Matches in SemOpenAlex for { <https://semopenalex.org/work/W3204282910> ?p ?o ?g. }
- W3204282910 endingPage "3864" @default.
- W3204282910 startingPage "3864" @default.
- W3204282910 abstract "Although automatic target recognition (ATR) models based on data-driven algorithms have achieved excellent performance in recent years, the synthetic aperture radar (SAR) ATR model often suffered from performance degradation when it encountered a small sample set. In this paper, an integrated counterfactual sample generation and filtering approach is proposed to alleviate the negative influence of a small sample set. The proposed method consists of a generation component and a filtering component. First, the proposed generation component utilizes the overfitting characteristics of generative adversarial networks (GANs), which ensures the generation of counterfactual target samples. Second, the proposed filtering component is built by learning different recognition functions. In the proposed filtering component, multiple SVMs trained by different SAR target sample sets provide pseudo-labels to the other SVMs to improve the recognition rate. Then, the proposed approach improves the performance of the recognition model dynamically while it continuously generates counterfactual target samples. At the same time, counterfactual target samples that are beneficial to the ATR model are also filtered. Moreover, ablation experiments demonstrate the effectiveness of the various components of the proposed method. Experimental results based on the Moving and Stationary Target Acquisition and Recognition (MSTAR) and OpenSARship dataset also show the advantages of the proposed approach. Even though the size of the constructed training set was 14.5% of the original training set, the recognition performance of the ATR model reached 91.27% with the proposed approach." @default.
- W3204282910 created "2021-10-11" @default.
- W3204282910 creator A5019411747 @default.
- W3204282910 creator A5030290401 @default.
- W3204282910 creator A5054459491 @default.
- W3204282910 creator A5061245960 @default.
- W3204282910 creator A5073006428 @default.
- W3204282910 date "2021-09-27" @default.
- W3204282910 modified "2023-10-07" @default.
- W3204282910 title "An Integrated Counterfactual Sample Generation and Filtering Approach for SAR Automatic Target Recognition with a Small Sample Set" @default.
- W3204282910 cites W2033753253 @default.
- W3204282910 cites W2038591350 @default.
- W3204282910 cites W2102544846 @default.
- W3204282910 cites W2111703458 @default.
- W3204282910 cites W2124648367 @default.
- W3204282910 cites W2138287042 @default.
- W3204282910 cites W2148791593 @default.
- W3204282910 cites W2253429366 @default.
- W3204282910 cites W2563202971 @default.
- W3204282910 cites W2585635281 @default.
- W3204282910 cites W2614504311 @default.
- W3204282910 cites W2730249686 @default.
- W3204282910 cites W2752788177 @default.
- W3204282910 cites W2762294195 @default.
- W3204282910 cites W2772879006 @default.
- W3204282910 cites W2773828237 @default.
- W3204282910 cites W2782415368 @default.
- W3204282910 cites W2803405656 @default.
- W3204282910 cites W2806263990 @default.
- W3204282910 cites W2898047322 @default.
- W3204282910 cites W2931068004 @default.
- W3204282910 cites W2942919589 @default.
- W3204282910 cites W2944556810 @default.
- W3204282910 cites W2956051753 @default.
- W3204282910 cites W2963047498 @default.
- W3204282910 cites W2963885538 @default.
- W3204282910 cites W2970503027 @default.
- W3204282910 cites W2997085028 @default.
- W3204282910 cites W2999592897 @default.
- W3204282910 doi "https://doi.org/10.3390/rs13193864" @default.
- W3204282910 hasPublicationYear "2021" @default.
- W3204282910 type Work @default.
- W3204282910 sameAs 3204282910 @default.
- W3204282910 citedByCount "4" @default.
- W3204282910 countsByYear W32042829102022 @default.
- W3204282910 countsByYear W32042829102023 @default.
- W3204282910 crossrefType "journal-article" @default.
- W3204282910 hasAuthorship W3204282910A5019411747 @default.
- W3204282910 hasAuthorship W3204282910A5030290401 @default.
- W3204282910 hasAuthorship W3204282910A5054459491 @default.
- W3204282910 hasAuthorship W3204282910A5061245960 @default.
- W3204282910 hasAuthorship W3204282910A5073006428 @default.
- W3204282910 hasBestOaLocation W32042829101 @default.
- W3204282910 hasConcept C108650721 @default.
- W3204282910 hasConcept C111472728 @default.
- W3204282910 hasConcept C117623542 @default.
- W3204282910 hasConcept C119857082 @default.
- W3204282910 hasConcept C121332964 @default.
- W3204282910 hasConcept C12267149 @default.
- W3204282910 hasConcept C138885662 @default.
- W3204282910 hasConcept C153180895 @default.
- W3204282910 hasConcept C154945302 @default.
- W3204282910 hasConcept C168167062 @default.
- W3204282910 hasConcept C177264268 @default.
- W3204282910 hasConcept C185592680 @default.
- W3204282910 hasConcept C198531522 @default.
- W3204282910 hasConcept C199360897 @default.
- W3204282910 hasConcept C22019652 @default.
- W3204282910 hasConcept C2779726219 @default.
- W3204282910 hasConcept C41008148 @default.
- W3204282910 hasConcept C43617362 @default.
- W3204282910 hasConcept C50644808 @default.
- W3204282910 hasConcept C87360688 @default.
- W3204282910 hasConcept C97355855 @default.
- W3204282910 hasConceptScore W3204282910C108650721 @default.
- W3204282910 hasConceptScore W3204282910C111472728 @default.
- W3204282910 hasConceptScore W3204282910C117623542 @default.
- W3204282910 hasConceptScore W3204282910C119857082 @default.
- W3204282910 hasConceptScore W3204282910C121332964 @default.
- W3204282910 hasConceptScore W3204282910C12267149 @default.
- W3204282910 hasConceptScore W3204282910C138885662 @default.
- W3204282910 hasConceptScore W3204282910C153180895 @default.
- W3204282910 hasConceptScore W3204282910C154945302 @default.
- W3204282910 hasConceptScore W3204282910C168167062 @default.
- W3204282910 hasConceptScore W3204282910C177264268 @default.
- W3204282910 hasConceptScore W3204282910C185592680 @default.
- W3204282910 hasConceptScore W3204282910C198531522 @default.
- W3204282910 hasConceptScore W3204282910C199360897 @default.
- W3204282910 hasConceptScore W3204282910C22019652 @default.
- W3204282910 hasConceptScore W3204282910C2779726219 @default.
- W3204282910 hasConceptScore W3204282910C41008148 @default.
- W3204282910 hasConceptScore W3204282910C43617362 @default.
- W3204282910 hasConceptScore W3204282910C50644808 @default.
- W3204282910 hasConceptScore W3204282910C87360688 @default.
- W3204282910 hasConceptScore W3204282910C97355855 @default.
- W3204282910 hasFunder F4320321001 @default.
- W3204282910 hasFunder F4320330207 @default.
- W3204282910 hasIssue "19" @default.