Matches in SemOpenAlex for { <https://semopenalex.org/work/W4367031609> ?p ?o ?g. }
- W4367031609 endingPage "4498" @default.
- W4367031609 startingPage "4484" @default.
- W4367031609 abstract "As deep learning attracts earth observation (EO) community's interest, the challenge to derive explainable, actionable information creates a bottleneck in EO models' development. Computer vision proved that effective results of the DL algorithms imply a considerable amount of training datasets. This is not the case in EO, where images are characterized by a broad variety of sensor data, ranging from multispectral to Synthetic Aperture Radar (SAR) with variable number of spectral bands, polarization, or spatial resolution. In this article, we present effective methodologies for fast training with reduced datasets of simple deep neural networks, while preserving the similar performance of state-of-the-art methods. The hybrid solutions we provide imply the reduction of input data dimension in a convolutional neural network. We replaced dataset's patches with histograms of pixel intensity, Bag-of-Words, or downsampled images. Following the proposed approaches, the training time and the dataset size are significantly reduced, while the performance of classification is preserved. These optimized implementations enable the deployment of lightweight deep learning models for real-time processing tasks able to exhibit accurate results, for instance, a disaster management scenario. We demonstrated the computational efficiency of these approaches on various, complex data, both multispectral and SAR, with different resolutions." @default.
- W4367031609 created "2023-04-27" @default.
- W4367031609 creator A5032370631 @default.
- W4367031609 creator A5064251688 @default.
- W4367031609 creator A5075098303 @default.
- W4367031609 date "2023-01-01" @default.
- W4367031609 modified "2023-10-18" @default.
- W4367031609 title "Dimensionality Reduction of Deep Learning for Earth Observation: Smaller, Faster, Simpler" @default.
- W4367031609 cites W1536680647 @default.
- W4367031609 cites W1843514792 @default.
- W4367031609 cites W1980038761 @default.
- W4367031609 cites W2009049007 @default.
- W4367031609 cites W2085669305 @default.
- W4367031609 cites W2090424610 @default.
- W4367031609 cites W2151039611 @default.
- W4367031609 cites W2248723555 @default.
- W4367031609 cites W2412588858 @default.
- W4367031609 cites W2604645045 @default.
- W4367031609 cites W2617536493 @default.
- W4367031609 cites W2626107033 @default.
- W4367031609 cites W2786055572 @default.
- W4367031609 cites W2791011783 @default.
- W4367031609 cites W2799544692 @default.
- W4367031609 cites W2804532080 @default.
- W4367031609 cites W2809328744 @default.
- W4367031609 cites W2901458284 @default.
- W4367031609 cites W2901791811 @default.
- W4367031609 cites W2904445802 @default.
- W4367031609 cites W2909678128 @default.
- W4367031609 cites W2942231644 @default.
- W4367031609 cites W2944512710 @default.
- W4367031609 cites W2963066447 @default.
- W4367031609 cites W2986943971 @default.
- W4367031609 cites W2990641522 @default.
- W4367031609 cites W2998270553 @default.
- W4367031609 cites W3000436394 @default.
- W4367031609 cites W3001606623 @default.
- W4367031609 cites W3010290582 @default.
- W4367031609 cites W3012326541 @default.
- W4367031609 cites W3022086662 @default.
- W4367031609 cites W3022140654 @default.
- W4367031609 cites W3034251466 @default.
- W4367031609 cites W3047443805 @default.
- W4367031609 cites W3080181119 @default.
- W4367031609 cites W3091542555 @default.
- W4367031609 cites W3100011500 @default.
- W4367031609 cites W3110832721 @default.
- W4367031609 cites W3130418180 @default.
- W4367031609 cites W3204719315 @default.
- W4367031609 cites W4313180686 @default.
- W4367031609 doi "https://doi.org/10.1109/jstars.2023.3270384" @default.
- W4367031609 hasPublicationYear "2023" @default.
- W4367031609 type Work @default.
- W4367031609 citedByCount "0" @default.
- W4367031609 crossrefType "journal-article" @default.
- W4367031609 hasAuthorship W4367031609A5032370631 @default.
- W4367031609 hasAuthorship W4367031609A5064251688 @default.
- W4367031609 hasAuthorship W4367031609A5075098303 @default.
- W4367031609 hasBestOaLocation W43670316091 @default.
- W4367031609 hasConcept C108583219 @default.
- W4367031609 hasConcept C111335779 @default.
- W4367031609 hasConcept C119857082 @default.
- W4367031609 hasConcept C124101348 @default.
- W4367031609 hasConcept C127413603 @default.
- W4367031609 hasConcept C146978453 @default.
- W4367031609 hasConcept C149635348 @default.
- W4367031609 hasConcept C153180895 @default.
- W4367031609 hasConcept C154945302 @default.
- W4367031609 hasConcept C160633673 @default.
- W4367031609 hasConcept C173163844 @default.
- W4367031609 hasConcept C19269812 @default.
- W4367031609 hasConcept C2524010 @default.
- W4367031609 hasConcept C2780513914 @default.
- W4367031609 hasConcept C33923547 @default.
- W4367031609 hasConcept C39399123 @default.
- W4367031609 hasConcept C41008148 @default.
- W4367031609 hasConcept C46686674 @default.
- W4367031609 hasConcept C50644808 @default.
- W4367031609 hasConcept C70518039 @default.
- W4367031609 hasConcept C81363708 @default.
- W4367031609 hasConcept C87360688 @default.
- W4367031609 hasConceptScore W4367031609C108583219 @default.
- W4367031609 hasConceptScore W4367031609C111335779 @default.
- W4367031609 hasConceptScore W4367031609C119857082 @default.
- W4367031609 hasConceptScore W4367031609C124101348 @default.
- W4367031609 hasConceptScore W4367031609C127413603 @default.
- W4367031609 hasConceptScore W4367031609C146978453 @default.
- W4367031609 hasConceptScore W4367031609C149635348 @default.
- W4367031609 hasConceptScore W4367031609C153180895 @default.
- W4367031609 hasConceptScore W4367031609C154945302 @default.
- W4367031609 hasConceptScore W4367031609C160633673 @default.
- W4367031609 hasConceptScore W4367031609C173163844 @default.
- W4367031609 hasConceptScore W4367031609C19269812 @default.
- W4367031609 hasConceptScore W4367031609C2524010 @default.
- W4367031609 hasConceptScore W4367031609C2780513914 @default.
- W4367031609 hasConceptScore W4367031609C33923547 @default.
- W4367031609 hasConceptScore W4367031609C39399123 @default.
- W4367031609 hasConceptScore W4367031609C41008148 @default.