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

03/25/2022
by   Pablo Hernández-Cámara, et al.
0

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.

READ FULL TEXT

page 2

page 3

page 5

research
07/30/2017

A Novel Approach for Image Segmentation based on Histograms computed from Hue-data

Computer Vision is growing day by day in terms of user specific applicat...
research
07/25/2018

Two at Once: Enhancing Learning and Generalization Capacities via IBN-Net

Convolutional neural networks (CNNs) have achieved great successes in ma...
research
12/02/2019

Adversarial normalization for multi domain image segmentation

Image normalization is a critical step in medical imaging. This step is ...
research
09/29/2020

Realistic Image Normalization for Multi-Domain Segmentation

Image normalization is a building block in medical image analysis. Conve...
research
04/15/2020

ALCN: Adaptive Local Contrast Normalization

To make Robotics and Augmented Reality applications robust to illuminati...
research
05/29/2020

WaveSNet: Wavelet Integrated Deep Networks for Image Segmentation

In deep networks, the lost data details significantly degrade the perfor...
research
12/06/2015

Linear Readout of Object Manifolds

Objects are represented in sensory systems by continuous manifolds due t...

Please sign up or login with your details

Forgot password? Click here to reset