MorphPool: Efficient Non-linear Pooling & Unpooling in CNNs
Rick Groenendijk (University of Amsterdam),* Leo Dorst (University of Amsterdam), Theo Gevers (University of Amsterdam)
The 33rd British Machine Vision Conference
Abstract
Pooling is essentially an operation from the field of Mathematical Morphology, with max pooling as a limited special case. The more general setting of MorphPooling greatly extends the tool set for building neural networks. In addition to pooling operations, encoder-decoder networks used for pixel-level predictions also require unpooling. It is common to combine unpooling with convolution or deconvolution for up-sampling. However, using its morphological properties, unpooling can be generalised and improved. Extensive experimentation on two tasks and three large-scale datasets shows that morphological pooling and unpooling lead to improved predictive performance at much reduced parameter counts.Video
Citation
@inproceedings{Groenendijk_2022_BMVC,
author = {Rick Groenendijk and Leo Dorst and Theo Gevers},
title = {MorphPool: Efficient Non-linear Pooling & Unpooling in CNNs},
booktitle = {33rd British Machine Vision Conference 2022, {BMVC} 2022, London, UK, November 21-24, 2022},
publisher = {{BMVA} Press},
year = {2022},
url = {https://bmvc2022.mpi-inf.mpg.de/0056.pdf}
}
Copyright © 2022
The British Machine Vision Conference is organised by