Dilated Convolution in Deep Learning
Dilated convolution is the concept of skipping the pixel while convoluting the kernel with the input.
It is also known as the pixel-skipping algorithm. the factor by which pixels are skipped is known as Dilation Factor (l)
Contents
Features of Dilated Convolution
- It helps to cover a larger area on the image with less computation
- It down-samples the features without pooling
Articles to Read
- https://www.geeksforgeeks.org/dilated-convolution/
- https://towardsdatascience.com/review-dilated-convolution-semantic-segmentation-9d5a5bd768f5
Standard Convolution vs Dilated Convolution
Post Tagged with : dilated convolution, dilatednet, down sampling without pooling, feature map, Machine Learning, skipping pixels