FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4308156913> ?p ?o ?g. }

• W4308156913 endingPage "109766" @default.
• W4308156913 startingPage "109766" @default.
• W4308156913 abstract "Remote sensing image change detection (CD) technology is an important means to understand the changes of the earth surface. In recent years, many excellent CD methods based on convolutional neural networks (CNN) have been proposed. Although these methods have achieved good results, CD is still a very challenging task. Recently, many visual algorithms based on multi-layer perceptron (MLP) have been proposed and achieved similar or even better results than CNN-based algorithms in many visual fields. Inspired by the success of these MLP-based algorithms, in this paper we propose a siamese U-shaped MLP-based CD network named SUMLP. First, SUMLP uses CycleMLP block as the basic unit of the network and combines the characteristics of the CD task to construct a MLP-based CD network with siamese U-shaped structure. Secondly, to better optimize the CD network, we design a new loss function, weighted cosine cross entropy (WCCE) loss. WCCE loss has two advantages: 1. WCCE loss gives different weights to the changed samples and the unchanged samples, which can cope with the data imbalance problem in the CD task; 2. WCCE loss uses cosine margin to increase the inter class distance and the intra class compactness, so as to better distinguish the changed samples from the unchanged samples. For comprehensively verifying the validity of our proposed method, we carried out many experiments on three public CD datasets: LEVIR-CD dataset, CDD dataset and WHU-CD dataset. On these datasets, SUMLP’s F 1 − s c o r e are at least 0.33%, 1.41% and 3.56% higher than the other relevant CD methods respectively. • A Siamese U-shaped MLP-based Network, SUMLP, was proposed, which is the fist CD netwoik based entiiely on MLP. • In oidei to bettei optimize the CD netwoik, weighted cosine cioss entiopy (WCCE) loss was designed. • The efectiveness of SUMLP and WCCEloss was evaluated." @default.
• W4308156913 created "2022-11-08" @default.
• W4308156913 creator A5038160921 @default.
• W4308156913 creator A5045353410 @default.
• W4308156913 creator A5067652312 @default.
• W4308156913 creator A5081489939 @default.
• W4308156913 date "2022-12-01" @default.
• W4308156913 modified "2023-09-24" @default.
• W4308156913 title "SUMLP: A Siamese U-shaped MLP-based network for change detection" @default.
• W4308156913 cites W1978283872 @default.
• W4308156913 cites W1998808035 @default.
• W4308156913 cites W2015619014 @default.
• W4308156913 cites W2015780366 @default.
• W4308156913 cites W2036841511 @default.
• W4308156913 cites W2097117768 @default.
• W4308156913 cites W2112796928 @default.
• W4308156913 cites W2140023211 @default.
• W4308156913 cites W2548780814 @default.
• W4308156913 cites W2739310573 @default.
• W4308156913 cites W2751993439 @default.
• W4308156913 cites W2805152403 @default.
• W4308156913 cites W2884561390 @default.
• W4308156913 cites W2891248708 @default.
• W4308156913 cites W2896092083 @default.
• W4308156913 cites W2908320224 @default.
• W4308156913 cites W2963037989 @default.
• W4308156913 cites W2963307811 @default.
• W4308156913 cites W2963446712 @default.
• W4308156913 cites W3009942016 @default.
• W4308156913 cites W3027225766 @default.
• W4308156913 cites W3099206234 @default.
• W4308156913 cites W3099503507 @default.
• W4308156913 cites W3101998545 @default.
• W4308156913 cites W3103152812 @default.
• W4308156913 cites W3120467244 @default.
• W4308156913 cites W4312350143 @default.
• W4308156913 cites W4312994792 @default.
• W4308156913 cites W639708223 @default.
• W4308156913 doi "https://doi.org/10.1016/j.asoc.2022.109766" @default.
• W4308156913 hasPublicationYear "2022" @default.
• W4308156913 type Work @default.
• W4308156913 citedByCount "0" @default.
• W4308156913 crossrefType "journal-article" @default.
• W4308156913 hasAuthorship W4308156913A5038160921 @default.
• W4308156913 hasAuthorship W4308156913A5045353410 @default.
• W4308156913 hasAuthorship W4308156913A5067652312 @default.
• W4308156913 hasAuthorship W4308156913A5081489939 @default.
• W4308156913 hasConcept C153180895 @default.
• W4308156913 hasConcept C154945302 @default.
• W4308156913 hasConcept C203595873 @default.
• W4308156913 hasConcept C41008148 @default.
• W4308156913 hasConceptScore W4308156913C153180895 @default.
• W4308156913 hasConceptScore W4308156913C154945302 @default.
• W4308156913 hasConceptScore W4308156913C203595873 @default.
• W4308156913 hasConceptScore W4308156913C41008148 @default.
• W4308156913 hasLocation W43081569131 @default.
• W4308156913 hasOpenAccess W4308156913 @default.
• W4308156913 hasPrimaryLocation W43081569131 @default.
• W4308156913 hasRelatedWork W1978450727 @default.
• W4308156913 hasRelatedWork W2033914206 @default.
• W4308156913 hasRelatedWork W2146076056 @default.
• W4308156913 hasRelatedWork W2163831990 @default.
• W4308156913 hasRelatedWork W2378160586 @default.
• W4308156913 hasRelatedWork W3003836766 @default.
• W4308156913 hasRelatedWork W3107474891 @default.
• W4308156913 hasRelatedWork W3199009818 @default.
• W4308156913 hasRelatedWork W4244943737 @default.
• W4308156913 hasRelatedWork W4285323898 @default.
• W4308156913 hasVolume "131" @default.
• W4308156913 isParatext "false" @default.
• W4308156913 isRetracted "false" @default.
• W4308156913 workType "article" @default.