Matches in SemOpenAlex for { <https://semopenalex.org/work/W3131142666> ?p ?o ?g. }
Showing items 1 to 82 of
82
with 100 items per page.
- W3131142666 abstract "Deep Neural Networks have recently demonstrated promising performance in binary change detection (CD) problems in remote sensing (RS), requiring a large amount of labeled multitemporal training samples. Since collecting such data is time-consuming and costly, most of the existing methods rely on pre-trained networks on publicly available computer vision (CV) datasets. However, because of the differences in image characteristics in CV and RS, this approach limits the performance of the existing CD methods. To address this problem, we propose a self-supervised conditional Generative Adversarial Network (S <sup xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>2</sup> -cGAN). The proposed S <sup xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>2</sup> -cGAN is trained to generate only the distribution of unchanged samples. To this end, the proposed method consists of two main steps: 1) Generating a reconstructed version of the input image as an unchanged image 2) Learning the distribution of unchanged samples through an adversarial game. Unlike the existing GAN based methods (which only use the discriminator during the adversarial training to supervise the generator), the S <sup xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>2</sup> -cGAN directly exploits the discriminator likelihood to solve the binary CD task. Experimental results show the effectiveness of the proposed S <sup xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>2</sup> -cGAN when compared to the state of the art CD methods." @default.
- W3131142666 created "2021-03-01" @default.
- W3131142666 creator A5008614342 @default.
- W3131142666 creator A5087126293 @default.
- W3131142666 creator A5088068842 @default.
- W3131142666 date "2020-09-26" @default.
- W3131142666 modified "2023-10-14" @default.
- W3131142666 title "S2-CGAN: Self-Supervised Adversarial Representation Learning for Binary Change Detection in Multispectral Images" @default.
- W3131142666 cites W2900587135 @default.
- W3131142666 cites W2910587630 @default.
- W3131142666 cites W2983224850 @default.
- W3131142666 cites W3015038817 @default.
- W3131142666 doi "https://doi.org/10.1109/igarss39084.2020.9324345" @default.
- W3131142666 hasPublicationYear "2020" @default.
- W3131142666 type Work @default.
- W3131142666 sameAs 3131142666 @default.
- W3131142666 citedByCount "5" @default.
- W3131142666 countsByYear W31311426662021 @default.
- W3131142666 countsByYear W31311426662022 @default.
- W3131142666 countsByYear W31311426662023 @default.
- W3131142666 crossrefType "proceedings-article" @default.
- W3131142666 hasAuthorship W3131142666A5008614342 @default.
- W3131142666 hasAuthorship W3131142666A5087126293 @default.
- W3131142666 hasAuthorship W3131142666A5088068842 @default.
- W3131142666 hasBestOaLocation W31311426662 @default.
- W3131142666 hasConcept C108583219 @default.
- W3131142666 hasConcept C115961682 @default.
- W3131142666 hasConcept C119857082 @default.
- W3131142666 hasConcept C12267149 @default.
- W3131142666 hasConcept C153180895 @default.
- W3131142666 hasConcept C154945302 @default.
- W3131142666 hasConcept C173163844 @default.
- W3131142666 hasConcept C17744445 @default.
- W3131142666 hasConcept C199539241 @default.
- W3131142666 hasConcept C2776359362 @default.
- W3131142666 hasConcept C2779803651 @default.
- W3131142666 hasConcept C33923547 @default.
- W3131142666 hasConcept C41008148 @default.
- W3131142666 hasConcept C48372109 @default.
- W3131142666 hasConcept C66905080 @default.
- W3131142666 hasConcept C76155785 @default.
- W3131142666 hasConcept C94375191 @default.
- W3131142666 hasConcept C94625758 @default.
- W3131142666 hasConcept C94915269 @default.
- W3131142666 hasConceptScore W3131142666C108583219 @default.
- W3131142666 hasConceptScore W3131142666C115961682 @default.
- W3131142666 hasConceptScore W3131142666C119857082 @default.
- W3131142666 hasConceptScore W3131142666C12267149 @default.
- W3131142666 hasConceptScore W3131142666C153180895 @default.
- W3131142666 hasConceptScore W3131142666C154945302 @default.
- W3131142666 hasConceptScore W3131142666C173163844 @default.
- W3131142666 hasConceptScore W3131142666C17744445 @default.
- W3131142666 hasConceptScore W3131142666C199539241 @default.
- W3131142666 hasConceptScore W3131142666C2776359362 @default.
- W3131142666 hasConceptScore W3131142666C2779803651 @default.
- W3131142666 hasConceptScore W3131142666C33923547 @default.
- W3131142666 hasConceptScore W3131142666C41008148 @default.
- W3131142666 hasConceptScore W3131142666C48372109 @default.
- W3131142666 hasConceptScore W3131142666C66905080 @default.
- W3131142666 hasConceptScore W3131142666C76155785 @default.
- W3131142666 hasConceptScore W3131142666C94375191 @default.
- W3131142666 hasConceptScore W3131142666C94625758 @default.
- W3131142666 hasConceptScore W3131142666C94915269 @default.
- W3131142666 hasFunder F4320338335 @default.
- W3131142666 hasLocation W31311426661 @default.
- W3131142666 hasLocation W31311426662 @default.
- W3131142666 hasOpenAccess W3131142666 @default.
- W3131142666 hasPrimaryLocation W31311426661 @default.
- W3131142666 hasRelatedWork W1489300767 @default.
- W3131142666 hasRelatedWork W1523447316 @default.
- W3131142666 hasRelatedWork W1980965563 @default.
- W3131142666 hasRelatedWork W2046798493 @default.
- W3131142666 hasRelatedWork W2057775761 @default.
- W3131142666 hasRelatedWork W2387995142 @default.
- W3131142666 hasRelatedWork W2964074194 @default.
- W3131142666 hasRelatedWork W4293202849 @default.
- W3131142666 hasRelatedWork W4319453655 @default.
- W3131142666 hasRelatedWork W4380714744 @default.
- W3131142666 isParatext "false" @default.
- W3131142666 isRetracted "false" @default.
- W3131142666 magId "3131142666" @default.
- W3131142666 workType "article" @default.