There are at least three questions on this site related to this
- What is the effect of using pooling layers in CNNs?
- Is pooling a kind of dropout?
- 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:
- To decrease the size of the feature maps
- To make the model stronger in feature extraction
Are there any other purposes of pooling in CNN other than them?