FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3119337483> ?p ?o ?g. }

• W3119337483 abstract "Although deep models have greatly improved the accuracy and robustness of image segmentation, obtaining segmentation results with highly accurate boundaries and fine structures is still a challenging problem. In this paper, we propose a simple yet powerful Boundary-Aware Segmentation Network (BASNet), which comprises a predict-refine architecture and a hybrid loss, for highly accurate image segmentation. The predict-refine architecture consists of a densely supervised encoder-decoder network and a residual refinement module, which are respectively used to predict and refine a segmentation probability map. The hybrid loss is a combination of the binary cross entropy, structural similarity and intersection-over-union losses, which guide the network to learn three-level (ie, pixel-, patch- and map- level) hierarchy representations. We evaluate our BASNet on two reverse tasks including salient object segmentation, camouflaged object segmentation, showing that it achieves very competitive performance with sharp segmentation boundaries. Importantly, BASNet runs at over 70 fps on a single GPU which benefits many potential real applications. Based on BASNet, we further developed two (close to) commercial applications: AR COPY & PASTE, in which BASNet is integrated with augmented reality for COPYING and PASTING real-world objects, and OBJECT CUT, which is a web-based tool for automatic object background removal. Both applications have already drawn huge amount of attention and have important real-world impacts. The code and two applications will be publicly available at: this https URL." @default.
• W3119337483 created "2021-01-18" @default.
• W3119337483 creator A5001882275 @default.
• W3119337483 creator A5017151626 @default.
• W3119337483 creator A5019003578 @default.
• W3119337483 creator A5024767229 @default.
• W3119337483 creator A5030948380 @default.
• W3119337483 creator A5045785006 @default.
• W3119337483 creator A5056294284 @default.
• W3119337483 creator A5060325960 @default.
• W3119337483 creator A5082634513 @default.
• W3119337483 date "2021-01-12" @default.
• W3119337483 modified "2023-09-23" @default.
• W3119337483 title "Boundary-Aware Segmentation Network for Mobile and Web Applications." @default.
• W3119337483 cites W1519696843 @default.
• W3119337483 cites W1533861849 @default.
• W3119337483 cites W1580389772 @default.
• W3119337483 cites W1699734612 @default.
• W3119337483 cites W1748750709 @default.
• W3119337483 cites W1819333392 @default.
• W3119337483 cites W1861492603 @default.
• W3119337483 cites W1894057436 @default.
• W3119337483 cites W1901129140 @default.
• W3119337483 cites W1903029394 @default.
• W3119337483 cites W1942214758 @default.
• W3119337483 cites W1947031653 @default.
• W3119337483 cites W1948843088 @default.
• W3119337483 cites W1982075130 @default.
• W3119337483 cites W1991113069 @default.
• W3119337483 cites W1994922096 @default.
• W3119337483 cites W2002781701 @default.
• W3119337483 cites W2006132599 @default.
• W3119337483 cites W2039313011 @default.
• W3119337483 cites W2072529824 @default.
• W3119337483 cites W2075326470 @default.
• W3119337483 cites W2086791339 @default.
• W3119337483 cites W2097117768 @default.
• W3119337483 cites W2102605133 @default.
• W3119337483 cites W2109407305 @default.
• W3119337483 cites W2110764733 @default.
• W3119337483 cites W2114487471 @default.
• W3119337483 cites W2115579991 @default.
• W3119337483 cites W2115761837 @default.
• W3119337483 cites W2117766076 @default.
• W3119337483 cites W2120947612 @default.
• W3119337483 cites W2121947440 @default.
• W3119337483 cites W2123402141 @default.
• W3119337483 cites W2124260943 @default.
• W3119337483 cites W2131910503 @default.
• W3119337483 cites W2132083787 @default.
• W3119337483 cites W2132603077 @default.
• W3119337483 cites W2140594263 @default.
• W3119337483 cites W2142707712 @default.
• W3119337483 cites W2144133758 @default.
• W3119337483 cites W2145803225 @default.
• W3119337483 cites W2148861411 @default.
• W3119337483 cites W2151103935 @default.
• W3119337483 cites W2169374938 @default.
• W3119337483 cites W2171378720 @default.
• W3119337483 cites W2194775991 @default.
• W3119337483 cites W2293332611 @default.
• W3119337483 cites W2296770417 @default.
• W3119337483 cites W2307770531 @default.
• W3119337483 cites W2340897893 @default.
• W3119337483 cites W2412782625 @default.
• W3119337483 cites W2437041077 @default.
• W3119337483 cites W2461475918 @default.
• W3119337483 cites W2518599539 @default.
• W3119337483 cites W2560023338 @default.
• W3119337483 cites W2565639579 @default.
• W3119337483 cites W2598666589 @default.
• W3119337483 cites W2604469346 @default.
• W3119337483 cites W2609825896 @default.
• W3119337483 cites W2630837129 @default.
• W3119337483 cites W2737258237 @default.
• W3119337483 cites W2740652190 @default.
• W3119337483 cites W2740667773 @default.
• W3119337483 cites W2744613561 @default.
• W3119337483 cites W2780708736 @default.
• W3119337483 cites W2780861787 @default.
• W3119337483 cites W2788154928 @default.
• W3119337483 cites W2793847580 @default.
• W3119337483 cites W2798791651 @default.
• W3119337483 cites W2798825526 @default.
• W3119337483 cites W2801872748 @default.
• W3119337483 cites W2802368751 @default.
• W3119337483 cites W2803110331 @default.
• W3119337483 cites W2807746031 @default.
• W3119337483 cites W2808442315 @default.
• W3119337483 cites W2884555738 @default.
• W3119337483 cites W2886482347 @default.
• W3119337483 cites W2893067557 @default.
• W3119337483 cites W2893459692 @default.
• W3119337483 cites W2895251968 @default.
• W3119337483 cites W2899771611 @default.
• W3119337483 cites W2920326761 @default.
• W3119337483 cites W2923601983 @default.
• W3119337483 cites W2938260698 @default.
• W3119337483 cites W2939217524 @default.
• W3119337483 cites W2948510860 @default.

• next