FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3194133609> ?p ?o ?g. }

• W3194133609 endingPage "17" @default.
• W3194133609 startingPage "1" @default.
• W3194133609 abstract "With the proposal of neural architecture search (NAS), automated network architecture design gradually becomes a new way in deep learning research. Due to its high capability regarding automated design, some pioneers have made an attempt to apply NAS in remote sensing and made some achievements, like 1-D/3-D Auto-convolutional neural network (CNN) and polarimetric synthetic aperture radar (PolSAR)-tailored Differentiable Architecture Search (PDAS). However, there are still some areas to be improved for existing NAS in remote-sensing field. In this article, we propose a random topology and random multiscale mapping (RTRMM) method to generate a multiscale and lightweight architecture for remote-sensing image recognition. First, a random topology generator generates the topology through random graph. Second, during the experiment, we find remote-sensing image features extracted by a multiscale network are more appropriate, compared with features extracted by a single-scale model. Nevertheless, the complexity inevitably increases with the introduction of a multiscale concept. Consequently, we design a variable search space consisting of decomposition convolution units under the guidance of mathematical analysis. The mapping of each neuron is then determined by a random multiscale mapping sampler. After that, we assemble the topology and mappings into blocks and construct three RTRMM models. Experiments on four scene classification datasets confirm the feature extraction capability and lightweight performance of RTRMM models. Moreover, we also observe that our approach achieves a better tradeoff between floating-point operations (FLOPs) and accuracy than some current well-behaved methods. Furthermore, the results on Vaihingen dataset verify the high feature-transfer capability." @default.
• W3194133609 created "2021-08-30" @default.
• W3194133609 creator A5002059265 @default.
• W3194133609 creator A5002110023 @default.
• W3194133609 creator A5005905514 @default.
• W3194133609 creator A5039791219 @default.
• W3194133609 creator A5055032051 @default.
• W3194133609 creator A5083406305 @default.
• W3194133609 date "2022-01-01" @default.
• W3194133609 modified "2023-10-01" @default.
• W3194133609 title "Random Topology and Random Multiscale Mapping: An Automated Design of Multiscale and Lightweight Neural Network for Remote-Sensing Image Recognition" @default.
• W3194133609 cites W1498436455 @default.
• W3194133609 cites W1526295910 @default.
• W3194133609 cites W1566135517 @default.
• W3194133609 cites W1677182931 @default.
• W3194133609 cites W1903029394 @default.
• W3194133609 cites W1912954554 @default.
• W3194133609 cites W1966342871 @default.
• W3194133609 cites W1973644502 @default.
• W3194133609 cites W1979426401 @default.
• W3194133609 cites W1980038761 @default.
• W3194133609 cites W1980287119 @default.
• W3194133609 cites W1999653836 @default.
• W3194133609 cites W2090411045 @default.
• W3194133609 cites W2097117768 @default.
• W3194133609 cites W2108598243 @default.
• W3194133609 cites W2112090702 @default.
• W3194133609 cites W2124637492 @default.
• W3194133609 cites W2124659975 @default.
• W3194133609 cites W2166148649 @default.
• W3194133609 cites W2194775991 @default.
• W3194133609 cites W2253590344 @default.
• W3194133609 cites W2283168383 @default.
• W3194133609 cites W2294802479 @default.
• W3194133609 cites W2347115704 @default.
• W3194133609 cites W2531409750 @default.
• W3194133609 cites W2560023338 @default.
• W3194133609 cites W2565639579 @default.
• W3194133609 cites W2778539913 @default.
• W3194133609 cites W2921708311 @default.
• W3194133609 cites W2925148117 @default.
• W3194133609 cites W2943270518 @default.
• W3194133609 cites W2955051405 @default.
• W3194133609 cites W2963037989 @default.
• W3194133609 cites W2963163009 @default.
• W3194133609 cites W2963378109 @default.
• W3194133609 cites W2963446712 @default.
• W3194133609 cites W2963821229 @default.
• W3194133609 cites W2963918968 @default.
• W3194133609 cites W2964081807 @default.
• W3194133609 cites W2965658867 @default.
• W3194133609 cites W2981748264 @default.
• W3194133609 cites W2981985696 @default.
• W3194133609 cites W2995801068 @default.
• W3194133609 cites W3004492228 @default.
• W3194133609 cites W3012028708 @default.
• W3194133609 cites W3025346498 @default.
• W3194133609 cites W3034202788 @default.
• W3194133609 cites W3036981345 @default.
• W3194133609 cites W3047053653 @default.
• W3194133609 cites W3047443805 @default.
• W3194133609 cites W3048631361 @default.
• W3194133609 cites W3102850314 @default.
• W3194133609 cites W3103856189 @default.
• W3194133609 cites W3105127913 @default.
• W3194133609 cites W3105577662 @default.
• W3194133609 cites W3122774149 @default.
• W3194133609 cites W3164443777 @default.
• W3194133609 cites W3208493772 @default.
• W3194133609 cites W4211091012 @default.
• W3194133609 doi "https://doi.org/10.1109/tgrs.2021.3102988" @default.
• W3194133609 hasPublicationYear "2022" @default.
• W3194133609 type Work @default.
• W3194133609 sameAs 3194133609 @default.
• W3194133609 citedByCount "4" @default.
• W3194133609 countsByYear W31941336092021 @default.
• W3194133609 countsByYear W31941336092022 @default.
• W3194133609 crossrefType "journal-article" @default.
• W3194133609 hasAuthorship W3194133609A5002059265 @default.
• W3194133609 hasAuthorship W3194133609A5002110023 @default.
• W3194133609 hasAuthorship W3194133609A5005905514 @default.
• W3194133609 hasAuthorship W3194133609A5039791219 @default.
• W3194133609 hasAuthorship W3194133609A5055032051 @default.
• W3194133609 hasAuthorship W3194133609A5083406305 @default.
• W3194133609 hasConcept C111919701 @default.
• W3194133609 hasConcept C11413529 @default.
• W3194133609 hasConcept C114614502 @default.
• W3194133609 hasConcept C115961682 @default.
• W3194133609 hasConcept C138885662 @default.
• W3194133609 hasConcept C153180895 @default.
• W3194133609 hasConcept C154945302 @default.
• W3194133609 hasConcept C184720557 @default.
• W3194133609 hasConcept C199845137 @default.
• W3194133609 hasConcept C2776401178 @default.
• W3194133609 hasConcept C33923547 @default.
• W3194133609 hasConcept C41008148 @default.
• W3194133609 hasConcept C41895202 @default.
• W3194133609 hasConcept C50644808 @default.

• next