Method Details
Details for method 'DeepLabv3'
Method overview
name | DeepLabv3 |
challenge | pixel-level semantic labeling |
details | In this work, we revisit atrous convolution, a powerful tool to explicitly adjust filter’s field-of-view as well as control the resolution of feature responses computed by Deep Convolutional Neural Networks, in the application of semantic image segmentation. To handle the problem of segmenting objects at multiple scales, we employ a module, called Atrous Spatial Pyrmid Pooling (ASPP), which adopts atrous convolution in parallel to capture multi-scale context with multiple atrous rates. Furthermore, we propose to augment ASPP module with image-level features encoding global context and further boost performance. Results obtained with a single model (no ensemble), trained with fine + coarse annotations. More details will be shown in the updated arXiv report. |
publication | Rethinking Atrous Convolution for Semantic Image Segmentation Liang-Chieh Chen, George Papandreou, Florian Schroff, Hartwig Adam arXiv preprint https://arxiv.org/abs/1706.05587 |
project page / code | |
used Cityscapes data | fine annotations, coarse annotations |
used external data | ImageNet |
runtime | n/a |
subsampling | no |
submission date | September, 2017 |
previous submissions |
Average results
Metric | Value |
---|---|
IoU Classes | 81.3379 |
iIoU Classes | 62.0511 |
IoU Categories | 91.6313 |
iIoU Categories | 81.69 |
Class results
Class | IoU | iIoU |
---|---|---|
road | 98.5931 | - |
sidewalk | 86.1916 | - |
building | 93.5295 | - |
wall | 55.1757 | - |
fence | 63.2389 | - |
pole | 70.0424 | - |
traffic light | 77.0897 | - |
traffic sign | 81.3333 | - |
vegetation | 93.7959 | - |
terrain | 72.3212 | - |
sky | 95.8643 | - |
person | 87.6126 | 72.8883 |
rider | 73.3587 | 53.8575 |
car | 96.3178 | 91.2151 |
truck | 75.0866 | 45.9517 |
bus | 90.3914 | 57.8137 |
train | 85.0893 | 55.9257 |
motorcycle | 72.0899 | 52.8869 |
bicycle | 78.2985 | 65.8698 |
Category results
Category | IoU | iIoU |
---|---|---|
flat | 98.7186 | - |
nature | 93.4534 | - |
object | 75.9651 | - |
sky | 95.8643 | - |
construction | 93.8672 | - |
human | 87.8607 | 73.9794 |
vehicle | 95.6898 | 89.4007 |