Matches in SemOpenAlex for { <https://semopenalex.org/work/W4328107821> ?p ?o ?g. }
- W4328107821 endingPage "662" @default.
- W4328107821 startingPage "652" @default.
- W4328107821 abstract "Abstract Semantic segmentation is a fundamental technology for autonomous driving. It has a high demand for inference speed and accuracy. However, a good trade‐off between accuracy and latency is yet not present in existing semantic segmentation approaches. Due to the limitation of speed, the authors cannot increase the number of network layers without limit and cannot design modules like in the networks without real‐time. It is a challenging problem how to design a model with good performance under limited resources. To alleviate these issues, in this study, the authors propose a refinement co‐supervision network (RCNet), which is real‐time on a high‐resolution image (1024×2048). The authors first construct the context refinement module, which can provide low computation cost way for obtaining the large receptive field and context information. Furthermore, a boundary co‐supervision mechanism is proposed. It strengthens the optimisation of easily neglected boundaries and small targets. Experimental results reveal that the proposed RCNet outperforms seven representative semantic segmentation methods." @default.
- W4328107821 created "2023-03-22" @default.
- W4328107821 creator A5017941291 @default.
- W4328107821 creator A5037688515 @default.
- W4328107821 creator A5039635960 @default.
- W4328107821 creator A5053975628 @default.
- W4328107821 creator A5057111851 @default.
- W4328107821 creator A5062388461 @default.
- W4328107821 date "2023-03-21" @default.
- W4328107821 modified "2023-10-16" @default.
- W4328107821 title "Refinement Co‐supervision network for real‐time semantic segmentation" @default.
- W4328107821 cites W1901129140 @default.
- W4328107821 cites W1903029394 @default.
- W4328107821 cites W1923115158 @default.
- W4328107821 cites W2097117768 @default.
- W4328107821 cites W2183341477 @default.
- W4328107821 cites W2194775991 @default.
- W4328107821 cites W2340897893 @default.
- W4328107821 cites W2412782625 @default.
- W4328107821 cites W2531409750 @default.
- W4328107821 cites W2560023338 @default.
- W4328107821 cites W2598666589 @default.
- W4328107821 cites W2740036778 @default.
- W4328107821 cites W2762439315 @default.
- W4328107821 cites W2886934227 @default.
- W4328107821 cites W2888965908 @default.
- W4328107821 cites W2905123719 @default.
- W4328107821 cites W2907536214 @default.
- W4328107821 cites W2955058313 @default.
- W4328107821 cites W2962772649 @default.
- W4328107821 cites W2963125010 @default.
- W4328107821 cites W2963136578 @default.
- W4328107821 cites W2963163009 @default.
- W4328107821 cites W2963918968 @default.
- W4328107821 cites W2964217532 @default.
- W4328107821 cites W2964309882 @default.
- W4328107821 cites W2965391153 @default.
- W4328107821 cites W2981609437 @default.
- W4328107821 cites W2982083293 @default.
- W4328107821 cites W2982605490 @default.
- W4328107821 cites W2987175876 @default.
- W4328107821 cites W2995279644 @default.
- W4328107821 cites W2996020415 @default.
- W4328107821 cites W2996290406 @default.
- W4328107821 cites W3005226210 @default.
- W4328107821 cites W3012528238 @default.
- W4328107821 cites W3017153481 @default.
- W4328107821 cites W3034681889 @default.
- W4328107821 cites W3035071066 @default.
- W4328107821 cites W3035414587 @default.
- W4328107821 cites W3049562662 @default.
- W4328107821 cites W3077024029 @default.
- W4328107821 cites W3088146056 @default.
- W4328107821 cites W3096653763 @default.
- W4328107821 cites W3110420020 @default.
- W4328107821 cites W3136206433 @default.
- W4328107821 cites W3144914540 @default.
- W4328107821 cites W3158412687 @default.
- W4328107821 cites W3158463880 @default.
- W4328107821 cites W3200850290 @default.
- W4328107821 cites W3215987876 @default.
- W4328107821 doi "https://doi.org/10.1049/cvi2.12187" @default.
- W4328107821 hasPublicationYear "2023" @default.
- W4328107821 type Work @default.
- W4328107821 citedByCount "3" @default.
- W4328107821 countsByYear W43281078212023 @default.
- W4328107821 crossrefType "journal-article" @default.
- W4328107821 hasAuthorship W4328107821A5017941291 @default.
- W4328107821 hasAuthorship W4328107821A5037688515 @default.
- W4328107821 hasAuthorship W4328107821A5039635960 @default.
- W4328107821 hasAuthorship W4328107821A5053975628 @default.
- W4328107821 hasAuthorship W4328107821A5057111851 @default.
- W4328107821 hasAuthorship W4328107821A5062388461 @default.
- W4328107821 hasBestOaLocation W43281078211 @default.
- W4328107821 hasConcept C11413529 @default.
- W4328107821 hasConcept C119857082 @default.
- W4328107821 hasConcept C124101348 @default.
- W4328107821 hasConcept C124504099 @default.
- W4328107821 hasConcept C151730666 @default.
- W4328107821 hasConcept C154945302 @default.
- W4328107821 hasConcept C199360897 @default.
- W4328107821 hasConcept C202444582 @default.
- W4328107821 hasConcept C2776214188 @default.
- W4328107821 hasConcept C2779343474 @default.
- W4328107821 hasConcept C2780801425 @default.
- W4328107821 hasConcept C31258907 @default.
- W4328107821 hasConcept C31972630 @default.
- W4328107821 hasConcept C33923547 @default.
- W4328107821 hasConcept C41008148 @default.
- W4328107821 hasConcept C45374587 @default.
- W4328107821 hasConcept C46637626 @default.
- W4328107821 hasConcept C76155785 @default.
- W4328107821 hasConcept C82876162 @default.
- W4328107821 hasConcept C86803240 @default.
- W4328107821 hasConcept C89600930 @default.
- W4328107821 hasConcept C9652623 @default.
- W4328107821 hasConceptScore W4328107821C11413529 @default.
- W4328107821 hasConceptScore W4328107821C119857082 @default.