Dilated Convolutions
Last updated
Last updated
In simple terms, dilated convolution is just a convolution applied to input with defined gaps. With this definitions, given our input is an 2D image, dilation rate k=1 is normal convolution and k=2 means skipping one pixel per input and k=4 means skipping 3 pixels. In dilated convolutions the change is in the filter and not features. The filters (weights) skips the input according to dilation rate.
This gives explanation of how dilated convolution are different from convolutions with strides.
In short, dilated convolution is a simple but effective idea and you might consider it in two cases;
Detection of fine-details by processing inputs in higher resolutions.
Broader view of the input to capture more contextual information.
Faster run-time with less parameters