Matches in SemOpenAlex for { <https://semopenalex.org/work/W3157530320> ?p ?o ?g. }
- W3157530320 abstract "Underwater image enhancement is an important low-level computer vision task for autonomous underwater vehicles and remotely operated vehicles to explore and understand the underwater environments. Recently, deep convolutional neural networks (CNNs) have been successfully used in many computer vision problems, and so does underwater image enhancement. There are many deep-learning-based methods with impressive performance for underwater image enhancement, but their memory and model parameter costs are hindrances in practical application. To address this issue, we propose a lightweight adaptive feature fusion network (LAFFNet). The model is the encoder-decoder model with multiple adaptive feature fusion (AAF) modules. AAF subsumes multiple branches with different kernel sizes to generate multi-scale feature maps. Furthermore, channel attention is used to merge these feature maps adaptively. Our method reduces the number of parameters from 2.5M to 0.15M (around 94% reduction) but outperforms state-of-the-art algorithms by extensive experiments. Furthermore, we demonstrate our LAFFNet effectively improves high-level vision tasks like salience object detection and single image depth estimation." @default.
- W3157530320 created "2021-05-10" @default.
- W3157530320 creator A5042818728 @default.
- W3157530320 creator A5052378221 @default.
- W3157530320 creator A5068697891 @default.
- W3157530320 date "2021-05-04" @default.
- W3157530320 modified "2023-10-16" @default.
- W3157530320 title "LAFFNet: A Lightweight Adaptive Feature Fusion Network for Underwater Image Enhancement" @default.
- W3157530320 cites W1522301498 @default.
- W3157530320 cites W1686810756 @default.
- W3157530320 cites W1821462560 @default.
- W3157530320 cites W1901129140 @default.
- W3157530320 cites W1963696504 @default.
- W3157530320 cites W2009071067 @default.
- W3157530320 cites W2091420866 @default.
- W3157530320 cites W2097117768 @default.
- W3157530320 cites W2099471712 @default.
- W3157530320 cites W2128254161 @default.
- W3157530320 cites W2145105988 @default.
- W3157530320 cites W2194775991 @default.
- W3157530320 cites W2294668072 @default.
- W3157530320 cites W2474516010 @default.
- W3157530320 cites W2476548250 @default.
- W3157530320 cites W2562637781 @default.
- W3157530320 cites W2587107113 @default.
- W3157530320 cites W2612445135 @default.
- W3157530320 cites W2762430768 @default.
- W3157530320 cites W2798898057 @default.
- W3157530320 cites W2890779068 @default.
- W3157530320 cites W2910639395 @default.
- W3157530320 cites W2913103673 @default.
- W3157530320 cites W2927633990 @default.
- W3157530320 cites W2948892662 @default.
- W3157530320 cites W2950055287 @default.
- W3157530320 cites W2955863859 @default.
- W3157530320 cites W2961348656 @default.
- W3157530320 cites W2962793481 @default.
- W3157530320 cites W2963073614 @default.
- W3157530320 cites W2963420686 @default.
- W3157530320 cites W2963446712 @default.
- W3157530320 cites W2964088115 @default.
- W3157530320 cites W2970027712 @default.
- W3157530320 cites W2970530557 @default.
- W3157530320 cites W2990176100 @default.
- W3157530320 cites W2990946490 @default.
- W3157530320 cites W2991006905 @default.
- W3157530320 cites W3004469096 @default.
- W3157530320 cites W3006777311 @default.
- W3157530320 cites W3014522660 @default.
- W3157530320 cites W3015557838 @default.
- W3157530320 cites W3024190941 @default.
- W3157530320 cites W3035414587 @default.
- W3157530320 cites W3090004407 @default.
- W3157530320 cites W3103549414 @default.
- W3157530320 cites W3119639728 @default.
- W3157530320 cites W3131899711 @default.
- W3157530320 cites W3159486490 @default.
- W3157530320 cites W3176718939 @default.
- W3157530320 cites W3178978045 @default.
- W3157530320 doi "https://doi.org/10.48550/arxiv.2105.01299" @default.
- W3157530320 hasPublicationYear "2021" @default.
- W3157530320 type Work @default.
- W3157530320 sameAs 3157530320 @default.
- W3157530320 citedByCount "0" @default.
- W3157530320 crossrefType "posted-content" @default.
- W3157530320 hasAuthorship W3157530320A5042818728 @default.
- W3157530320 hasAuthorship W3157530320A5052378221 @default.
- W3157530320 hasAuthorship W3157530320A5068697891 @default.
- W3157530320 hasBestOaLocation W31575303201 @default.
- W3157530320 hasConcept C108154423 @default.
- W3157530320 hasConcept C111368507 @default.
- W3157530320 hasConcept C111919701 @default.
- W3157530320 hasConcept C115961682 @default.
- W3157530320 hasConcept C118505674 @default.
- W3157530320 hasConcept C127313418 @default.
- W3157530320 hasConcept C138885662 @default.
- W3157530320 hasConcept C153180895 @default.
- W3157530320 hasConcept C154945302 @default.
- W3157530320 hasConcept C197129107 @default.
- W3157530320 hasConcept C23123220 @default.
- W3157530320 hasConcept C2776401178 @default.
- W3157530320 hasConcept C31972630 @default.
- W3157530320 hasConcept C41008148 @default.
- W3157530320 hasConcept C41895202 @default.
- W3157530320 hasConcept C69744172 @default.
- W3157530320 hasConcept C81363708 @default.
- W3157530320 hasConcept C98083399 @default.
- W3157530320 hasConceptScore W3157530320C108154423 @default.
- W3157530320 hasConceptScore W3157530320C111368507 @default.
- W3157530320 hasConceptScore W3157530320C111919701 @default.
- W3157530320 hasConceptScore W3157530320C115961682 @default.
- W3157530320 hasConceptScore W3157530320C118505674 @default.
- W3157530320 hasConceptScore W3157530320C127313418 @default.
- W3157530320 hasConceptScore W3157530320C138885662 @default.
- W3157530320 hasConceptScore W3157530320C153180895 @default.
- W3157530320 hasConceptScore W3157530320C154945302 @default.
- W3157530320 hasConceptScore W3157530320C197129107 @default.
- W3157530320 hasConceptScore W3157530320C23123220 @default.
- W3157530320 hasConceptScore W3157530320C2776401178 @default.
- W3157530320 hasConceptScore W3157530320C31972630 @default.