Matches in SemOpenAlex for { <https://semopenalex.org/work/W3168553612> ?p ?o ?g. }
Showing items 1 to 93 of
93
with 100 items per page.
- W3168553612 endingPage "6385" @default.
- W3168553612 startingPage "6372" @default.
- W3168553612 abstract "Recent years have witnessed great progress in synthetic aperture radar (SAR) target detection methods based on deep learning. However, these methods generally assume the training data and test data obey the same distribution, which does not always hold when the radar parameters, imaging algorithm, viewpoints, scenes, etc., change in practice. When such a distribution mismatch occurs, it will cause a significant performance drop. Domain adaptation methods provide an effective way to address this problem by transferring knowledge from the source domain (training data) to the target domain (test data). In this article, we proposed an unsupervised faster R-CNN SAR target detection framework based on domain adaptation, which can improve SAR target detection performance in the unlabeled target domain by borrowing the knowledge of the labeled source domain. Our approach is composed of the following three stages: pixel-domain adaptation (PDA), multilevel feature domain adaptation (MFDA), and iterative pseudolabeling (IPL). By generating transition domain using generative adversarial networks, the PDA stage can reduce the appearance differences of SAR images. At the MFDA stage, the detector can not only learn the domain-invariant global features and instance-level regional features via multilevel adversarial learning in the common feature space but also reweight the low-level global features according to their relative importance to the target domain. At the IPL stage, we design an iterative pseudo labeling strategy that can select pseudo-labels on instance level and image level to encourage the detector to learn more discriminative features of the target domain directly. We evaluate our method using miniSAR and FARADSAR datasets. The experimental results demonstrate the effectiveness of the proposed unsupervised domain adaptation target detection approach." @default.
- W3168553612 created "2021-06-22" @default.
- W3168553612 creator A5035519525 @default.
- W3168553612 creator A5035630827 @default.
- W3168553612 creator A5057461830 @default.
- W3168553612 date "2021-01-01" @default.
- W3168553612 modified "2023-10-05" @default.
- W3168553612 title "Unsupervised Domain Adaptation for SAR Target Detection" @default.
- W3168553612 cites W2073222764 @default.
- W3168553612 cites W2584009249 @default.
- W3168553612 cites W2593768305 @default.
- W3168553612 cites W2747165560 @default.
- W3168553612 cites W2774244034 @default.
- W3168553612 cites W2799646862 @default.
- W3168553612 cites W2892123021 @default.
- W3168553612 cites W2897902589 @default.
- W3168553612 cites W2962687275 @default.
- W3168553612 cites W2962793481 @default.
- W3168553612 cites W2962823940 @default.
- W3168553612 cites W2963858786 @default.
- W3168553612 cites W2964115968 @default.
- W3168553612 cites W2968634921 @default.
- W3168553612 cites W2969583814 @default.
- W3168553612 cites W2990641522 @default.
- W3168553612 cites W2990740643 @default.
- W3168553612 cites W2991277950 @default.
- W3168553612 cites W3018998681 @default.
- W3168553612 cites W3035175896 @default.
- W3168553612 cites W639708223 @default.
- W3168553612 doi "https://doi.org/10.1109/jstars.2021.3089238" @default.
- W3168553612 hasPublicationYear "2021" @default.
- W3168553612 type Work @default.
- W3168553612 sameAs 3168553612 @default.
- W3168553612 citedByCount "17" @default.
- W3168553612 countsByYear W31685536122022 @default.
- W3168553612 countsByYear W31685536122023 @default.
- W3168553612 crossrefType "journal-article" @default.
- W3168553612 hasAuthorship W3168553612A5035519525 @default.
- W3168553612 hasAuthorship W3168553612A5035630827 @default.
- W3168553612 hasAuthorship W3168553612A5057461830 @default.
- W3168553612 hasBestOaLocation W31685536121 @default.
- W3168553612 hasConcept C134306372 @default.
- W3168553612 hasConcept C138885662 @default.
- W3168553612 hasConcept C153180895 @default.
- W3168553612 hasConcept C154945302 @default.
- W3168553612 hasConcept C16910744 @default.
- W3168553612 hasConcept C199360897 @default.
- W3168553612 hasConcept C2776151529 @default.
- W3168553612 hasConcept C2776401178 @default.
- W3168553612 hasConcept C31972630 @default.
- W3168553612 hasConcept C33923547 @default.
- W3168553612 hasConcept C36503486 @default.
- W3168553612 hasConcept C41008148 @default.
- W3168553612 hasConcept C41895202 @default.
- W3168553612 hasConcept C87360688 @default.
- W3168553612 hasConcept C97931131 @default.
- W3168553612 hasConceptScore W3168553612C134306372 @default.
- W3168553612 hasConceptScore W3168553612C138885662 @default.
- W3168553612 hasConceptScore W3168553612C153180895 @default.
- W3168553612 hasConceptScore W3168553612C154945302 @default.
- W3168553612 hasConceptScore W3168553612C16910744 @default.
- W3168553612 hasConceptScore W3168553612C199360897 @default.
- W3168553612 hasConceptScore W3168553612C2776151529 @default.
- W3168553612 hasConceptScore W3168553612C2776401178 @default.
- W3168553612 hasConceptScore W3168553612C31972630 @default.
- W3168553612 hasConceptScore W3168553612C33923547 @default.
- W3168553612 hasConceptScore W3168553612C36503486 @default.
- W3168553612 hasConceptScore W3168553612C41008148 @default.
- W3168553612 hasConceptScore W3168553612C41895202 @default.
- W3168553612 hasConceptScore W3168553612C87360688 @default.
- W3168553612 hasConceptScore W3168553612C97931131 @default.
- W3168553612 hasFunder F4320321001 @default.
- W3168553612 hasFunder F4320327912 @default.
- W3168553612 hasLocation W31685536121 @default.
- W3168553612 hasOpenAccess W3168553612 @default.
- W3168553612 hasPrimaryLocation W31685536121 @default.
- W3168553612 hasRelatedWork W2024160000 @default.
- W3168553612 hasRelatedWork W2061273563 @default.
- W3168553612 hasRelatedWork W2285052147 @default.
- W3168553612 hasRelatedWork W2729514902 @default.
- W3168553612 hasRelatedWork W2743258233 @default.
- W3168553612 hasRelatedWork W2773500201 @default.
- W3168553612 hasRelatedWork W2970216048 @default.
- W3168553612 hasRelatedWork W2998168123 @default.
- W3168553612 hasRelatedWork W4287995534 @default.
- W3168553612 hasRelatedWork W2073139667 @default.
- W3168553612 hasVolume "14" @default.
- W3168553612 isParatext "false" @default.
- W3168553612 isRetracted "false" @default.
- W3168553612 magId "3168553612" @default.
- W3168553612 workType "article" @default.