Matches in SemOpenAlex for { <https://semopenalex.org/work/W3217775520> ?p ?o ?g. }
- W3217775520 endingPage "12148" @default.
- W3217775520 startingPage "12132" @default.
- W3217775520 abstract "Recently, the deep learning models have achieved great success in the recognition of inverse synthetic aperture radar (ISAR) images. However, most of the deep learning models fail to obtain satisfactory results under the condition of small samples due to the contradiction between the large parameter space of the deep learning models and the insufficient labeled samples of space target imaging by ISAR. In this paper, a method of meta-learner based stack- ing network (MSN) is proposed, which can realize the high- precision classification of space target by ISAR images under the condition of small sample. Innovatively, a rotation-invariant attention mechanism (RAM) module is added into Resnet50 network to magnify the difference of embedded features of target and background. Complementarily, the deep relationship between the features of fine-grained ISAR image is extracted by using graph convolutional network (GCN) and relation network (RN). Finally, an innovative adaptive weighted XGBoost algorithm is used to integrate the prediction results of the base learners. The main contributions of this paper include proposing a RAM module and using an innovative adaptive weighted XGBoost algorithm to realize ensemble learning. The experiment results show that the RAM module effectively concentrates the networks attention on the recognized target, and the recognition rate of MSN is about 5% higher than that of a single base learner under different data volume conditions, which proves that MSN achieves competitive accuracy against other state-of-the-art approaches." @default.
- W3217775520 created "2021-12-06" @default.
- W3217775520 creator A5019425672 @default.
- W3217775520 creator A5019602223 @default.
- W3217775520 creator A5038020087 @default.
- W3217775520 creator A5077104733 @default.
- W3217775520 creator A5091046811 @default.
- W3217775520 date "2021-01-01" @default.
- W3217775520 modified "2023-10-16" @default.
- W3217775520 title "Meta-Learner-Based Stacking Network on Space Target Recognition for ISAR Images" @default.
- W3217775520 cites W1501856433 @default.
- W3217775520 cites W1826695102 @default.
- W3217775520 cites W1989207420 @default.
- W3217775520 cites W2042847482 @default.
- W3217775520 cites W2046523124 @default.
- W3217775520 cites W2086422866 @default.
- W3217775520 cites W2099628041 @default.
- W3217775520 cites W2116341502 @default.
- W3217775520 cites W2117539524 @default.
- W3217775520 cites W2123461112 @default.
- W3217775520 cites W2126204609 @default.
- W3217775520 cites W2127952006 @default.
- W3217775520 cites W2139906443 @default.
- W3217775520 cites W2147394424 @default.
- W3217775520 cites W2149441458 @default.
- W3217775520 cites W2153513200 @default.
- W3217775520 cites W2166681504 @default.
- W3217775520 cites W2537146607 @default.
- W3217775520 cites W2544339223 @default.
- W3217775520 cites W2771180079 @default.
- W3217775520 cites W2774292910 @default.
- W3217775520 cites W2809195560 @default.
- W3217775520 cites W2894727785 @default.
- W3217775520 cites W2894982307 @default.
- W3217775520 cites W2895734781 @default.
- W3217775520 cites W2962858109 @default.
- W3217775520 cites W2963845150 @default.
- W3217775520 cites W2964105864 @default.
- W3217775520 cites W2979301925 @default.
- W3217775520 cites W3006022342 @default.
- W3217775520 cites W3015746332 @default.
- W3217775520 cites W3020063029 @default.
- W3217775520 cites W3102476541 @default.
- W3217775520 cites W4210257598 @default.
- W3217775520 doi "https://doi.org/10.1109/jstars.2021.3128938" @default.
- W3217775520 hasPublicationYear "2021" @default.
- W3217775520 type Work @default.
- W3217775520 sameAs 3217775520 @default.
- W3217775520 citedByCount "9" @default.
- W3217775520 countsByYear W32177755202022 @default.
- W3217775520 countsByYear W32177755202023 @default.
- W3217775520 crossrefType "journal-article" @default.
- W3217775520 hasAuthorship W3217775520A5019425672 @default.
- W3217775520 hasAuthorship W3217775520A5019602223 @default.
- W3217775520 hasAuthorship W3217775520A5038020087 @default.
- W3217775520 hasAuthorship W3217775520A5077104733 @default.
- W3217775520 hasAuthorship W3217775520A5091046811 @default.
- W3217775520 hasBestOaLocation W32177755201 @default.
- W3217775520 hasConcept C108583219 @default.
- W3217775520 hasConcept C109094680 @default.
- W3217775520 hasConcept C10929652 @default.
- W3217775520 hasConcept C127413603 @default.
- W3217775520 hasConcept C146978453 @default.
- W3217775520 hasConcept C153180895 @default.
- W3217775520 hasConcept C154945302 @default.
- W3217775520 hasConcept C187107819 @default.
- W3217775520 hasConcept C29829512 @default.
- W3217775520 hasConcept C41008148 @default.
- W3217775520 hasConcept C52622490 @default.
- W3217775520 hasConcept C554190296 @default.
- W3217775520 hasConcept C76155785 @default.
- W3217775520 hasConceptScore W3217775520C108583219 @default.
- W3217775520 hasConceptScore W3217775520C109094680 @default.
- W3217775520 hasConceptScore W3217775520C10929652 @default.
- W3217775520 hasConceptScore W3217775520C127413603 @default.
- W3217775520 hasConceptScore W3217775520C146978453 @default.
- W3217775520 hasConceptScore W3217775520C153180895 @default.
- W3217775520 hasConceptScore W3217775520C154945302 @default.
- W3217775520 hasConceptScore W3217775520C187107819 @default.
- W3217775520 hasConceptScore W3217775520C29829512 @default.
- W3217775520 hasConceptScore W3217775520C41008148 @default.
- W3217775520 hasConceptScore W3217775520C52622490 @default.
- W3217775520 hasConceptScore W3217775520C554190296 @default.
- W3217775520 hasConceptScore W3217775520C76155785 @default.
- W3217775520 hasFunder F4320321001 @default.
- W3217775520 hasLocation W32177755201 @default.
- W3217775520 hasLocation W32177755202 @default.
- W3217775520 hasOpenAccess W3217775520 @default.
- W3217775520 hasPrimaryLocation W32177755201 @default.
- W3217775520 hasRelatedWork W1964120219 @default.
- W3217775520 hasRelatedWork W2062264607 @default.
- W3217775520 hasRelatedWork W2115641108 @default.
- W3217775520 hasRelatedWork W2270280304 @default.
- W3217775520 hasRelatedWork W2312454952 @default.
- W3217775520 hasRelatedWork W2369744060 @default.
- W3217775520 hasRelatedWork W2399062725 @default.
- W3217775520 hasRelatedWork W2784759481 @default.
- W3217775520 hasRelatedWork W2806588494 @default.