Method Details
Details for method 'Segnet basic'
Method overview
| name | Segnet basic |
| challenge | pixel-level semantic labeling |
| details | Trained on a pre-release version of the dataset |
| publication | SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation V. Badrinarayanan, A. Kendall, and R. Cipolla arXiv preprint 2015 http://arxiv.org/pdf/1511.00561v2 |
| project page / code | https://github.com/alexgkendall/caffe-segnet |
| used Cityscapes data | fine annotations |
| used external data | ImageNet |
| runtime | 0.06 s |
| subsampling | 4 |
| submission date | April, 2016 |
| previous submissions |
Average results
| Metric | Value |
|---|---|
| IoU Classes | 56.9587 |
| iIoU Classes | 31.9834 |
| IoU Categories | 79.1333 |
| iIoU Categories | 61.9014 |
Class results
| Class | IoU | iIoU |
|---|---|---|
| road | 96.4035 | - |
| sidewalk | 73.2057 | - |
| building | 83.9933 | - |
| wall | 28.453 | - |
| fence | 29.0315 | - |
| pole | 35.7008 | - |
| traffic light | 39.7643 | - |
| traffic sign | 45.1568 | - |
| vegetation | 87.017 | - |
| terrain | 63.8135 | - |
| sky | 91.7628 | - |
| person | 62.7811 | 44.3207 |
| rider | 42.8068 | 22.739 |
| car | 89.2729 | 78.3561 |
| truck | 38.1286 | 16.1161 |
| bus | 43.1184 | 24.2727 |
| train | 44.1504 | 20.6503 |
| motorcycle | 35.7857 | 15.8372 |
| bicycle | 51.8698 | 33.5749 |
Category results
| Category | IoU | iIoU |
|---|---|---|
| flat | 97.4114 | - |
| nature | 86.6803 | - |
| object | 42.4578 | - |
| sky | 91.7628 | - |
| construction | 83.7608 | - |
| human | 64.6647 | 46.9724 |
| vehicle | 87.1951 | 76.8303 |