一文读懂空洞卷积(Dilated Convolutions)
点击左上方蓝字关注我们
转载自 | 极市平台
一、空洞卷积的提出

二、空洞卷积的原理



a是普通的卷积过程(dilation rate = 1),卷积后的感受野为3 b是dilation rate = 2的空洞卷积,卷积后的感受野为5 c是dilation rate = 3的空洞卷积,卷积后的感受野为8






dense prediction problems such as semantic segmentation ... to increase the performance of dense prediction architectures by aggregating multi-scale contextual information(来自[1])
三、感受野的计算










当前层的感受野计算公式如下,其中,













四、潜在的问题及解决方法

Panqu Wang,Pengfei Chen,et al**.Understanding Convolution for Semantic Segmentation.//**WACV 2018 Fisher Yu,et al.Dilated Residual Networks.//CVPR 2017 Zhengyang Wang,et al.**Smoothed Dilated Convolutions for Improved Dense Prediction.//**KDD 2018. Liang-Chieh Chen,et al.Rethinking Atrous Convolution for Semantic Image Segmentation//2017 Sachin Mehta,et al.ESPNet: Efficient Spatial Pyramid of DilatedConvolutions for Semantic Segmentation.//ECCV 2018 Tianyi Wu**,et al.Tree-structured Kronecker Convolutional Networks for Semantic Segmentation.//AAAI2019** Hyojin Park,et al.Concentrated-Comprehensive Convolutionsfor lightweight semantic segmentation.//2018 Efficient Smoothing of Dilated Convolutions for Image Segmentation.//2019
END
整理不易,点赞三连↓
评论