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

In this paper, we present an adversarial unsupervised domain adaptationframework for object detection. Prior approaches utilize adversarial trainingbased on cross entropy between the source and target domain distributions tolearn a shared feature mapping that minimizes the domain gap. Here, we minimizethe Wasserstein distance between the two distributions instead of cross entropyor Jensen-Shannon divergence to improve the stability of domain adaptation inhigh-dimensional feature spaces that are inherent to object detection task.Additionally, we remove the exact consistency constraint of the shared featuremapping between the source and target domains, so that the target featuremapping can be optimized independently, which is necessary in the case ofsignificant domain gap. We empirically show that the proposed framework canmitigate domain shift in different scenarios, and provide improved targetdomain object detection performance.

Wasserstein Distance Based Domain Adaptation for Object Detection