Semantic Segmentation On Skyscapes Dense 1
Metrics
Mean IoU
Results
Performance results of various models on this benchmark
Model Name | Mean IoU | Paper Title | Repository |
|---|---|---|---|
| DenseASPP (ResNet-101) | 24.73 | DenseASPP for Semantic Segmentation in Street Scenes | |
| DeepLabv3+ | 38.20 | Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation | |
| U-Net | 14.15 | U-Net: Convolutional Networks for Biomedical Image Segmentation | |
| BiSeNet (ResNet-50) | 30.82 | BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation | |
| SegNet | 23.14 | SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation | |
| FCN8s (ResNet-50) | 33.06 | Fully Convolutional Networks for Semantic Segmentation | |
| SkyScapesNet-Dense | 40.13 | SkyScapes Fine-Grained Semantic Understanding of Aerial Scenes | - |
0 of 7 row(s) selected.