# Max-plus Operators Applied to Filter Selection and Model Pruning in Neural Networks

arXiv: https://arxiv.org/abs/1903.08072 · HTML: https://mlsanity.com/paper/1903.08072/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Mar 2019.

## Built on by (most cited first, 7 of 7)

- [Learning Deep Morphological Networks with Neural Architecture Search](https://mlsanity.com/paper/2106.07714/) (2021)
- [Going beyond p-convolutions to learn grayscale morphological operators](https://mlsanity.com/paper/2102.10038/) (2021)
- [Training Deep Morphological Neural Networks as Universal Approximators](https://mlsanity.com/paper/2505.09710/) (2025)
- [Logarithmic Morphological Neural Nets robust to lighting variations](https://mlsanity.com/paper/2204.09319/) (2022)
- [Exploiting Subgradient Sparsity in Max-Plus Neural Networks](https://mlsanity.com/paper/2603.04133/) (2026)
- [Training morphological neural networks with gradient descent: some theoretical insights](https://mlsanity.com/paper/2403.12975/) (2024)
- [Sparse Hybrid Linear-Morphological Networks](https://mlsanity.com/paper/2504.09289/) (2025)

## Abstract (arXiv)

Following recent advances in morphological neural networks, we propose to study in more depth how Max-plus operators can be exploited to define morphological units and how they behave when incorporated in layers of conventional neural networks. Besides showing that they can be easily implemented with modern machine learning frameworks , we confirm and extend the observation that a Max-plus layer can be used to select important filters and reduce redundancy in its previous layer, without incurring performance loss. Experimental results demonstrate that the filter selection strategy enabled by a Max-plus is highly efficient and robust, through which we successfully performed model pruning on different neural network architectures. We also point out that there is a close connection between Maxout networks and our pruned Max-plus networks by comparing their respective characteristics. The code for reproducing our experiments is available online.