Zilong Huang, Xinggang Wang, Yunchao Wei, Lichao Huang, Humphrey Shi, Wenyu Liu, Thomas S. Huang. "CCNet: Criss-cross attention for semantic segmentation." Proceedings of the IEEE/CVF International Conference on Computer Vision. 2019.
| Model | Backbone | Resolution | Training Iters | mIoU | mIoU (flip) | mIoU (ms+flip) | Links |
|---|---|---|---|---|---|---|---|
| CCNet | ResNet101_OS8 | 769x769 | 60000 | 80.95% | 81.23% | 81.32% | model|log|vdl |