Huajun Liu, Fuqiang Liu, Xinyi Fan and Dong Huang. "Polarized Self-Attention: Towards High-quality Pixel-wise Regression." arXiv preprint arXiv:2107.00782v2 (2021).
| Model | Backbone | Resolution | Training Iters | mIoU | mIoU (flip) | mIoU (ms+flip) | Links |
|---|---|---|---|---|---|---|---|
| MscaleOCRNet | HRNet_w48+psa_p | 1024x2048 | 150000 | 84.62% | 84.90% | 84.89% | model|log|vdl |
- This is the MscaleOCRNet that supports Polarized Self-Attention(PSA).
- Since we cannot reproduce the training results from the authors' official repo, we follow the settings in the original paper to train and evaluate our models, and the final accuracy is lower than that reported in the paper.
- We observed a reduced accuracy when applying ms+flip augmentation to MsacleOCRNet during test time. This is probably due to that MscaleOCRNet has built internally multi-scale operations in the network.