# MorphPool: Efficient Non-linear Pooling & Unpooling in CNNs

arXiv: https://arxiv.org/abs/2211.14037 · HTML: https://mlsanity.com/paper/2211.14037/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 43 references that are in the map.
- First posted on arXiv 25 Nov 2022.

## Builds on (most cited first, 17 of 17)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [Xception: Deep Learning with Depthwise Separable Convolutions](https://mlsanity.com/paper/1610.02357/) (2016)
- [Visualizing and Understanding Convolutional Networks](https://mlsanity.com/paper/1311.2901/) (2013)
- [SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation](https://mlsanity.com/paper/1511.00561/) (2015)
- [Joint 2D-3D-Semantic Data for Indoor Scene Understanding](https://mlsanity.com/paper/1702.01105/) (2017)
- [Deeper Depth Prediction with Fully Convolutional Residual Networks](https://mlsanity.com/paper/1606.00373/) (2016)
- [Learning Deconvolution Network for Semantic Segmentation](https://mlsanity.com/paper/1505.04366/) (2015)
- [Deep Scale-spaces: Equivariance Over Scale](https://mlsanity.com/paper/1905.11697/) (2019)
- [Pooling Methods in Deep Neural Networks, a Review](https://mlsanity.com/paper/2009.07485/) (2020)
- [Learning to Generate Chairs, Tables and Cars with Convolutional Networks](https://mlsanity.com/paper/1411.5928/) (2014)
- [Scale Equivariant Neural Networks with Morphological Scale-Spaces](https://mlsanity.com/paper/2105.01335/) (2021)
- [Some open questions on morphological operators and representations in the deep learning era](https://mlsanity.com/paper/2105.01339/) (2021)

## Built on by (most cited first, 3 of 3)

- [Discrete Morphological Neural Networks](https://mlsanity.com/paper/2309.00588/) (2023)
- [An Algorithm to Train Unrestricted Sequential Discrete Morphological Neural Networks](https://mlsanity.com/paper/2310.04584/) (2023)
- [HaarNet: Large-scale Linear-Morphological Hybrid Network for RGB-D Semantic Segmentation](https://mlsanity.com/paper/2310.07669/) (2023)

## Abstract (arXiv)

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.