适配方法

UPerNet

介绍

UPerNet适用于SwinTransformer、CNN等具有多层结构的骨干网络，基于特征金字塔网络(FPN)和金字塔池化(PPM)实现，将骨干网络得到的不同尺寸特征图进行融合从而提升模型性能。

论文引用

@inproceedings{xiao2018unified,
  title={Unified perceptual parsing for scene understanding},
  author={Xiao, Tete and Liu, Yingcheng and Zhou, Bolei and Jiang, Yuning and Sun, Jian},
  booktitle={European Conference on Computer Vision},
  pages={418--434},
  year={2018}
}

SETR

介绍

SETR是适用于ViT的方法，采用渐进式上采样，交替卷积和上采样将骨干网络的特征图恢复至原图大小进行预测，从而减少噪声预测。

论文引用

@inproceedings{zheng2021rethinking,
  title={Rethinking semantic segmentation from a sequence-to-sequence perspective with transformers},
  author={Zheng, Sixiao and Lu, Jiachen and Zhao, Hengshuang and Zhu, Xiatian and Luo, Zekun and Wang, Yabiao and Fu, Yanwei and Feng, Jianfeng and Xiang, Tao and Torr, Philip HS and others},
  booktitle={Computer Vision and Pattern Recognition},
  pages={6881--6890},
  year={2021}
}