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

Unsupervised domain adaptation for semantic segmentation has been intensivelystudied due to the low cost of the pixel-level annotation for synthetic data.The most common approaches try to generate images or features mimicking thedistribution in the target domain while preserving the semantic contents in thesource domain so that a model can be trained with annotations from the latter.However, such methods highly rely on an image translator or feature extractortrained in an elaborated mechanism including adversarial training, which bringsin extra complexity and instability in the adaptation process. Furthermore,these methods mainly focus on taking advantage of the labeled source dataset,leaving the unlabeled target dataset not fully utilized. In this paper, wepropose a bidirectional style-induced domain adaptation method, called BiSIDA,that employs consistency regularization to efficiently exploit information fromthe unlabeled target domain dataset, requiring only a simple neural styletransfer model. BiSIDA aligns domains by not only transferring source imagesinto the style of target images but also transferring target images into thestyle of source images to perform high-dimensional perturbation on theunlabeled target images, which is crucial to the success in applyingconsistency regularization in segmentation tasks. Extensive experiments showthat our BiSIDA achieves new state-of-the-art on two commonly-usedsynthetic-to-real domain adaptation benchmarks: GTA5-to-CityScapes andSYNTHIA-to-CityScapes.

Consistency Regularization with High-dimensional Non-adversarial Source-guided Perturbation for Unsupervised Domain Adaptation in Segmentation