Chen, Liang-Chieh, George Papandreou, Florian Schroff, and Hartwig Adam. "Rethinking Atrous Convolution for Semantic Image Segmentation." arXiv preprint arXiv:1706.05587 (2017).
Model | Backbone | Resolution | Training Iters | mIoU | mIoU (multi-scale) | Links |
---|---|---|---|---|---|---|
DeepLabV3 | ResNet50_OS8 | 1024x512 | 160000 | 79.60% | - | model | log | vdl |
DeepLabV3 | ResNet101_OS8 | 1024x512 | 160000 | 80.05% | - | model | log | vdl |