of parameters and inference time. Please refer to https://arxiv.org/abs/1808.03833 for details. A live demo on various datasets can be viewed at http://deepscene.cs.uni-freiburg.de
publication Self-Supervised Model Adaptation for Multimodal Semantic Segmentation
Abhinav Valada, Rohit Mohan, Wolfram Burgard
arXiv
https://arxiv.org/abs/1808.03833
project page / code http://deepscene.cs.uni-freiburg.de
used Cityscapes data fine annotations, coarse annotations
used external data ImageNet
runtime n/a
subsampling no
submission date January, 2019
previous submissions

 

Average results

Metric Value
IoU Classes 81.3415
iIoU Classes 59.5319
IoU Categories 90.9922
iIoU Categories 80.1118

 

Class results

Class IoU iIoU
road 98.5699 -
sidewalk 86.1829 -
building 93.3291 -
wall 57.7995 -
fence 62.0458 -
pole 67.2715 -
traffic light 75.0183 -
traffic sign 79.5701 -
vegetation 93.5718 -
terrain 72.2916 -
sky 95.2716 -
person 86.378 70.309
rider 72.2123 50.0194
car 96.1648 90.3079
truck 81.473 44.578
bus 92.4473 55.1327
train 88.0135 54.3795
motorcycle 71.2278 48.2081
bicycle 76.6494 63.3204

 

Category results

Category IoU iIoU
flat 98.6804 -
nature 93.1996 -
object 73.7185 -
sky 95.2716 -
construction 93.5739 -
human 86.7158 71.5125
vehicle 95.7858 88.7112

 

Links

Download results as .csv file

Benchmark page