FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4308703323> ?p ?o ?g. }

• W4308703323 endingPage "5675" @default.
• W4308703323 startingPage "5675" @default.
• W4308703323 abstract "Currently, under supervised learning, a model pre-trained by a large-scale nature scene dataset and then fine-tuned on a few specific task labeling data is the paradigm that has dominated knowledge transfer learning. Unfortunately, due to different categories of imaging data and stiff challenges of data annotation, there is not a large enough and uniform remote sensing dataset to support large-scale pre-training in the remote sensing domain (RSD). Moreover, pre-training models on large-scale nature scene datasets by supervised learning and then directly fine-tuning on diverse downstream tasks seems to be a crude method, which is easily affected by inevitable incorrect labeling, severe domain gaps and task-aware discrepancies. Thus, in this paper, considering the self-supervised pre-training and powerful vision transformer (ViT) architecture, a concise and effective knowledge transfer learning strategy called ConSecutive Pre-Training (CSPT) is proposed based on the idea of not stopping pre-training in natural language processing (NLP), which can gradually bridge the domain gap and transfer large-scale data knowledge to any specific domain (e.g., from nature scene domain to RSD) In addition, the proposed CSPT also can release the huge potential of unlabeled data for task-aware model training. Finally, extensive experiments were carried out on twelve remote sensing datasets involving three types of downstream tasks (e.g., scene classification, object detection and land cover classification) and two types of imaging data (e.g., optical and synthetic aperture radar (SAR)). The results show that by utilizing the proposed CSPT for task-aware model training, almost all downstream tasks in the RSD can outperform the previous knowledge transfer learning strategies based on model pre-training without any expensive manually labeling and even surpass the state-of-the-art (SOTA) performance without any careful network architecture designing." @default.
• W4308703323 created "2022-11-14" @default.
• W4308703323 creator A5006719409 @default.
• W4308703323 creator A5012371005 @default.
• W4308703323 creator A5023179941 @default.
• W4308703323 creator A5037709424 @default.
• W4308703323 creator A5054059229 @default.
• W4308703323 creator A5059679943 @default.
• W4308703323 creator A5085917066 @default.
• W4308703323 date "2022-11-10" @default.
• W4308703323 modified "2023-10-10" @default.
• W4308703323 title "Consecutive Pre-Training: A Knowledge Transfer Learning Strategy with Relevant Unlabeled Data for Remote Sensing Domain" @default.
• W4308703323 cites W1491152520 @default.
• W4308703323 cites W1525224174 @default.
• W4308703323 cites W1861492603 @default.
• W4308703323 cites W2005368619 @default.
• W4308703323 cites W2037227137 @default.
• W4308703323 cites W2097117768 @default.
• W4308703323 cites W2117539524 @default.
• W4308703323 cites W2194775991 @default.
• W4308703323 cites W2549139847 @default.
• W4308703323 cites W2594177559 @default.
• W4308703323 cites W2618530766 @default.
• W4308703323 cites W2732026016 @default.
• W4308703323 cites W2774244034 @default.
• W4308703323 cites W2778539913 @default.
• W4308703323 cites W2787630273 @default.
• W4308703323 cites W2794377509 @default.
• W4308703323 cites W2914928371 @default.
• W4308703323 cites W2962749812 @default.
• W4308703323 cites W2963150697 @default.
• W4308703323 cites W2963857746 @default.
• W4308703323 cites W2982220924 @default.
• W4308703323 cites W2991488782 @default.
• W4308703323 cites W2992240579 @default.
• W4308703323 cites W3017622525 @default.
• W4308703323 cites W3034238904 @default.
• W4308703323 cites W3035524453 @default.
• W4308703323 cites W3038948729 @default.
• W4308703323 cites W3043257208 @default.
• W4308703323 cites W3047889186 @default.
• W4308703323 cites W3101627915 @default.
• W4308703323 cites W3103856189 @default.
• W4308703323 cites W3105577662 @default.
• W4308703323 cites W3114606989 @default.
• W4308703323 cites W3127010634 @default.
• W4308703323 cites W3136987292 @default.
• W4308703323 cites W3138516171 @default.
• W4308703323 cites W3139236157 @default.
• W4308703323 cites W3144483443 @default.
• W4308703323 cites W3145450063 @default.
• W4308703323 cites W3175184835 @default.
• W4308703323 cites W3176276772 @default.
• W4308703323 cites W3196798006 @default.
• W4308703323 cites W3199365085 @default.
• W4308703323 cites W3207924272 @default.
• W4308703323 cites W3207962952 @default.
• W4308703323 cites W3213288046 @default.
• W4308703323 cites W4214644404 @default.
• W4308703323 cites W4221015298 @default.
• W4308703323 cites W4226359564 @default.
• W4308703323 cites W4285605548 @default.
• W4308703323 cites W4312309864 @default.
• W4308703323 cites W4312513332 @default.
• W4308703323 cites W4312795296 @default.
• W4308703323 cites W4312804044 @default.
• W4308703323 cites W4312904550 @default.
• W4308703323 cites W4313056800 @default.
• W4308703323 cites W4313156423 @default.
• W4308703323 cites W4315705623 @default.
• W4308703323 cites W639708223 @default.
• W4308703323 doi "https://doi.org/10.3390/rs14225675" @default.
• W4308703323 hasPublicationYear "2022" @default.
• W4308703323 type Work @default.
• W4308703323 citedByCount "5" @default.
• W4308703323 countsByYear W43087033232023 @default.
• W4308703323 crossrefType "journal-article" @default.
• W4308703323 hasAuthorship W4308703323A5006719409 @default.
• W4308703323 hasAuthorship W4308703323A5012371005 @default.
• W4308703323 hasAuthorship W4308703323A5023179941 @default.
• W4308703323 hasAuthorship W4308703323A5037709424 @default.
• W4308703323 hasAuthorship W4308703323A5054059229 @default.
• W4308703323 hasAuthorship W4308703323A5059679943 @default.
• W4308703323 hasAuthorship W4308703323A5085917066 @default.
• W4308703323 hasBestOaLocation W43087033231 @default.
• W4308703323 hasConcept C119857082 @default.
• W4308703323 hasConcept C121332964 @default.
• W4308703323 hasConcept C134306372 @default.
• W4308703323 hasConcept C150899416 @default.
• W4308703323 hasConcept C153180895 @default.
• W4308703323 hasConcept C154945302 @default.
• W4308703323 hasConcept C162324750 @default.
• W4308703323 hasConcept C187736073 @default.
• W4308703323 hasConcept C207685749 @default.
• W4308703323 hasConcept C2776145971 @default.
• W4308703323 hasConcept C2776321320 @default.
• W4308703323 hasConcept C2776960227 @default.
• W4308703323 hasConcept C2778755073 @default.

• next