FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3136296717> ?p ?o ?g. }

• W3136296717 endingPage "3747" @default.
• W3136296717 startingPage "3734" @default.
• W3136296717 abstract "Despite the fact that great progress has been made on single image deraining tasks, it is still challenging for existing models to produce satisfactory results directly, and it often requires a single or multiple refinement stages to gradually improve the quality. However, in this paper, we demonstrate that existing image-level refinement with a stage-independent learning design is problematic with the side effect of over/under-deraining. To resolve this issue, we for the first time propose the mechanism of learning to carry out refinement on the unsatisfactory features, and propose a novel attentive feature refinement (AFR) module. Specifically, AFR is designed as a two-branched network for simultaneous rain-distribution-aware attention map learning and attention guided hierarchy-preserving feature refinement. Guided by task-specific attention, coarse features are progressively refined to better model the diversified rainy effects. By using a separable convolution as the basic component, our AFR module introduces little computation overhead and can be readily integrated into most rainy-to-clean image translation networks for achieving better deraining results. By incorporating a series of AFR modules into a general encoder-decoder network, AFR-Net is constructed for deraining and it achieves new state-of-the-art results on both synthetic and real images. Furthermore, by using AFR-Net as a teacher model, we explore the use of knowledge distillation to successfully learn a student model that is also able to achieve state-of-the-art results but with a much faster inference speed (i.e., it only takes 0.08 second to process a 512×512 rainy image). Code and pre-trained models are available at (https://github.com/RobinCSIRO/AFR-Net)." @default.
• W3136296717 created "2021-03-29" @default.
• W3136296717 creator A5011057377 @default.
• W3136296717 creator A5041589060 @default.
• W3136296717 creator A5055952724 @default.
• W3136296717 date "2021-01-01" @default.
• W3136296717 modified "2023-10-12" @default.
• W3136296717 title "Attentive Feature Refinement Network for Single Rainy Image Restoration" @default.
• W3136296717 cites W1965572510 @default.
• W3136296717 cites W2017416107 @default.
• W3136296717 cites W2119535410 @default.
• W3136296717 cites W2121396509 @default.
• W3136296717 cites W2122596619 @default.
• W3136296717 cites W2154621477 @default.
• W3136296717 cites W2154815154 @default.
• W3136296717 cites W2177195834 @default.
• W3136296717 cites W2194775991 @default.
• W3136296717 cites W2209874411 @default.
• W3136296717 cites W2466666260 @default.
• W3136296717 cites W2509784253 @default.
• W3136296717 cites W2531409750 @default.
• W3136296717 cites W2559264300 @default.
• W3136296717 cites W2739879705 @default.
• W3136296717 cites W2740982616 @default.
• W3136296717 cites W2887181327 @default.
• W3136296717 cites W2896911342 @default.
• W3136296717 cites W2912435603 @default.
• W3136296717 cites W2963073614 @default.
• W3136296717 cites W2963446712 @default.
• W3136296717 cites W2963800716 @default.
• W3136296717 cites W2963866045 @default.
• W3136296717 cites W2964030969 @default.
• W3136296717 cites W2964101377 @default.
• W3136296717 cites W2964212750 @default.
• W3136296717 cites W2964971929 @default.
• W3136296717 cites W2967584026 @default.
• W3136296717 cites W2980047233 @default.
• W3136296717 cites W2991350899 @default.
• W3136296717 cites W3088524582 @default.
• W3136296717 doi "https://doi.org/10.1109/tip.2021.3064229" @default.
• W3136296717 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/33729937" @default.
• W3136296717 hasPublicationYear "2021" @default.
• W3136296717 type Work @default.
• W3136296717 sameAs 3136296717 @default.
• W3136296717 citedByCount "12" @default.
• W3136296717 countsByYear W31362967172021 @default.
• W3136296717 countsByYear W31362967172022 @default.
• W3136296717 countsByYear W31362967172023 @default.
• W3136296717 crossrefType "journal-article" @default.
• W3136296717 hasAuthorship W3136296717A5011057377 @default.
• W3136296717 hasAuthorship W3136296717A5041589060 @default.
• W3136296717 hasAuthorship W3136296717A5055952724 @default.
• W3136296717 hasConcept C111919701 @default.
• W3136296717 hasConcept C115961682 @default.
• W3136296717 hasConcept C118505674 @default.
• W3136296717 hasConcept C119857082 @default.
• W3136296717 hasConcept C121332964 @default.
• W3136296717 hasConcept C125411270 @default.
• W3136296717 hasConcept C138885662 @default.
• W3136296717 hasConcept C153180895 @default.
• W3136296717 hasConcept C154945302 @default.
• W3136296717 hasConcept C162324750 @default.
• W3136296717 hasConcept C168167062 @default.
• W3136296717 hasConcept C187736073 @default.
• W3136296717 hasConcept C2776214188 @default.
• W3136296717 hasConcept C2776401178 @default.
• W3136296717 hasConcept C2779960059 @default.
• W3136296717 hasConcept C2780451532 @default.
• W3136296717 hasConcept C41008148 @default.
• W3136296717 hasConcept C41895202 @default.
• W3136296717 hasConcept C97355855 @default.
• W3136296717 hasConceptScore W3136296717C111919701 @default.
• W3136296717 hasConceptScore W3136296717C115961682 @default.
• W3136296717 hasConceptScore W3136296717C118505674 @default.
• W3136296717 hasConceptScore W3136296717C119857082 @default.
• W3136296717 hasConceptScore W3136296717C121332964 @default.
• W3136296717 hasConceptScore W3136296717C125411270 @default.
• W3136296717 hasConceptScore W3136296717C138885662 @default.
• W3136296717 hasConceptScore W3136296717C153180895 @default.
• W3136296717 hasConceptScore W3136296717C154945302 @default.
• W3136296717 hasConceptScore W3136296717C162324750 @default.
• W3136296717 hasConceptScore W3136296717C168167062 @default.
• W3136296717 hasConceptScore W3136296717C187736073 @default.
• W3136296717 hasConceptScore W3136296717C2776214188 @default.
• W3136296717 hasConceptScore W3136296717C2776401178 @default.
• W3136296717 hasConceptScore W3136296717C2779960059 @default.
• W3136296717 hasConceptScore W3136296717C2780451532 @default.
• W3136296717 hasConceptScore W3136296717C41008148 @default.
• W3136296717 hasConceptScore W3136296717C41895202 @default.
• W3136296717 hasConceptScore W3136296717C97355855 @default.
• W3136296717 hasFunder F4320320965 @default.
• W3136296717 hasLocation W31362967171 @default.
• W3136296717 hasOpenAccess W3136296717 @default.
• W3136296717 hasPrimaryLocation W31362967171 @default.
• W3136296717 hasRelatedWork W2050101445 @default.
• W3136296717 hasRelatedWork W2167739281 @default.
• W3136296717 hasRelatedWork W2248478696 @default.
• W3136296717 hasRelatedWork W2382607599 @default.

• next