[深度学习论文笔记][Semantic Segmentation] Learning Deconvolution Network for Semantic Segmentation

Noh, Hyeonwoo, Seunghoon Hong, and Bohyung Han. “Learning deconvolution network for semantic segmentation.” Proceedings of the IEEE International Conference on Com-
puter Vision. 2015. (Citations: 139).


1 Motivation

The deconvolution layer of FCN is too coarse and overly simple.


2 Architecture

See Fig. Region proposals are fed into the network. Compared with feeding the whole image into the network, it can handle object in various sizes.

[深度学习论文笔记][Semantic Segmentation] Learning Deconvolution Network for Semantic Segmentation_第1张图片


The network is composed with a VGG followed by a upside down (mirrored) VGG. The forward pass of unpooling layer is the backward pass of standard pooling layer. The

unpooling switches are from the correponding pooling layer. 


3 References
[1]. http://web.cs.hacettepe.edu.tr/ ̃aykut/classes/spring2016/bil722/slides/w06-deconvnet.pdf.

你可能感兴趣的:(CNN,Papers)