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

Annotating large scale datasets to train modern convolutional neural networksis prohibitively expensive and time-consuming for many real tasks. Onealternative is to train the model on labeled synthetic datasets and apply it inthe real scenes. However, this straightforward method often fails to generalizewell mainly due to the domain bias between the synthetic and real datasets.Many unsupervised domain adaptation (UDA) methods are introduced to addressthis problem but most of them only focus on the simple classification task. Inthis paper, we present a novel UDA model to solve the more complex objectdetection problem in the context of autonomous driving. Our model integratesboth pixel level and feature level based transformtions to fulfill the crossdomain detection task and can be further trained end-to-end to pursue betterperformance. We employ objectives of the generative adversarial network and thecycle consistency loss for image translation in the pixel space. To address thepotential semantic inconsistency problem, we propose region proposal basedfeature adversarial training to preserve the semantics of our target objects aswell as further minimize the domain shifts. Extensive experiments are conductedon several different datasets, and the results demonstrate the robustness andsuperiority of our method.

Pixel and Feature Level Based Domain Adaption for Object Detection in Autonomous Driving