There are at least three questions on this site related to this

  1. What is the effect of using pooling layers in CNNs?
  2. Is pooling a kind of dropout?
  3. What are the benefits of using max-pooling in convolutional neural networks?

I got the following useful information regarding the purpose of pooling. As per my understanding, the purposes of pooling, based on priority, in general, are as follows:

  1. To decrease the size of the feature maps
  2. To make the model stronger in feature extraction

Are there any other purposes of pooling in CNN other than them?

  • $\begingroup$ Without pooling, how do you recommend making the image smaller? $\endgroup$ Sep 3, 2021 at 13:30
  • $\begingroup$ @user253751 It can be one of the purpose. $\endgroup$
    – hanugm
    Sep 30, 2021 at 0:41


You must log in to answer this question.

Browse other questions tagged .