Matches in SemOpenAlex for { <https://semopenalex.org/work/W3217368032> ?p ?o ?g. }
- W3217368032 abstract "The development of accurate methods for multi-label classification (MLC) of remote sensing (RS) images is one of the most important research topics in RS. Methods based on Deep Convolutional Neural Networks (CNNs) have shown strong performance gains in RS MLC problems. However, CNN-based methods usually require a high number of reliable training images annotated by multiple land-cover class labels. Collecting such data is time-consuming and costly. To address this problem, the publicly available thematic products, which can include noisy labels, can be used to annotate RS images with zero-labeling cost. However, multi-label noise (which can be associated with wrong and missing label annotations) can distort the learning process of the MLC algorithm. The detection and correction of label noise are challenging tasks, especially in a multi-label scenario, where each image can be associated with more than one label. To address this problem, we propose a novel noise robust collaborative multi-label learning (RCML) method to alleviate the adverse effects of multi-label noise during the training phase of the CNN model. RCML identifies, ranks and excludes noisy multi-labels in RS images based on three main modules: 1) discrepancy module; 2) group lasso module; and 3) swap module. The discrepancy module ensures that the two networks learn diverse features, while producing the same predictions. The task of the group lasso module is to detect the potentially noisy labels assigned to the multi-labeled training images, while the swap module task is devoted to exchanging the ranking information between two networks. Unlike existing methods that make assumptions about the noise distribution, our proposed RCML does not make any prior assumption about the type of noise in the training set. Our code is publicly available online: this http URL" @default.
- W3217368032 created "2021-12-06" @default.
- W3217368032 creator A5020394413 @default.
- W3217368032 creator A5087126293 @default.
- W3217368032 creator A5088068842 @default.
- W3217368032 date "2021-12-02" @default.
- W3217368032 modified "2023-10-01" @default.
- W3217368032 title "Multi-Label Noise Robust Collaborative Learning Model for Remote Sensing Image Classification." @default.
- W3217368032 cites W112296118 @default.
- W3217368032 cites W1598493270 @default.
- W3217368032 cites W1861492603 @default.
- W3217368032 cites W1866072925 @default.
- W3217368032 cites W1980038761 @default.
- W3217368032 cites W2019899889 @default.
- W3217368032 cites W2048679005 @default.
- W3217368032 cites W2086234878 @default.
- W3217368032 cites W2100233488 @default.
- W3217368032 cites W2108598243 @default.
- W3217368032 cites W2138019504 @default.
- W3217368032 cites W2167460663 @default.
- W3217368032 cites W2194775991 @default.
- W3217368032 cites W2212660284 @default.
- W3217368032 cites W2302255633 @default.
- W3217368032 cites W2362855512 @default.
- W3217368032 cites W2602837914 @default.
- W3217368032 cites W2730167212 @default.
- W3217368032 cites W2752971446 @default.
- W3217368032 cites W2766938848 @default.
- W3217368032 cites W2801602507 @default.
- W3217368032 cites W2884821995 @default.
- W3217368032 cites W2901576309 @default.
- W3217368032 cites W2946885980 @default.
- W3217368032 cites W2963081269 @default.
- W3217368032 cites W2963334011 @default.
- W3217368032 cites W2963351448 @default.
- W3217368032 cites W2963371670 @default.
- W3217368032 cites W2963386594 @default.
- W3217368032 cites W2963460857 @default.
- W3217368032 cites W2963697299 @default.
- W3217368032 cites W2963735582 @default.
- W3217368032 cites W2963759070 @default.
- W3217368032 cites W2964292098 @default.
- W3217368032 cites W2967052791 @default.
- W3217368032 cites W2969238677 @default.
- W3217368032 cites W2969792713 @default.
- W3217368032 cites W2978625989 @default.
- W3217368032 cites W2986943971 @default.
- W3217368032 cites W3009525954 @default.
- W3217368032 cites W3024382584 @default.
- W3217368032 cites W3027532550 @default.
- W3217368032 cites W3036380739 @default.
- W3217368032 cites W3042609801 @default.
- W3217368032 cites W3095052591 @default.
- W3217368032 cites W3100593864 @default.
- W3217368032 cites W3130213261 @default.
- W3217368032 cites W3132186014 @default.
- W3217368032 cites W3137695714 @default.
- W3217368032 cites W3194167564 @default.
- W3217368032 cites W9014458 @default.
- W3217368032 hasPublicationYear "2021" @default.
- W3217368032 type Work @default.
- W3217368032 sameAs 3217368032 @default.
- W3217368032 citedByCount "0" @default.
- W3217368032 crossrefType "posted-content" @default.
- W3217368032 hasAuthorship W3217368032A5020394413 @default.
- W3217368032 hasAuthorship W3217368032A5087126293 @default.
- W3217368032 hasAuthorship W3217368032A5088068842 @default.
- W3217368032 hasConcept C10138342 @default.
- W3217368032 hasConcept C108583219 @default.
- W3217368032 hasConcept C115961682 @default.
- W3217368032 hasConcept C119857082 @default.
- W3217368032 hasConcept C124101348 @default.
- W3217368032 hasConcept C153180895 @default.
- W3217368032 hasConcept C154945302 @default.
- W3217368032 hasConcept C162324750 @default.
- W3217368032 hasConcept C187736073 @default.
- W3217368032 hasConcept C2776482837 @default.
- W3217368032 hasConcept C2777212361 @default.
- W3217368032 hasConcept C2780451532 @default.
- W3217368032 hasConcept C41008148 @default.
- W3217368032 hasConcept C81363708 @default.
- W3217368032 hasConcept C99498987 @default.
- W3217368032 hasConcept C99821215 @default.
- W3217368032 hasConceptScore W3217368032C10138342 @default.
- W3217368032 hasConceptScore W3217368032C108583219 @default.
- W3217368032 hasConceptScore W3217368032C115961682 @default.
- W3217368032 hasConceptScore W3217368032C119857082 @default.
- W3217368032 hasConceptScore W3217368032C124101348 @default.
- W3217368032 hasConceptScore W3217368032C153180895 @default.
- W3217368032 hasConceptScore W3217368032C154945302 @default.
- W3217368032 hasConceptScore W3217368032C162324750 @default.
- W3217368032 hasConceptScore W3217368032C187736073 @default.
- W3217368032 hasConceptScore W3217368032C2776482837 @default.
- W3217368032 hasConceptScore W3217368032C2777212361 @default.
- W3217368032 hasConceptScore W3217368032C2780451532 @default.
- W3217368032 hasConceptScore W3217368032C41008148 @default.
- W3217368032 hasConceptScore W3217368032C81363708 @default.
- W3217368032 hasConceptScore W3217368032C99498987 @default.
- W3217368032 hasConceptScore W3217368032C99821215 @default.
- W3217368032 hasLocation W32173680321 @default.