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 novel method that tackles the problem of unsupervised domainadaptation for semantic segmentation by maximizing the cosine similaritybetween the source and the target domain at the feature level. A segmentationnetwork mainly consists of two parts, a feature extractor and a classificationhead. We expect that if we can make the two domains have small domain gap atthe feature level, they would also have small domain discrepancy at theclassification head. Our method computes a cosine similarity matrix between thesource feature map and the target feature map, then we maximize the elementsexceeding a threshold to guide the target features to have high similarity withthe most similar source feature. Moreover, we use a class-wise source featuredictionary which stores the latest features of the source domain to prevent theunmatching problem when computing the cosine similarity matrix and be able tocompare a target feature with various source features from various images.Through extensive experiments, we verify that our method gains performance ontwo unsupervised domain adaptation tasks (GTA5$\to$ Cityscaspes andSYNTHIA$\to$ Cityscapes).

Maximizing Cosine Similarity Between Spatial Features for Unsupervised Domain Adaptation in Semantic Segmentation