In CNN, the area size of the input layer that determines an element in the output of a certain layer is called the receptive field (receptive field), which refers to the area that can be perceived by a neuron in the neural network. In CNN, That is, the calculation of a certain element is affected by the area on the input image, and this area is the receptive field of the element on the feature map.
The receptive field is a relative concept. The elements on a certain layer see different areas in the previous layer. Usually, unless otherwise specified, the receptive field refers to the area on the input image.