FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3124992511> ?p ?o ?g. }

• W3124992511 endingPage "394" @default.
• W3124992511 startingPage "394" @default.
• W3124992511 abstract "Land cover classification is one of the most fundamental tasks in the field of remote sensing. In recent years, fully supervised fully convolutional network (FCN)-based semantic segmentation models have achieved state-of-the-art performance in the semantic segmentation task. However, creating pixel-level annotations is prohibitively expensive and laborious, especially when dealing with remote sensing images. Weakly supervised learning methods from weakly labeled annotations can overcome this difficulty to some extent and achieve impressive segmentation results, but results are limited in accuracy. Inspired by point supervision and the traditional segmentation method of seeded region growing (SRG) algorithm, a weakly towards strongly (WTS) supervised learning framework is proposed in this study for remote sensing land cover classification to handle the absence of well-labeled and abundant pixel-level annotations when using segmentation models. In this framework, only several points with true class labels are required as the training set, which are much less expensive to acquire compared with pixel-level annotations through field survey or visual interpretation using high-resolution images. Firstly, they are used to train a Support Vector Machine (SVM) classifier. Once fully trained, the SVM is used to generate the initial seeded pixel-level training set, in which only the pixels with high confidence are assigned with class labels whereas others are unlabeled. They are used to weakly train the segmentation model. Then, the seeded region growing module and fully connected Conditional Random Fields (CRFs) are used to iteratively update the seeded pixel-level training set for progressively increasing pixel-level supervision of the segmentation model. Sentinel-2 remote sensing images are used to validate the proposed framework, and SVM is selected for comparison. In addition, FROM-GLC10 global land cover map is used as training reference to directly train the segmentation model. Experimental results show that the proposed framework outperforms other methods and can be highly recommended for land cover classification tasks when the pixel-level labeled datasets are insufficient by using segmentation models." @default.
• W3124992511 created "2021-02-01" @default.
• W3124992511 creator A5039849966 @default.
• W3124992511 creator A5046531394 @default.
• W3124992511 creator A5051151162 @default.
• W3124992511 creator A5066891690 @default.
• W3124992511 date "2021-01-23" @default.
• W3124992511 modified "2023-10-14" @default.
• W3124992511 title "WTS: A Weakly towards Strongly Supervised Learning Framework for Remote Sensing Land Cover Classification Using Segmentation Models" @default.
• W3124992511 cites W1485323427 @default.
• W3124992511 cites W1901129140 @default.
• W3124992511 cites W1903029394 @default.
• W3124992511 cites W2020795785 @default.
• W3124992511 cites W2063907334 @default.
• W3124992511 cites W2096579040 @default.
• W3124992511 cites W2102605133 @default.
• W3124992511 cites W2194775991 @default.
• W3124992511 cites W2256456552 @default.
• W3124992511 cites W2317513234 @default.
• W3124992511 cites W2412782625 @default.
• W3124992511 cites W2538244214 @default.
• W3124992511 cites W2604086375 @default.
• W3124992511 cites W2610528085 @default.
• W3124992511 cites W2616755213 @default.
• W3124992511 cites W2744274881 @default.
• W3124992511 cites W2749751926 @default.
• W3124992511 cites W2765226977 @default.
• W3124992511 cites W2793091350 @default.
• W3124992511 cites W2793268137 @default.
• W3124992511 cites W2884821113 @default.
• W3124992511 cites W2886742956 @default.
• W3124992511 cites W2888697548 @default.
• W3124992511 cites W2889206596 @default.
• W3124992511 cites W2890833618 @default.
• W3124992511 cites W2898682679 @default.
• W3124992511 cites W2904005494 @default.
• W3124992511 cites W2913087080 @default.
• W3124992511 cites W2919352650 @default.
• W3124992511 cites W2920254659 @default.
• W3124992511 cites W2945231726 @default.
• W3124992511 cites W2948648905 @default.
• W3124992511 cites W2963881378 @default.
• W3124992511 cites W2973660294 @default.
• W3124992511 cites W3037021879 @default.
• W3124992511 cites W3045585619 @default.
• W3124992511 cites W3086458417 @default.
• W3124992511 cites W639708223 @default.
• W3124992511 doi "https://doi.org/10.3390/rs13030394" @default.
• W3124992511 hasPublicationYear "2021" @default.
• W3124992511 type Work @default.
• W3124992511 sameAs 3124992511 @default.
• W3124992511 citedByCount "12" @default.
• W3124992511 countsByYear W31249925112021 @default.
• W3124992511 countsByYear W31249925112022 @default.
• W3124992511 countsByYear W31249925112023 @default.
• W3124992511 crossrefType "journal-article" @default.
• W3124992511 hasAuthorship W3124992511A5039849966 @default.
• W3124992511 hasAuthorship W3124992511A5046531394 @default.
• W3124992511 hasAuthorship W3124992511A5051151162 @default.
• W3124992511 hasAuthorship W3124992511A5066891690 @default.
• W3124992511 hasBestOaLocation W31249925111 @default.
• W3124992511 hasConcept C119857082 @default.
• W3124992511 hasConcept C12267149 @default.
• W3124992511 hasConcept C127413603 @default.
• W3124992511 hasConcept C147176958 @default.
• W3124992511 hasConcept C152565575 @default.
• W3124992511 hasConcept C153180895 @default.
• W3124992511 hasConcept C154945302 @default.
• W3124992511 hasConcept C160633673 @default.
• W3124992511 hasConcept C205649164 @default.
• W3124992511 hasConcept C2775953691 @default.
• W3124992511 hasConcept C2780648208 @default.
• W3124992511 hasConcept C41008148 @default.
• W3124992511 hasConcept C4792198 @default.
• W3124992511 hasConcept C62649853 @default.
• W3124992511 hasConcept C89600930 @default.
• W3124992511 hasConcept C95623464 @default.
• W3124992511 hasConceptScore W3124992511C119857082 @default.
• W3124992511 hasConceptScore W3124992511C12267149 @default.
• W3124992511 hasConceptScore W3124992511C127413603 @default.
• W3124992511 hasConceptScore W3124992511C147176958 @default.
• W3124992511 hasConceptScore W3124992511C152565575 @default.
• W3124992511 hasConceptScore W3124992511C153180895 @default.
• W3124992511 hasConceptScore W3124992511C154945302 @default.
• W3124992511 hasConceptScore W3124992511C160633673 @default.
• W3124992511 hasConceptScore W3124992511C205649164 @default.
• W3124992511 hasConceptScore W3124992511C2775953691 @default.
• W3124992511 hasConceptScore W3124992511C2780648208 @default.
• W3124992511 hasConceptScore W3124992511C41008148 @default.
• W3124992511 hasConceptScore W3124992511C4792198 @default.
• W3124992511 hasConceptScore W3124992511C62649853 @default.
• W3124992511 hasConceptScore W3124992511C89600930 @default.
• W3124992511 hasConceptScore W3124992511C95623464 @default.
• W3124992511 hasFunder F4320321001 @default.
• W3124992511 hasIssue "3" @default.
• W3124992511 hasLocation W31249925111 @default.
• W3124992511 hasLocation W31249925112 @default.
• W3124992511 hasOpenAccess W3124992511 @default.

• next