AI engineering glossary · Computer vision
What is dilated convolution?
Dilated convolution (also called Atrous convolution): A convolution whose kernel taps are spaced apart by gaps, enlarging the receptive field without extra parameters or lost resolution. It is popular in segmentation, where wide context is needed but the output must stay detailed.
Dilated convolution: an example
A 3 x 3 kernel with dilation 2 covers a 5 x 5 area while still using only 9 weights.
Related terms
More Computer vision terms
- Document layout analysis
- Edge detection
- EfficientNet
- Face detection
- Fast R-CNN
- Faster R-CNN
- Feature descriptor
- Feature detection
Where you learn it
Dilated convolution is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.