English

MorphPool: Efficient Non-linear Pooling & Unpooling in CNNs

Computer Vision and Pattern Recognition 2022-11-28 v1 Machine Learning

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.

Keywords

Cite

@article{arxiv.2211.14037,
  title  = {MorphPool: Efficient Non-linear Pooling & Unpooling in CNNs},
  author = {Rick Groenendijk and Leo Dorst and Theo Gevers},
  journal= {arXiv preprint arXiv:2211.14037},
  year   = {2022}
}

Comments

Accepted paper at the British Machine Vision Conference (BMVC) 2022

R2 v1 2026-06-28T07:12:33.803Z