RefineNet

RefineNet

2019/11/18

前言：

RefineNet 可以參考 RefineDet 的兩路設計。首先第一路的卷積網路可以產生不同大小的特徵圖，再進入第二路的 Refine 模組運算。模組主要由殘差卷積單元、多解析融合、鍊式殘差池化、以及輸出層構成。

-----

# RefineNet

-----

# RefineDet

-----

# RefineNet

-----

// Review  RefineNet — Multi-path Refinement Network (Semantic Segmentation)

-----

# RefineNet

-----

References

# RefineNet

Lin, Guosheng, et al. "Refinenet: Multi-path refinement networks for high-resolution semantic segmentation." Proceedings of the IEEE conference on computer vision and pattern recognition. 2017.

http://openaccess.thecvf.com/content_cvpr_2017/papers/Lin_RefineNet_Multi-Path_Refinement_CVPR_2017_paper.pdf 

# RefineDet

Zhang, Shifeng, et al. "Single-shot refinement neural network for object detection." Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2018.

http://openaccess.thecvf.com/content_cvpr_2018/papers/Zhang_Single-Shot_Refinement_Neural_CVPR_2018_paper.pdf

-----

Review  RefineNet — Multi-path Refinement Network (Semantic Segmentation)
https://towardsdatascience.com/review-refinenet-multi-path-refinement-network-semantic-segmentation-5763d9da47c1

-----

语义分割之RefineNet - 知乎
https://zhuanlan.zhihu.com/p/37805109