# Neural Networks with Divisive normalization for image segmentation with application in cityscapes dataset

arXiv: https://arxiv.org/abs/2203.13558 · HTML: https://mlsanity.com/paper/2203.13558/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 32 references that are in the map.
- First posted on arXiv 25 Mar 2022.

## Builds on (most cited first, 11 of 11)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [End-to-end Optimized Image Compression](https://mlsanity.com/paper/1611.01704/) (2016)
- [Semantic Foggy Scene Understanding with Synthetic Data](https://mlsanity.com/paper/1708.07819/) (2017)
- [Density Modeling of Images using a Generalized Normalization Transformation](https://mlsanity.com/paper/1511.06281/) (2015)
- [Perceptually Optimized Image Rendering](https://mlsanity.com/paper/1701.06641/) (2017)
- [Normalizing the Normalizers: Comparing and Extending Network Normalization Schemes](https://mlsanity.com/paper/1611.04520/) (2016)
- [PerceptNet: A Human Visual System Inspired Neural Network for Estimating Perceptual Distance](https://mlsanity.com/paper/1910.12548/) (2019)
- [Derivatives and Inverse of Cascaded Linear+Nonlinear Neural Models](https://mlsanity.com/paper/1711.00526/) (2017)
- [Spatio-Chromatic Information available from different Neural Layers via Gaussianization](https://mlsanity.com/paper/1910.01559/) (2019)
- [Integrating Flexible Normalization into Mid-Level Representations of Deep Convolutional Neural Networks](https://mlsanity.com/paper/1806.01823/) (2018)

## Abstract (arXiv)

One of the key problems in computer vision is adaptation: models are too rigid to follow the variability of the inputs. The canonical computation that explains adaptation in sensory neuroscience is divisive normalization, and it has appealing effects on image manifolds. In this work we show that including divisive normalization in current deep networks makes them more invariant to non-informative changes in the images. In particular, we focus on U-Net architectures for image segmentation. Experiments show that the inclusion of divisive normalization in the U-Net architecture leads to better segmentation results with respect to conventional U-Net. The gain increases steadily when dealing with images acquired in bad weather conditions. In addition to the results on the Cityscapes and Foggy Cityscapes datasets, we explain these advantages through visualization of the responses: the equalization induced by the divisive normalization leads to more invariant features to local changes in contrast and illumination.