FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4384080234> ?p ?o ?g. }

• W4384080234 endingPage "18" @default.
• W4384080234 startingPage "1" @default.
• W4384080234 abstract "Cloud detection plays a significant role in remote sensing image applications. Existing deep learning-based cloud detection methods rely on massive precise pixel-wise annotations, which are time-consuming and expensive. To alleviate this problem, we propose a weakly supervised cloud detection framework that leverages physical rules to generate weak supervision for cloud detection in remote sensing images. Specifically, a rule-based adaptive pseudo labeling (RAPL) algorithm is devised to adaptively annotate potential cloud pixels based on cloud spectral properties without manual intervention. Unlike existing physical annotations using fixed thresholds, RAPL employs the bidirectional threshold segmentation and adaptive gating mechanism to annotate cloud and boundary masks with more explicit semantic categories and spatial structures separately. Subsequently, these pseudo masks are treated as weak supervision to optimize the heuristic cloud detection network for pixel-wise segmentation. Considering that clouds appear as complex geometric structures and nonuniform spectral reflectance, a deformable boundary refining module is designed to enhance the modeling ability of spatial transformation and activate sharp boundaries from translucent cloud regions. Moreover, a harmonic loss is employed to recognize clouds with nonuniform spectral reflectance and suppress the interference of bright backgrounds. Extensive experiments on the GF-1, L8 Biome, and WDCD datasets demonstrate that the proposed method achieves state-of-the-art results. A public reference implementation of this work in PyTorch is available at https://github.com/NiAn-creator/HeuristicCloudDetection." @default.
• W4384080234 created "2023-07-13" @default.
• W4384080234 creator A5020484951 @default.
• W4384080234 creator A5021115301 @default.
• W4384080234 creator A5037675566 @default.
• W4384080234 creator A5039910230 @default.
• W4384080234 creator A5040765066 @default.
• W4384080234 creator A5049242358 @default.
• W4384080234 creator A5054864219 @default.
• W4384080234 creator A5078175622 @default.
• W4384080234 date "2023-01-01" @default.
• W4384080234 modified "2023-10-17" @default.
• W4384080234 title "Leveraging Physical Rules for Weakly Supervised Cloud Detection in Remote Sensing Images" @default.
• W4384080234 cites W1533693043 @default.
• W4384080234 cites W1967386275 @default.
• W4384080234 cites W2001599060 @default.
• W4384080234 cites W2014096274 @default.
• W4384080234 cites W2025745000 @default.
• W4384080234 cites W2028191110 @default.
• W4384080234 cites W2028240797 @default.
• W4384080234 cites W2068124105 @default.
• W4384080234 cites W2133059825 @default.
• W4384080234 cites W2166251851 @default.
• W4384080234 cites W2194775991 @default.
• W4384080234 cites W2326555679 @default.
• W4384080234 cites W2412782625 @default.
• W4384080234 cites W2565639579 @default.
• W4384080234 cites W2584156879 @default.
• W4384080234 cites W2601564443 @default.
• W4384080234 cites W2605847660 @default.
• W4384080234 cites W2801541271 @default.
• W4384080234 cites W2886928598 @default.
• W4384080234 cites W2901249518 @default.
• W4384080234 cites W2904005494 @default.
• W4384080234 cites W2914757358 @default.
• W4384080234 cites W2927122915 @default.
• W4384080234 cites W2946072066 @default.
• W4384080234 cites W2950314938 @default.
• W4384080234 cites W2964334477 @default.
• W4384080234 cites W2982092116 @default.
• W4384080234 cites W2989491750 @default.
• W4384080234 cites W3000627240 @default.
• W4384080234 cites W3027738884 @default.
• W4384080234 cites W3028160024 @default.
• W4384080234 cites W3037529526 @default.
• W4384080234 cites W3042088791 @default.
• W4384080234 cites W3080368312 @default.
• W4384080234 cites W3098834274 @default.
• W4384080234 cites W3110908156 @default.
• W4384080234 cites W3118957360 @default.
• W4384080234 cites W3129390331 @default.
• W4384080234 cites W3132505321 @default.
• W4384080234 cites W3134927667 @default.
• W4384080234 cites W3138074985 @default.
• W4384080234 cites W3173374491 @default.
• W4384080234 cites W3183732083 @default.
• W4384080234 cites W3184748435 @default.
• W4384080234 cites W3192168220 @default.
• W4384080234 cites W3194376449 @default.
• W4384080234 cites W3194482819 @default.
• W4384080234 cites W3203755984 @default.
• W4384080234 cites W4205510142 @default.
• W4384080234 cites W4206571460 @default.
• W4384080234 cites W4210847275 @default.
• W4384080234 cites W4213186602 @default.
• W4384080234 cites W4224028831 @default.
• W4384080234 cites W4285198998 @default.
• W4384080234 cites W4285207472 @default.
• W4384080234 cites W4285302592 @default.
• W4384080234 cites W4289205113 @default.
• W4384080234 cites W4292702164 @default.
• W4384080234 cites W4313192742 @default.
• W4384080234 cites W4313438466 @default.
• W4384080234 cites W4366310757 @default.
• W4384080234 cites W4376481071 @default.
• W4384080234 cites W625827677 @default.
• W4384080234 doi "https://doi.org/10.1109/tgrs.2023.3294817" @default.
• W4384080234 hasPublicationYear "2023" @default.
• W4384080234 type Work @default.
• W4384080234 citedByCount "0" @default.
• W4384080234 crossrefType "journal-article" @default.
• W4384080234 hasAuthorship W4384080234A5020484951 @default.
• W4384080234 hasAuthorship W4384080234A5021115301 @default.
• W4384080234 hasAuthorship W4384080234A5037675566 @default.
• W4384080234 hasAuthorship W4384080234A5039910230 @default.
• W4384080234 hasAuthorship W4384080234A5040765066 @default.
• W4384080234 hasAuthorship W4384080234A5049242358 @default.
• W4384080234 hasAuthorship W4384080234A5054864219 @default.
• W4384080234 hasAuthorship W4384080234A5078175622 @default.
• W4384080234 hasConcept C108583219 @default.
• W4384080234 hasConcept C111919701 @default.
• W4384080234 hasConcept C124504099 @default.
• W4384080234 hasConcept C127313418 @default.
• W4384080234 hasConcept C154945302 @default.
• W4384080234 hasConcept C160633673 @default.
• W4384080234 hasConcept C173801870 @default.
• W4384080234 hasConcept C31972630 @default.
• W4384080234 hasConcept C41008148 @default.

• next