Matches in SemOpenAlex for { <https://semopenalex.org/work/W4229079201> ?p ?o ?g. }
- W4229079201 endingPage "20" @default.
- W4229079201 startingPage "1" @default.
- W4229079201 abstract "In this study, a novel distillation paradigm named perceptual distillation is proposed to guide the training of image fusion networks without ground truths. In the paradigm, the student network which we called main autoencoder takes in source images and produces a fused image, and the teacher network is a well-trained network exploited to compute teacher representations of images. Knowledge in the teacher representations of source images is distilled and transferred to our student main autoencoder with the help of the perceptual saliency scheme. The scheme also derives a pixel level scheme of pixel compensation, which combines with source image to enhance the pixel intensity of the fused image. Moreover, a multi-autoencoder architecture is developed by assembling two auxiliary decoders behind the main autoencoder. The architecture is trained with self-supervision to consolidate fusion training against the limitation of teacher network. Qualitative and quantitative experiments demonstrate that the proposed network achieves the state-of-the-art performance on multi-source image fusion compared with the existing fusion methods." @default.
- W4229079201 created "2022-05-08" @default.
- W4229079201 creator A5002452488 @default.
- W4229079201 creator A5014632549 @default.
- W4229079201 creator A5032488382 @default.
- W4229079201 creator A5061971878 @default.
- W4229079201 date "2022-08-01" @default.
- W4229079201 modified "2023-10-01" @default.
- W4229079201 title "A multi-autoencoder fusion network guided by perceptual distillation" @default.
- W4229079201 cites W1543016129 @default.
- W4229079201 cites W1708141795 @default.
- W4229079201 cites W2025133197 @default.
- W4229079201 cites W2034995331 @default.
- W4229079201 cites W2039465985 @default.
- W4229079201 cites W2116702374 @default.
- W4229079201 cites W2133665775 @default.
- W4229079201 cites W2142060261 @default.
- W4229079201 cites W2146353910 @default.
- W4229079201 cites W2266694576 @default.
- W4229079201 cites W2331128040 @default.
- W4229079201 cites W2461851607 @default.
- W4229079201 cites W2559870345 @default.
- W4229079201 cites W2751011928 @default.
- W4229079201 cites W2772136803 @default.
- W4229079201 cites W2777967210 @default.
- W4229079201 cites W2783573276 @default.
- W4229079201 cites W2809795042 @default.
- W4229079201 cites W2912147220 @default.
- W4229079201 cites W2933955397 @default.
- W4229079201 cites W2946893679 @default.
- W4229079201 cites W2953216366 @default.
- W4229079201 cites W2963470893 @default.
- W4229079201 cites W2963787388 @default.
- W4229079201 cites W2997833216 @default.
- W4229079201 cites W3000491333 @default.
- W4229079201 cites W3002137088 @default.
- W4229079201 cites W3010015985 @default.
- W4229079201 cites W3011768656 @default.
- W4229079201 cites W3016744618 @default.
- W4229079201 cites W3035441328 @default.
- W4229079201 cites W3083574456 @default.
- W4229079201 cites W3105639468 @default.
- W4229079201 cites W3122765966 @default.
- W4229079201 cites W3124474911 @default.
- W4229079201 cites W4226178544 @default.
- W4229079201 cites W828875492 @default.
- W4229079201 doi "https://doi.org/10.1016/j.ins.2022.05.018" @default.
- W4229079201 hasPublicationYear "2022" @default.
- W4229079201 type Work @default.
- W4229079201 citedByCount "2" @default.
- W4229079201 countsByYear W42290792012022 @default.
- W4229079201 countsByYear W42290792012023 @default.
- W4229079201 crossrefType "journal-article" @default.
- W4229079201 hasAuthorship W4229079201A5002452488 @default.
- W4229079201 hasAuthorship W4229079201A5014632549 @default.
- W4229079201 hasAuthorship W4229079201A5032488382 @default.
- W4229079201 hasAuthorship W4229079201A5061971878 @default.
- W4229079201 hasConcept C101738243 @default.
- W4229079201 hasConcept C11171543 @default.
- W4229079201 hasConcept C115961682 @default.
- W4229079201 hasConcept C119857082 @default.
- W4229079201 hasConcept C125411270 @default.
- W4229079201 hasConcept C134306372 @default.
- W4229079201 hasConcept C138885662 @default.
- W4229079201 hasConcept C153180895 @default.
- W4229079201 hasConcept C154945302 @default.
- W4229079201 hasConcept C15744967 @default.
- W4229079201 hasConcept C158525013 @default.
- W4229079201 hasConcept C160633673 @default.
- W4229079201 hasConcept C169760540 @default.
- W4229079201 hasConcept C178790620 @default.
- W4229079201 hasConcept C185592680 @default.
- W4229079201 hasConcept C193415008 @default.
- W4229079201 hasConcept C204030448 @default.
- W4229079201 hasConcept C26760741 @default.
- W4229079201 hasConcept C2780023022 @default.
- W4229079201 hasConcept C31972630 @default.
- W4229079201 hasConcept C33923547 @default.
- W4229079201 hasConcept C38652104 @default.
- W4229079201 hasConcept C41008148 @default.
- W4229079201 hasConcept C41895202 @default.
- W4229079201 hasConcept C50644808 @default.
- W4229079201 hasConcept C77618280 @default.
- W4229079201 hasConcept C86803240 @default.
- W4229079201 hasConceptScore W4229079201C101738243 @default.
- W4229079201 hasConceptScore W4229079201C11171543 @default.
- W4229079201 hasConceptScore W4229079201C115961682 @default.
- W4229079201 hasConceptScore W4229079201C119857082 @default.
- W4229079201 hasConceptScore W4229079201C125411270 @default.
- W4229079201 hasConceptScore W4229079201C134306372 @default.
- W4229079201 hasConceptScore W4229079201C138885662 @default.
- W4229079201 hasConceptScore W4229079201C153180895 @default.
- W4229079201 hasConceptScore W4229079201C154945302 @default.
- W4229079201 hasConceptScore W4229079201C15744967 @default.
- W4229079201 hasConceptScore W4229079201C158525013 @default.
- W4229079201 hasConceptScore W4229079201C160633673 @default.
- W4229079201 hasConceptScore W4229079201C169760540 @default.
- W4229079201 hasConceptScore W4229079201C178790620 @default.