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

Due to the scarcity of dense pixel-level semantic annotations for imagesrecorded in adverse visual conditions, there has been a keen interest inunsupervised domain adaptation (UDA) for the semantic segmentation of suchimages. UDA adapts models trained on normal conditions to the targetadverse-condition domains. Meanwhile, multiple datasets with driving scenesprovide corresponding images of the same scenes across multiple conditions,which can serve as a form of weak supervision for domain adaptation. We proposeRefign, a generic extension to self-training-based UDA methods which leveragesthese cross-domain correspondences. Refign consists of two steps: (1) aligningthe normal-condition image to the corresponding adverse-condition image usingan uncertainty-aware dense matching network, and (2) refining the adverseprediction with the normal prediction using an adaptive label correctionmechanism. We design custom modules to streamline both steps and set the newstate of the art for domain-adaptive semantic segmentation on severaladverse-condition benchmarks, including ACDC and Dark Zurich. The approachintroduces no extra training parameters, minimal computational overhead --during training only -- and can be used as a drop-in extension to improve anygiven self-training-based UDA method. Code is available athttps://github.com/brdav/refign.

Refign: Align and Refine for Adaptation of Semantic Segmentation to Adverse Conditions