What is the receptive field in a CNN?
mediumAnswer
- The receptive field of a neuron is the region of the input image that influences its value.
- It grows with depth, kernel size, and stride/dilation.
- Deeper layers see larger regions.
- Techniques to grow the receptive field: stacking layers, larger kernels, strided convolutions, dilated (atrous) convolutions, and pooling.
- A large enough receptive field is required to capture global context.
Check yourself — multiple choice
- The receptive field shrinks with depth
- Dilated convolutions increase the receptive field without more parameters
- Larger kernels reduce the receptive field
- Stride does not affect the receptive field
Dilation enlarges the receptive field cheaply — used in segmentation networks.
#cnn
Practise Deep Learning
214 interview questions in this topic.
Related questions
- What inductive biases do CNNs have?
- Compute the output shape of a 2D convolution with input (H, W), kernel k, stride s, padding p, dilation d.
- SAME vs VALID vs REFLECT padding — what are the practical differences?
- What is a dilated (atrous) convolution?
- What is a transposed convolution ('deconv') and its checkerboard artifact issue?
- How does a depthwise separable convolution reduce compute?