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

We propose a normalization layer for unsupervised domain adaption in semanticscene segmentation. Normalization layers are known to improve convergence andgeneralization and are part of many state-of-the-art fully-convolutional neuralnetworks. We show that conventional normalization layers worsen the performanceof current Unsupervised Adversarial Domain Adaption (UADA), which is a methodto improve network performance on unlabeled datasets and the focus of ourresearch. Therefore, we propose a novel Domain Agnostic Normalization layer andthereby unlock the benefits of normalization layers for unsupervisedadversarial domain adaptation. In our evaluation, we adapt from the syntheticGTA5 data set to the real Cityscapes data set, a common benchmark experiment,and surpass the state-of-the-art. As our normalization layer is domain agnosticat test time, we furthermore demonstrate that UADA using Domain AgnosticNormalization improves performance on unseen domains, specifically onApolloscape and Mapillary.

A Domain Agnostic Normalization Layer for Unsupervised Adversarial Domain Adaptation