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

Artificial intelligence (AI) approaches nowadays have gained remarkablesuccess in single-modality-dominated remote sensing (RS) applications,especially with an emphasis on individual urban environments (e.g., singlecities or regions). Yet these AI models tend to meet the performance bottleneckin the case studies across cities or regions, due to the lack of diverse RSinformation and cutting-edge solutions with high generalization ability. Tothis end, we build a new set of multimodal remote sensing benchmark datasets(including hyperspectral, multispectral, SAR) for the study purpose of thecross-city semantic segmentation task (called C2Seg dataset), which consists oftwo cross-city scenes, i.e., Berlin-Augsburg (in Germany) and Beijing-Wuhan (inChina). Beyond the single city, we propose a high-resolution domain adaptationnetwork, HighDAN for short, to promote the AI model's generalization abilityfrom the multi-city environments. HighDAN is capable of retaining the spatiallytopological structure of the studied urban scene well in a parallel high-to-lowresolution fusion fashion but also closing the gap derived from enormousdifferences of RS image representations between different cities by means ofadversarial learning. In addition, the Dice loss is considered in HighDAN toalleviate the class imbalance issue caused by factors across cities. Extensiveexperiments conducted on the C2Seg dataset show the superiority of our HighDANin terms of segmentation performance and generalization ability, compared tostate-of-the-art competitors. The C2Seg dataset and the semantic segmentationtoolbox (involving the proposed HighDAN) will be available publicly athttps://github.com/danfenghong.

Cross-City Matters: A Multimodal Remote Sensing Benchmark Dataset for  Cross-City Semantic Segmentation using High-Resolution Domain Adaptation  Networks