Matches in SemOpenAlex for { <https://semopenalex.org/work/W4387303314> ?p ?o ?g. }
Showing items 1 to 72 of
72
with 100 items per page.
- W4387303314 endingPage "13" @default.
- W4387303314 startingPage "1" @default.
- W4387303314 abstract "Nowadays, the developed deep neural networks (DNN) have been widely applied to synthetic aperture radar (SAR) image interpretation, such as target classification and recognition, which can automatically learn high-level semantic features in data-driven and task-driven manners. For the supervised learning methods, abundant labeled samples are required to avoid the over-fitting of designed networks, which is usually difficult for SAR image applications. To address these issues, a novel two-stage algorithm based on contrastive learning (CL) is proposed for SAR image target classification. In the pre-training stage, to extract self-supervised representations (SSRs) from an unlabeled train set, a convolutional neural network (CNN)-based encoder is first pre-trained using a contrasting strategy. This encoder can convert SAR images into a discriminative embedding space. Meanwhile, the optimal encoder can be determined using a linear evaluation protocol, which can indirectly confirm the transferability of pre-learned SSRs to downstream tasks. Therefore, in the fine-tuning stage, a SAR target classifier can be adequately trained using a few labeled SSRs in a supervised manner, which benefits from the powerful pre-trained encoder. Numerical experiments are carried out on the shared MSTAR dataset to demonstrate that the model based on the proposed self-supervised feature learning algorithm is superior to the conventional supervised methods under labeled data constraints. In addition, knowledge transfer experiments are also conducted on the openSARship dataset, showing that the encoder pre-trained from the MSTAR dataset can support the classifier training with high efficiency and precision. These results demonstrate the excellent training convergence and classification performance of the proposed algorithm." @default.
- W4387303314 created "2023-10-04" @default.
- W4387303314 creator A5021408538 @default.
- W4387303314 creator A5027178045 @default.
- W4387303314 creator A5033020983 @default.
- W4387303314 creator A5040591331 @default.
- W4387303314 creator A5087493208 @default.
- W4387303314 date "2023-01-01" @default.
- W4387303314 modified "2023-10-05" @default.
- W4387303314 title "Self-supervised Feature Representation for SAR Image Target Classification Using Contrastive Learning" @default.
- W4387303314 doi "https://doi.org/10.1109/jstars.2023.3321769" @default.
- W4387303314 hasPublicationYear "2023" @default.
- W4387303314 type Work @default.
- W4387303314 citedByCount "0" @default.
- W4387303314 crossrefType "journal-article" @default.
- W4387303314 hasAuthorship W4387303314A5021408538 @default.
- W4387303314 hasAuthorship W4387303314A5027178045 @default.
- W4387303314 hasAuthorship W4387303314A5033020983 @default.
- W4387303314 hasAuthorship W4387303314A5040591331 @default.
- W4387303314 hasAuthorship W4387303314A5087493208 @default.
- W4387303314 hasBestOaLocation W43873033141 @default.
- W4387303314 hasConcept C108583219 @default.
- W4387303314 hasConcept C111919701 @default.
- W4387303314 hasConcept C115961682 @default.
- W4387303314 hasConcept C118505674 @default.
- W4387303314 hasConcept C119857082 @default.
- W4387303314 hasConcept C150899416 @default.
- W4387303314 hasConcept C153180895 @default.
- W4387303314 hasConcept C154945302 @default.
- W4387303314 hasConcept C41008148 @default.
- W4387303314 hasConcept C59404180 @default.
- W4387303314 hasConcept C75294576 @default.
- W4387303314 hasConcept C81363708 @default.
- W4387303314 hasConcept C87360688 @default.
- W4387303314 hasConcept C95623464 @default.
- W4387303314 hasConcept C97931131 @default.
- W4387303314 hasConceptScore W4387303314C108583219 @default.
- W4387303314 hasConceptScore W4387303314C111919701 @default.
- W4387303314 hasConceptScore W4387303314C115961682 @default.
- W4387303314 hasConceptScore W4387303314C118505674 @default.
- W4387303314 hasConceptScore W4387303314C119857082 @default.
- W4387303314 hasConceptScore W4387303314C150899416 @default.
- W4387303314 hasConceptScore W4387303314C153180895 @default.
- W4387303314 hasConceptScore W4387303314C154945302 @default.
- W4387303314 hasConceptScore W4387303314C41008148 @default.
- W4387303314 hasConceptScore W4387303314C59404180 @default.
- W4387303314 hasConceptScore W4387303314C75294576 @default.
- W4387303314 hasConceptScore W4387303314C81363708 @default.
- W4387303314 hasConceptScore W4387303314C87360688 @default.
- W4387303314 hasConceptScore W4387303314C95623464 @default.
- W4387303314 hasConceptScore W4387303314C97931131 @default.
- W4387303314 hasFunder F4320321001 @default.
- W4387303314 hasFunder F4320322769 @default.
- W4387303314 hasFunder F4320335787 @default.
- W4387303314 hasLocation W43873033141 @default.
- W4387303314 hasOpenAccess W4387303314 @default.
- W4387303314 hasPrimaryLocation W43873033141 @default.
- W4387303314 hasRelatedWork W2905846897 @default.
- W4387303314 hasRelatedWork W2996856019 @default.
- W4387303314 hasRelatedWork W2998168123 @default.
- W4387303314 hasRelatedWork W3012393889 @default.
- W4387303314 hasRelatedWork W3018421652 @default.
- W4387303314 hasRelatedWork W3091976719 @default.
- W4387303314 hasRelatedWork W3192840557 @default.
- W4387303314 hasRelatedWork W4220996320 @default.
- W4387303314 hasRelatedWork W4287995534 @default.
- W4387303314 hasRelatedWork W4312200629 @default.
- W4387303314 isParatext "false" @default.
- W4387303314 isRetracted "false" @default.
- W4387303314 workType "article" @default.