AI engineering glossary · Computer vision
What is receptive field?
Receptive field: The region of the original input image that can influence one unit in a given layer. It grows as layers are stacked, so early units see small edges and deeper units see whole objects, which is why depth matters for recognising large structures.
Receptive field: an example
Two stacked 3 x 3 convolutions with stride 1 give each output unit a 5 x 5 receptive field; three give 7 x 7.
Related terms
More Computer vision terms
Where you learn it
Receptive field is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.