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

Object detection networks have reached an impressive performance level, yet alack of suitable data in specific applications often limits it in practice.Typically, additional data sources are utilized to support the training task.In these, however, domain gaps between different data sources pose a challengein deep learning. GAN-based image-to-image style-transfer is commonly appliedto shrink the domain gap, but is unstable and decoupled from the objectdetection task. We propose AWADA, an Attention-Weighted Adversarial DomainAdaptation framework for creating a feedback loop between style-transformationand detection task. By constructing foreground object attention maps fromobject detector proposals, we focus the transformation on foreground objectregions and stabilize style-transfer training. In extensive experiments andablation studies, we show that AWADA reaches state-of-the-art unsuperviseddomain adaptation object detection performance in the commonly used benchmarksfor tasks such as synthetic-to-real, adverse weather and cross-cameraadaptation.

AWADA: Attention-Weighted Adversarial Domain Adaptation for Object Detection