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

The research in self-supervised domain adaptation in semantic segmentationhas recently received considerable attention. Although GAN-based methods havebecome one of the most popular approaches to domain adaptation, they havesuffered from some limitations. They are insufficient to model both global andlocal structures of a given image, especially in small regions of tail classes.Moreover, they perform bad on the tail classes containing limited number ofpixels or less training samples. In order to address these issues, we present anew self-supervised domain adaptation approach to tackle long-tail semanticsegmentation in this paper. Firstly, a new metric is introduced to formulatelong-tail domain adaptation in the segmentation problem. Secondly, a newConditional Maximum Likelihood (CoMaL) approach in an autoregressive frameworkis presented to solve the problem of long-tail domain adaptation. Althoughother segmentation methods work under the pixel independence assumption, thelong-tailed pixel distributions in CoMaL are generally solved in the context ofstructural dependency, as that is more realistic. Finally, the proposed methodis evaluated on popular large-scale semantic segmentation benchmarks, i.e.,"SYNTHIA to Cityscapes" and "GTA to Cityscapes", and outperforms the priormethods by a large margin in both the standard and the proposed evaluationprotocols.

CoMaL: Conditional Maximum Likelihood Approach to Self-supervised Domain Adaptation in Long-tail Semantic Segmentation