RefineNet-LW

RefineNet-LW

2019/11/21

前言：

Light-weight RefineNet 藉由三個改進讓 RefineNet 適合在行動裝置上運作。首先是將 Conv3 改成 Conv1，其次是去除殘差卷積單元，最後則是將網路骨幹改成行動裝置的卷積網路如 MobileNet 等。

-----

# RefineNet-LW

-----

# RefineNet-LW

-----

# RefineNet-LW

-----

# RefineNet-LW

-----

# RefineNet-LW

-----

# RefineNet-LW

-----

# RefineNet-LW

-----

# RefineNet-LW

-----

References

# RefineNet-LW

Nekrasov, Vladimir, Chunhua Shen, and Ian Reid. "Light-weight refinenet for real-time semantic segmentation." arXiv preprint arXiv:1810.03272 (2018).

https://arxiv.org/pdf/1810.03272.pdf 

图像分割之Light-Weight RefineNet - 年轻即出发， - CSDN博客
https://blog.csdn.net/qq_14845119/article/details/84776977