Method Details
Details for method 'ESPNetv2'
Method overview
| name | ESPNetv2 |
| challenge | pixel-level semantic labeling |
| details | We introduce a light-weight, power efficient, and general purpose convolutional neural network, ESPNetv2, for modeling visual and sequential data. Our network uses group point-wise and depth-wise dilated separable convolutions to learn representations from a large effective receptive field with fewer FLOPs and parameters. The performance of our network is evaluated on three different tasks: (1) object classification, (2) semantic segmentation, and (3) language modeling. Experiments on these tasks, including image classification on the ImageNet and language modeling on the PenTree bank dataset, demonstrate the superior performance of our method over the state-of-the-art methods. Our network has better generalization properties than ShuffleNetv2 when tested on the MSCOCO multi-object classification task and the Cityscapes urban scene semantic segmentation task. Our experiments show that ESPNetv2 is much more power efficient than existing state-of-the-art efficient methods including ShuffleNets and MobileNets. Our code is open-source and available at https://github.com/sacmehta/ESPNetv2 |
| publication | ESPNetv2: A Light-weight, Power Efficient, and General Purpose Convolutional Neural Network Sachin Mehta, Mohammad Rastegari, Linda Shapiro, and Hannaneh Hajishirzi CVPR 2019 https://arxiv.org/abs/1811.11431 |
| project page / code | https://github.com/sacmehta/ESPNetv2 |
| used Cityscapes data | fine annotations |
| used external data | ImageNet |
| runtime | n/a |
| subsampling | 2 |
| submission date | March, 2019 |
| previous submissions | 1, 2 |
Average results
| Metric | Value |
|---|---|
| IoU Classes | 66.1564 |
| iIoU Classes | 36.0315 |
| IoU Categories | 84.3478 |
| iIoU Categories | 66.3271 |
Class results
| Class | IoU | iIoU |
|---|---|---|
| road | 97.2993 | - |
| sidewalk | 78.5928 | - |
| building | 88.7831 | - |
| wall | 43.5251 | - |
| fence | 42.086 | - |
| pole | 49.3236 | - |
| traffic light | 52.5581 | - |
| traffic sign | 60.0014 | - |
| vegetation | 90.5263 | - |
| terrain | 66.8086 | - |
| sky | 93.3358 | - |
| person | 72.9348 | 50.5031 |
| rider | 53.1468 | 23.5182 |
| car | 91.7846 | 83.3899 |
| truck | 52.9504 | 19.3246 |
| bus | 65.9212 | 31.4983 |
| train | 53.2478 | 22.5001 |
| motorcycle | 44.2348 | 19.2151 |
| bicycle | 59.9118 | 38.3026 |
Category results
| Category | IoU | iIoU |
|---|---|---|
| flat | 97.8758 | - |
| nature | 90.1245 | - |
| object | 56.2099 | - |
| sky | 93.3358 | - |
| construction | 88.8955 | - |
| human | 73.2771 | 51.4141 |
| vehicle | 90.7159 | 81.2402 |