FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3113755791> ?p ?o ?g. }

• W3113755791 endingPage "3136" @default.
• W3113755791 startingPage "3125" @default.
• W3113755791 abstract "Recent progress on salient object detection (SOD) mainly benefits from multi-scale learning, where the high-level and low-level features collaborate in locating salient objects and discovering fine details, respectively. However, most efforts are devoted to low-level feature learning by fusing multi-scale features or enhancing boundary representations. High-level features, which although have long proven effective for many other tasks, yet have been barely studied for SOD. In this paper, we tap into this gap and show that enhancing high-level features is essential for SOD as well. To this end, we introduce an Extremely-Downsampled Network (EDN), which employs an extreme downsampling technique to effectively learn a global view of the whole image, leading to accurate salient object localization. To accomplish better multi-level feature fusion, we construct the Scale-Correlated Pyramid Convolution (SCPC) to build an elegant decoder for recovering object details from the above extreme downsampling. Extensive experiments demonstrate that EDN achieves state-of-the-art performance with real-time speed. Our efficient EDN-Lite also achieves competitive performance with a speed of 316fps. Hence, this work is expected to spark some new thinking in SOD. Code is available at https://github.com/yuhuan-wu/EDN." @default.
• W3113755791 created "2021-01-05" @default.
• W3113755791 creator A5001598042 @default.
• W3113755791 creator A5021019207 @default.
• W3113755791 creator A5037131575 @default.
• W3113755791 creator A5056961910 @default.
• W3113755791 date "2022-01-01" @default.
• W3113755791 modified "2023-10-17" @default.
• W3113755791 title "EDN: Salient Object Detection via Extremely-Downsampled Network" @default.
• W3113755791 cites W1903001680 @default.
• W3113755791 cites W1942214758 @default.
• W3113755791 cites W1994922096 @default.
• W3113755791 cites W2002781701 @default.
• W3113755791 cites W2014854862 @default.
• W3113755791 cites W2031489346 @default.
• W3113755791 cites W2039313011 @default.
• W3113755791 cites W2055180303 @default.
• W3113755791 cites W2086791339 @default.
• W3113755791 cites W2117539524 @default.
• W3113755791 cites W2157381954 @default.
• W3113755791 cites W2194775991 @default.
• W3113755791 cites W2338972621 @default.
• W3113755791 cites W2395611524 @default.
• W3113755791 cites W2412782625 @default.
• W3113755791 cites W2461475918 @default.
• W3113755791 cites W2472480899 @default.
• W3113755791 cites W2517325737 @default.
• W3113755791 cites W2560023338 @default.
• W3113755791 cites W2569272946 @default.
• W3113755791 cites W2605929543 @default.
• W3113755791 cites W2740667773 @default.
• W3113755791 cites W2744613561 @default.
• W3113755791 cites W2754188632 @default.
• W3113755791 cites W2767623212 @default.
• W3113755791 cites W2772161954 @default.
• W3113755791 cites W2780708736 @default.
• W3113755791 cites W2798807298 @default.
• W3113755791 cites W2798825526 @default.
• W3113755791 cites W2799074129 @default.
• W3113755791 cites W2799213142 @default.
• W3113755791 cites W2799231793 @default.
• W3113755791 cites W2884555738 @default.
• W3113755791 cites W2895251968 @default.
• W3113755791 cites W2908685061 @default.
• W3113755791 cites W2928165649 @default.
• W3113755791 cites W2939217524 @default.
• W3113755791 cites W2948300571 @default.
• W3113755791 cites W2948500402 @default.
• W3113755791 cites W2948510860 @default.
• W3113755791 cites W2961348656 @default.
• W3113755791 cites W2962914239 @default.
• W3113755791 cites W2963032190 @default.
• W3113755791 cites W2963091558 @default.
• W3113755791 cites W2963112696 @default.
• W3113755791 cites W2963163009 @default.
• W3113755791 cites W2963342032 @default.
• W3113755791 cites W2963529609 @default.
• W3113755791 cites W2963706010 @default.
• W3113755791 cites W2963868681 @default.
• W3113755791 cites W2963906836 @default.
• W3113755791 cites W2981689412 @default.
• W3113755791 cites W2981899103 @default.
• W3113755791 cites W2986825110 @default.
• W3113755791 cites W2987701848 @default.
• W3113755791 cites W2989161706 @default.
• W3113755791 cites W2990984982 @default.
• W3113755791 cites W2997316506 @default.
• W3113755791 cites W3019728440 @default.
• W3113755791 cites W3034185160 @default.
• W3113755791 cites W3035290198 @default.
• W3113755791 cites W3035422681 @default.
• W3113755791 cites W3085685449 @default.
• W3113755791 cites W3093213431 @default.
• W3113755791 cites W3097336090 @default.
• W3113755791 cites W3100341797 @default.
• W3113755791 cites W3107944836 @default.
• W3113755791 cites W3108948422 @default.
• W3113755791 cites W3109623941 @default.
• W3113755791 cites W3112885960 @default.
• W3113755791 cites W3114848016 @default.
• W3113755791 cites W3125520697 @default.
• W3113755791 cites W3127842933 @default.
• W3113755791 cites W3129581972 @default.
• W3113755791 cites W3137142667 @default.
• W3113755791 cites W3175722450 @default.
• W3113755791 cites W3208937872 @default.
• W3113755791 cites W4239147634 @default.
• W3113755791 doi "https://doi.org/10.1109/tip.2022.3164550" @default.
• W3113755791 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/35412981" @default.
• W3113755791 hasPublicationYear "2022" @default.
• W3113755791 type Work @default.
• W3113755791 sameAs 3113755791 @default.
• W3113755791 citedByCount "36" @default.
• W3113755791 countsByYear W31137557912021 @default.
• W3113755791 countsByYear W31137557912022 @default.
• W3113755791 countsByYear W31137557912023 @default.
• W3113755791 crossrefType "journal-article" @default.
• W3113755791 hasAuthorship W3113755791A5001598042 @default.

• next