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 ConvolutionsPaper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Semantic Segmentation | 153 | 16.26% |
Reinforcement Learning (RL) | 77 | 8.18% |
Object Detection | 43 | 4.57% |
Image Segmentation | 42 | 4.46% |
Autonomous Driving | 24 | 2.55% |
Continuous Control | 22 | 2.34% |
Image Classification | 20 | 2.13% |
Instance Segmentation | 17 | 1.81% |
General Classification | 14 | 1.49% |
Component | Type |
|
---|---|---|
🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |