Matches in SemOpenAlex for { <https://semopenalex.org/work/W4382138552> ?p ?o ?g. }
- W4382138552 endingPage "64293" @default.
- W4382138552 startingPage "64282" @default.
- W4382138552 abstract "For the contour detection task, we use the EfficientNet model as the backbone network and propose a network model that uses dilated convolution for multi-scale optimization. The network is accumulated top-down layer by layer, combining multiple optimization modules concat together to achieve a richer feature representation. To fuse feature information at different scales, we introduce a new Multi-scale optimization module to replace the use of deeper network structures or more complex decoding methods, which uses channel attention module to learn the correlation between channels and then uses dilated convolution of different scales to enhance contextual information. High generalization performance and accuracy are obtained in comparison with recent deep learning-based contour detection models. We evaluate our approach on two datasets, i.e., BSDS500 and NYUD-v2, achieving an ODS F-measure value of 0.828 on BSDS500. In particular, the results of BSDS500 exceed the human-level performance under more stringent criteria." @default.
- W4382138552 created "2023-06-27" @default.
- W4382138552 creator A5000738217 @default.
- W4382138552 creator A5026071588 @default.
- W4382138552 creator A5047421795 @default.
- W4382138552 creator A5070909438 @default.
- W4382138552 creator A5084622854 @default.
- W4382138552 date "2023-01-01" @default.
- W4382138552 modified "2023-10-18" @default.
- W4382138552 title "Learning Multi-Scale Features Using Dilated Convolution for Contour Detection" @default.
- W4382138552 cites W1565402342 @default.
- W4382138552 cites W1930528368 @default.
- W4382138552 cites W1971995096 @default.
- W4382138552 cites W1976047850 @default.
- W4382138552 cites W1991367009 @default.
- W4382138552 cites W2034584499 @default.
- W4382138552 cites W2037227137 @default.
- W4382138552 cites W2062432103 @default.
- W4382138552 cites W2067912884 @default.
- W4382138552 cites W2077195530 @default.
- W4382138552 cites W2102605133 @default.
- W4382138552 cites W2108598243 @default.
- W4382138552 cites W2110158442 @default.
- W4382138552 cites W2119823327 @default.
- W4382138552 cites W2145023731 @default.
- W4382138552 cites W2194775991 @default.
- W4382138552 cites W2300687442 @default.
- W4382138552 cites W2412782625 @default.
- W4382138552 cites W2483076098 @default.
- W4382138552 cites W2490270993 @default.
- W4382138552 cites W2546441927 @default.
- W4382138552 cites W2550980575 @default.
- W4382138552 cites W2560023338 @default.
- W4382138552 cites W2565639579 @default.
- W4382138552 cites W2606492274 @default.
- W4382138552 cites W2618530766 @default.
- W4382138552 cites W2740400853 @default.
- W4382138552 cites W2752782242 @default.
- W4382138552 cites W2768489488 @default.
- W4382138552 cites W2883254424 @default.
- W4382138552 cites W2894469712 @default.
- W4382138552 cites W2899607431 @default.
- W4382138552 cites W2953881420 @default.
- W4382138552 cites W2969985801 @default.
- W4382138552 cites W3016571809 @default.
- W4382138552 cites W3017001049 @default.
- W4382138552 cites W3037327307 @default.
- W4382138552 cites W3084355642 @default.
- W4382138552 cites W3105688002 @default.
- W4382138552 cites W3126883214 @default.
- W4382138552 cites W3175508255 @default.
- W4382138552 cites W4200161046 @default.
- W4382138552 cites W4214774769 @default.
- W4382138552 cites W4220795296 @default.
- W4382138552 cites W4241071816 @default.
- W4382138552 cites W845365781 @default.
- W4382138552 doi "https://doi.org/10.1109/access.2023.3289203" @default.
- W4382138552 hasPublicationYear "2023" @default.
- W4382138552 type Work @default.
- W4382138552 citedByCount "0" @default.
- W4382138552 crossrefType "journal-article" @default.
- W4382138552 hasAuthorship W4382138552A5000738217 @default.
- W4382138552 hasAuthorship W4382138552A5026071588 @default.
- W4382138552 hasAuthorship W4382138552A5047421795 @default.
- W4382138552 hasAuthorship W4382138552A5070909438 @default.
- W4382138552 hasAuthorship W4382138552A5084622854 @default.
- W4382138552 hasBestOaLocation W43821385521 @default.
- W4382138552 hasConcept C11413529 @default.
- W4382138552 hasConcept C119599485 @default.
- W4382138552 hasConcept C121332964 @default.
- W4382138552 hasConcept C127162648 @default.
- W4382138552 hasConcept C127413603 @default.
- W4382138552 hasConcept C134306372 @default.
- W4382138552 hasConcept C138885662 @default.
- W4382138552 hasConcept C141353440 @default.
- W4382138552 hasConcept C153180895 @default.
- W4382138552 hasConcept C154945302 @default.
- W4382138552 hasConcept C162324750 @default.
- W4382138552 hasConcept C177148314 @default.
- W4382138552 hasConcept C17744445 @default.
- W4382138552 hasConcept C178790620 @default.
- W4382138552 hasConcept C185592680 @default.
- W4382138552 hasConcept C187736073 @default.
- W4382138552 hasConcept C199539241 @default.
- W4382138552 hasConcept C2776359362 @default.
- W4382138552 hasConcept C2776401178 @default.
- W4382138552 hasConcept C2778755073 @default.
- W4382138552 hasConcept C2779227376 @default.
- W4382138552 hasConcept C2780451532 @default.
- W4382138552 hasConcept C31258907 @default.
- W4382138552 hasConcept C33923547 @default.
- W4382138552 hasConcept C41008148 @default.
- W4382138552 hasConcept C41895202 @default.
- W4382138552 hasConcept C45347329 @default.
- W4382138552 hasConcept C50644808 @default.
- W4382138552 hasConcept C57273362 @default.
- W4382138552 hasConcept C59404180 @default.
- W4382138552 hasConcept C62520636 @default.