English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

One of the key problems in computer vision is adaptation: models are toorigid to follow the variability of the inputs. The canonical computation thatexplains adaptation in sensory neuroscience is divisive normalization, and ithas appealing effects on image manifolds. In this work we show that includingdivisive normalization in current deep networks makes them more invariant tonon-informative changes in the images. In particular, we focus on U-Netarchitectures for image segmentation. Experiments show that the inclusion ofdivisive normalization in the U-Net architecture leads to better segmentationresults with respect to conventional U-Net. The gain increases steadily whendealing with images acquired in bad weather conditions. In addition to theresults on the Cityscapes and Foggy Cityscapes datasets, we explain theseadvantages through visualization of the responses: the equalization induced bythe divisive normalization leads to more invariant features to local changes incontrast and illumination.

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