mlsanityData to 14 Oct 2026

MorphoActivation: Generalizing ReLU activation function by mathematical morphology

arXiv 2207.06413 ↗First posted 13 Jul 2022cs.LG cs.DM eess.IVcited by 3

Not on the map. Why?

Abstract (arXiv)

This paper analyses both nonlinear activation functions and spatial max-pooling for Deep Convolutional Neural Networks (DCNNs) by means of the algebraic basis of mathematical morphology. Additionally, a general family of activation functions is proposed by considering both max-pooling and nonlinear operators in the context of morphological representations. Experimental section validates the goodness of our approach on classical benchmarks for supervised learning by DCNN.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 6 of its 36 references that are in the map. First posted on arXiv 13 Jul 2022.

Builds on

6 of 36 references.

References · 6

  1. 2015Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classificationcited by 3,611
  2. 2013Maxout Networkscited by 187
  3. 2020Training BatchNorm and Only BatchNorm: On the Expressive Power of Random Features in CNNscited by 104
  4. 2018Tropical Geometry of Deep Neural Networkscited by 95
  5. 2020Activate or Not: Learning Customized Activationcited by 22
  6. 2020Reduced Dilation-Erosion Perceptron for Binary Classificationcited by 7

Built on by

Cited by year

Citing papers per year: 2023: 2; 2024: 0; 2025: 1.

3 papers.

  1. 2023Tight Certified Robustness via Min-Max Representations of ReLU Neural Networkscited by 2
  2. 2025Training Deep Morphological Neural Networks as Universal Approximatorscited by 2
  3. 2023HaarNet: Large-scale Linear-Morphological Hybrid Network for RGB-D Semantic Segmentationcited by 0