What’s pooling in CNN? Why do we need it?
Computer VisionLevel: IntermediateNeural networks for computer vision
What’s pooling in CNN? Why do we need it?
Hints
- Track the receptive field and input/output dimensions.
- Check stride, padding, weight sharing and channel count.
Answer
Pooling is a technique to downsample the feature map. It allows layers which receive relatively undistorted versions of the input to learn low level features such as lines, while layers deeper in the model can learn more abstract features such as texture.
Source and licence: Alexey Grigorev & contributors — Data Science Interviews · CC-BY-4.0