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

Although considerable progress has been made in semantic scene understandingunder clear weather, it is still a tough problem under adverse weatherconditions, such as dense fog, due to the uncertainty caused by imperfectobservations. Besides, difficulties in collecting and labeling foggy imageshinder the progress of this field. Considering the success in semantic sceneunderstanding under clear weather, we think it is reasonable to transferknowledge learned from clear images to the foggy domain. As such, the problembecomes to bridge the domain gap between clear images and foggy images. Unlikeprevious methods that mainly focus on closing the domain gap caused by fog --defogging the foggy images or fogging the clear images, we propose to alleviatethe domain gap by considering fog influence and style variation simultaneously.The motivation is based on our finding that the style-related gap and thefog-related gap can be divided and closed respectively, by adding anintermediate domain. Thus, we propose a new pipeline to cumulatively adaptstyle, fog and the dual-factor (style and fog). Specifically, we devise aunified framework to disentangle the style factor and the fog factorseparately, and then the dual-factor from images in different domains.Furthermore, we collaborate the disentanglement of three factors with a novelcumulative loss to thoroughly disentangle these three factors. Our methodachieves the state-of-the-art performance on three benchmarks and showsgeneralization ability in rainy and snowy scenes.

Both Style and Fog Matter: Cumulative Domain Adaptation for Semantic Foggy Scene Understanding