FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4285505226> ?p ?o ?g. }

• W4285505226 endingPage "8341" @default.
• W4285505226 startingPage "8327" @default.
• W4285505226 abstract "Image deraining has achieved considerable progress based on supervised learning with synthetic training pairs, but is usually limited in handling real-world rainy images. Although semi-supervised methods are suggested to exploit real-world rainy images when training deep deraining models, their performances are still notably inferior. To address this crucial issue, this work proposes a semi-supervised image deraining network with knowledge distillation (SSID-KD) for better exploiting real-world rainy images. In particular, the consistency of feature distribution of rain streaks extracted from synthetic and real-world rainy images is enforced by adopting knowledge distillation. Moreover, as for the backbone in SSID-KD, we propose the multi-scale feature fusion module and the pyramid fusion module to better extract deep features of rainy images. SSID-KD can relieve the problem of over-deraining or under-deraining for real-world rainy images, while it can keep comparable performance with supervised deraining methods on several benchmark datasets. Extensive experiments on both synthetic and real-world rainy images have validated that our SSID-KD not only can achieve better deraining results than existing semi-supervised deraining methods but also are quantitatively comparable with state-of-the-art supervised deraining methods. Benefiting from the well exploration of real-world rainy images, our SSID-KD can obtain more visually plausible deraining results. The source code and trained models are publicly available at <uri xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>https://github.com/cuiyixin555/SSID-KD</uri> ." @default.
• W4285505226 created "2022-07-15" @default.
• W4285505226 creator A5006952581 @default.
• W4285505226 creator A5022586507 @default.
• W4285505226 creator A5037080387 @default.
• W4285505226 creator A5046078938 @default.
• W4285505226 creator A5051402211 @default.
• W4285505226 date "2022-12-01" @default.
• W4285505226 modified "2023-10-02" @default.
• W4285505226 title "Semi-Supervised Image Deraining Using Knowledge Distillation" @default.
• W4285505226 cites W1909316225 @default.
• W4285505226 cites W2054604489 @default.
• W4285505226 cites W2102166818 @default.
• W4285505226 cites W2103559027 @default.
• W4285505226 cites W2119535410 @default.
• W4285505226 cites W2121396509 @default.
• W4285505226 cites W2128254161 @default.
• W4285505226 cites W2133665775 @default.
• W4285505226 cites W2154621477 @default.
• W4285505226 cites W2157331557 @default.
• W4285505226 cites W2209874411 @default.
• W4285505226 cites W2331376995 @default.
• W4285505226 cites W2466666260 @default.
• W4285505226 cites W2509784253 @default.
• W4285505226 cites W2559264300 @default.
• W4285505226 cites W2563705555 @default.
• W4285505226 cites W2613184245 @default.
• W4285505226 cites W2737207197 @default.
• W4285505226 cites W2740982616 @default.
• W4285505226 cites W2759428153 @default.
• W4285505226 cites W2780930362 @default.
• W4285505226 cites W2784344583 @default.
• W4285505226 cites W2789288870 @default.
• W4285505226 cites W2798401637 @default.
• W4285505226 cites W2798744505 @default.
• W4285505226 cites W2884068670 @default.
• W4285505226 cites W2887181327 @default.
• W4285505226 cites W2912435603 @default.
• W4285505226 cites W2930755307 @default.
• W4285505226 cites W2948667002 @default.
• W4285505226 cites W2962793481 @default.
• W4285505226 cites W2963017889 @default.
• W4285505226 cites W2963843230 @default.
• W4285505226 cites W2963878020 @default.
• W4285505226 cites W2964030969 @default.
• W4285505226 cites W2964116203 @default.
• W4285505226 cites W2964212750 @default.
• W4285505226 cites W2964267765 @default.
• W4285505226 cites W2966083079 @default.
• W4285505226 cites W2970722589 @default.
• W4285505226 cites W2971230840 @default.
• W4285505226 cites W2971719842 @default.
• W4285505226 cites W2980047233 @default.
• W4285505226 cites W2981380309 @default.
• W4285505226 cites W2988209803 @default.
• W4285505226 cites W3006233221 @default.
• W4285505226 cites W3009606699 @default.
• W4285505226 cites W3016213311 @default.
• W4285505226 cites W3022210053 @default.
• W4285505226 cites W3026432413 @default.
• W4285505226 cites W3034242291 @default.
• W4285505226 cites W3034278302 @default.
• W4285505226 cites W3034724715 @default.
• W4285505226 cites W3034972231 @default.
• W4285505226 cites W3035250394 @default.
• W4285505226 cites W3035326127 @default.
• W4285505226 cites W3035505140 @default.
• W4285505226 cites W3035631962 @default.
• W4285505226 cites W3083885798 @default.
• W4285505226 cites W3092703224 @default.
• W4285505226 cites W3093101131 @default.
• W4285505226 cites W3093244203 @default.
• W4285505226 cites W3097364975 @default.
• W4285505226 cites W3112479442 @default.
• W4285505226 cites W3134379028 @default.
• W4285505226 cites W3169078099 @default.
• W4285505226 cites W3170697543 @default.
• W4285505226 cites W3171125843 @default.
• W4285505226 cites W3208945517 @default.
• W4285505226 cites W4214717317 @default.
• W4285505226 doi "https://doi.org/10.1109/tcsvt.2022.3190516" @default.
• W4285505226 hasPublicationYear "2022" @default.
• W4285505226 type Work @default.
• W4285505226 citedByCount "7" @default.
• W4285505226 countsByYear W42855052262022 @default.
• W4285505226 countsByYear W42855052262023 @default.
• W4285505226 crossrefType "journal-article" @default.
• W4285505226 hasAuthorship W4285505226A5006952581 @default.
• W4285505226 hasAuthorship W4285505226A5022586507 @default.
• W4285505226 hasAuthorship W4285505226A5037080387 @default.
• W4285505226 hasAuthorship W4285505226A5046078938 @default.
• W4285505226 hasAuthorship W4285505226A5051402211 @default.
• W4285505226 hasConcept C119857082 @default.
• W4285505226 hasConcept C124101348 @default.
• W4285505226 hasConcept C136389625 @default.
• W4285505226 hasConcept C138885662 @default.
• W4285505226 hasConcept C142575187 @default.
• W4285505226 hasConcept C153180895 @default.

• next