Dilated Convolutions are a type of convolution that “inflate” the kernel by inserting holes between the kernel elements. An additional parameter $l$ (dilation rate) indicates how much the kernel is widened. There are usually $l-1$ spaces inserted between kernel elements.
Note that concept has existed in past literature under different names, for instance the algorithme a trous, an algorithm for wavelet decomposition (Holschneider et al., 1987; Shensa, 1992).Source: Multi-Scale Context Aggregation by Dilated Convolutions
|🤖 No Components Found||You can add them if they exist; e.g. Mask R-CNN uses RoIAlign|