Matches in SemOpenAlex for { <https://semopenalex.org/work/W4285223668> ?p ?o ?g. }
- W4285223668 endingPage "14" @default.
- W4285223668 startingPage "1" @default.
- W4285223668 abstract "Owing to the powerful and automatic representation capabilities, deep learning (DL) techniques have made significant breakthroughs and progress in hyperspectral unmixing (HU). Among the DL approaches, autoencoders (AEs) have become a widely-used and promising network architecture. However, these AE-based methods heavily rely on manual design and may not be a good fit for specific datasets. To unmix hyperspectral images more intelligently, we propose an automatic neural architecture search model for HU, AutoNAS for short, to determine the optimal network architecture by considering channel configurations and convolution kernels simultaneously. In AutoNAS, the self-supervised training mechanism based on hyperspectral images is first designed for generating the training samples of the supernet. Then, the affine parameter sharing strategy is adopted by applying different affine transformations on the supernet weights in the training phase, which enables finding the optimal channel configuration. Furthermore, on the basis of the obtained channel configuration, the evolutionary algorithm with additional computational constraints is introduced into networks to achieve flexible convolution kernel search by evaluating unmixing results of different architectures in the supernet. Extensive experiments conducted on four hyperspectral datasets demonstrate the effectiveness and superiority of the proposed AutoNAS in comparison with several state-of-the-art unmixing algorithms." @default.
- W4285223668 created "2022-07-14" @default.
- W4285223668 creator A5023381631 @default.
- W4285223668 creator A5035508615 @default.
- W4285223668 creator A5064140321 @default.
- W4285223668 creator A5066378186 @default.
- W4285223668 creator A5075013625 @default.
- W4285223668 creator A5086253211 @default.
- W4285223668 date "2022-01-01" @default.
- W4285223668 modified "2023-10-10" @default.
- W4285223668 title "AutoNAS: Automatic Neural Architecture Search for Hyperspectral Unmixing" @default.
- W4285223668 cites W1957094454 @default.
- W4285223668 cites W1963659868 @default.
- W4285223668 cites W2009576740 @default.
- W4285223668 cites W2011315899 @default.
- W4285223668 cites W2024165284 @default.
- W4285223668 cites W2025090977 @default.
- W4285223668 cites W2032944446 @default.
- W4285223668 cites W2042626896 @default.
- W4285223668 cites W2070424424 @default.
- W4285223668 cites W2088259770 @default.
- W4285223668 cites W2119919858 @default.
- W4285223668 cites W2141494774 @default.
- W4285223668 cites W2143500192 @default.
- W4285223668 cites W2157321686 @default.
- W4285223668 cites W2163886442 @default.
- W4285223668 cites W2415341181 @default.
- W4285223668 cites W2418263100 @default.
- W4285223668 cites W2755091472 @default.
- W4285223668 cites W2765455392 @default.
- W4285223668 cites W2773706593 @default.
- W4285223668 cites W2774093485 @default.
- W4285223668 cites W2792897399 @default.
- W4285223668 cites W2808979303 @default.
- W4285223668 cites W2809306703 @default.
- W4285223668 cites W2886042776 @default.
- W4285223668 cites W2887697063 @default.
- W4285223668 cites W2894115892 @default.
- W4285223668 cites W2897962879 @default.
- W4285223668 cites W2902746003 @default.
- W4285223668 cites W2910655660 @default.
- W4285223668 cites W2921511952 @default.
- W4285223668 cites W2943270518 @default.
- W4285223668 cites W2952565170 @default.
- W4285223668 cites W2963371848 @default.
- W4285223668 cites W2977355106 @default.
- W4285223668 cites W3005148902 @default.
- W4285223668 cites W3010416187 @default.
- W4285223668 cites W3028000844 @default.
- W4285223668 cites W3034528892 @default.
- W4285223668 cites W3037215700 @default.
- W4285223668 cites W3043468555 @default.
- W4285223668 cites W3043719198 @default.
- W4285223668 cites W3047443805 @default.
- W4285223668 cites W3048051136 @default.
- W4285223668 cites W3048631361 @default.
- W4285223668 cites W3089661409 @default.
- W4285223668 cites W3096533519 @default.
- W4285223668 cites W3097353710 @default.
- W4285223668 cites W3100195331 @default.
- W4285223668 cites W3101012758 @default.
- W4285223668 cites W3101640299 @default.
- W4285223668 cites W3103294617 @default.
- W4285223668 cites W3110749113 @default.
- W4285223668 cites W3118513496 @default.
- W4285223668 cites W3122463936 @default.
- W4285223668 cites W3129608167 @default.
- W4285223668 cites W3129771090 @default.
- W4285223668 cites W3132317653 @default.
- W4285223668 cites W3135445258 @default.
- W4285223668 cites W3136985054 @default.
- W4285223668 cites W3137191419 @default.
- W4285223668 cites W3140885850 @default.
- W4285223668 cites W3154512708 @default.
- W4285223668 cites W3164008977 @default.
- W4285223668 cites W3165729427 @default.
- W4285223668 cites W3186409694 @default.
- W4285223668 cites W3214821343 @default.
- W4285223668 cites W4212955958 @default.
- W4285223668 cites W4214854488 @default.
- W4285223668 cites W4226275810 @default.
- W4285223668 cites W4233760599 @default.
- W4285223668 doi "https://doi.org/10.1109/tgrs.2022.3186480" @default.
- W4285223668 hasPublicationYear "2022" @default.
- W4285223668 type Work @default.
- W4285223668 citedByCount "11" @default.
- W4285223668 countsByYear W42852236682022 @default.
- W4285223668 countsByYear W42852236682023 @default.
- W4285223668 crossrefType "journal-article" @default.
- W4285223668 hasAuthorship W4285223668A5023381631 @default.
- W4285223668 hasAuthorship W4285223668A5035508615 @default.
- W4285223668 hasAuthorship W4285223668A5064140321 @default.
- W4285223668 hasAuthorship W4285223668A5066378186 @default.
- W4285223668 hasAuthorship W4285223668A5075013625 @default.
- W4285223668 hasAuthorship W4285223668A5086253211 @default.
- W4285223668 hasConcept C114614502 @default.
- W4285223668 hasConcept C119857082 @default.
- W4285223668 hasConcept C127162648 @default.