The unpooling operation is used to revert the effect of the max pooling operation; the idea is just to work as an upsampler. This operation has been used on some older papers and is not used so much anymore due to the fact that you also need a CONV layer to inpaint (low pass filter) the results of the upsampling:
Get Hands-On Convolutional Neural Networks with TensorFlow now with the O’Reilly learning platform.
O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.
Get Mark Richards’s Software Architecture Patterns ebook to better understand how to design components—and how they should interact.
Dive in for free with a 10-day trial of the O’Reilly learning platform—then explore all the other resources our members count on to build skills and solve problems every day.
Start your free trial Become a member now