C 4.8 | Pooling Layer Intuition | CNN | Convolutional Neural Network | Object Detection | EvODN

Описание: Pooling layer is similar to downsampling of an image, where the most important features are retained despite the loss of information.
Except, in the case of CNNs, we downsample the Feature Vector outputs of Conv layer.

------------------------
This is a part of the course 'Evolution of Object Detection Networks'.
See full playlist here:    • Evolution Of Object Detection Networks  
------------------------
Credits:
https://www.researchgate.net/figure/D...

Copyright Disclaimer: Under section 107 of the Copyright Act 1976, allowance is made for “fair use” for purposes such as criticism, comment, news reporting, teaching, scholarship, education and research.