FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2961348656> ?p ?o ?g. }

• W2961348656 abstract "Deep Convolutional Neural Networks have been adopted for salient object detection and achieved the state-of-the-art performance. Most of the previous works however focus on region accuracy but not on the boundary quality. In this paper, we propose a predict-refine architecture, BASNet, and a new hybrid loss for Boundary-Aware Salient object detection. Specifically, the architecture is composed of a densely supervised Encoder-Decoder network and a residual refinement module, which are respectively in charge of saliency prediction and saliency map refinement. The hybrid loss guides the network to learn the transformation between the input image and the ground truth in a three-level hierarchy -- pixel-, patch- and map- level -- by fusing Binary Cross Entropy (BCE), Structural SIMilarity (SSIM) and Intersection-over-Union (IoU) losses. Equipped with the hybrid loss, the proposed predict-refine architecture is able to effectively segment the salient object regions and accurately predict the fine structures with clear boundaries. Experimental results on six public datasets show that our method outperforms the state-of-the-art methods both in terms of regional and boundary evaluation measures. Our method runs at over 25 fps on a single GPU. The code is available at: https://github.com/NathanUA/BASNet." @default.
• W2961348656 created "2019-07-23" @default.
• W2961348656 creator A5001882275 @default.
• W2961348656 creator A5006157212 @default.
• W2961348656 creator A5019003578 @default.
• W2961348656 creator A5030948380 @default.
• W2961348656 creator A5056815920 @default.
• W2961348656 creator A5068320786 @default.
• W2961348656 date "2019-06-01" @default.
• W2961348656 modified "2023-10-10" @default.
• W2961348656 title "BASNet: Boundary-Aware Salient Object Detection" @default.
• W2961348656 cites W1580389772 @default.
• W2961348656 cites W1699734612 @default.
• W2961348656 cites W1942214758 @default.
• W2961348656 cites W1947031653 @default.
• W2961348656 cites W1982075130 @default.
• W2961348656 cites W1991113069 @default.
• W2961348656 cites W2002781701 @default.
• W2961348656 cites W2039313011 @default.
• W2961348656 cites W2041719651 @default.
• W2961348656 cites W2047670868 @default.
• W2961348656 cites W2086791339 @default.
• W2961348656 cites W2100470808 @default.
• W2961348656 cites W2102605133 @default.
• W2961348656 cites W2114487471 @default.
• W2961348656 cites W2123402141 @default.
• W2961348656 cites W2132083787 @default.
• W2961348656 cites W2140594263 @default.
• W2961348656 cites W2154741421 @default.
• W2961348656 cites W2171378720 @default.
• W2961348656 cites W2194775991 @default.
• W2961348656 cites W2211996548 @default.
• W2961348656 cites W2212216676 @default.
• W2961348656 cites W2293332611 @default.
• W2961348656 cites W2416190443 @default.
• W2961348656 cites W2437041077 @default.
• W2961348656 cites W2461475918 @default.
• W2961348656 cites W2518599539 @default.
• W2961348656 cites W2560311620 @default.
• W2961348656 cites W2598666589 @default.
• W2961348656 cites W2740652190 @default.
• W2961348656 cites W2740667773 @default.
• W2961348656 cites W2744613561 @default.
• W2961348656 cites W2774320778 @default.
• W2961348656 cites W2780708736 @default.
• W2961348656 cites W2798791651 @default.
• W2961348656 cites W2798825526 @default.
• W2961348656 cites W2799074129 @default.
• W2961348656 cites W2801872748 @default.
• W2961348656 cites W2802368751 @default.
• W2961348656 cites W2807746031 @default.
• W2961348656 cites W2886482347 @default.
• W2961348656 cites W2893067557 @default.
• W2961348656 cites W2895251968 @default.
• W2961348656 cites W2963032190 @default.
• W2961348656 cites W2963152757 @default.
• W2961348656 cites W2963299740 @default.
• W2961348656 cites W2963586803 @default.
• W2961348656 cites W2963635628 @default.
• W2961348656 cites W2963685207 @default.
• W2961348656 cites W2963753350 @default.
• W2961348656 cites W2963881378 @default.
• W2961348656 cites W2963906836 @default.
• W2961348656 cites W2964213565 @default.
• W2961348656 cites W3104979525 @default.
• W2961348656 cites W3171930565 @default.
• W2961348656 cites W845365781 @default.
• W2961348656 doi "https://doi.org/10.1109/cvpr.2019.00766" @default.
• W2961348656 hasPublicationYear "2019" @default.
• W2961348656 type Work @default.
• W2961348656 sameAs 2961348656 @default.
• W2961348656 citedByCount "712" @default.
• W2961348656 countsByYear W29613486562019 @default.
• W2961348656 countsByYear W29613486562020 @default.
• W2961348656 countsByYear W29613486562021 @default.
• W2961348656 countsByYear W29613486562022 @default.
• W2961348656 countsByYear W29613486562023 @default.
• W2961348656 crossrefType "proceedings-article" @default.
• W2961348656 hasAuthorship W2961348656A5001882275 @default.
• W2961348656 hasAuthorship W2961348656A5006157212 @default.
• W2961348656 hasAuthorship W2961348656A5019003578 @default.
• W2961348656 hasAuthorship W2961348656A5030948380 @default.
• W2961348656 hasAuthorship W2961348656A5056815920 @default.
• W2961348656 hasAuthorship W2961348656A5068320786 @default.
• W2961348656 hasConcept C104317684 @default.
• W2961348656 hasConcept C106301342 @default.
• W2961348656 hasConcept C111919701 @default.
• W2961348656 hasConcept C11413529 @default.
• W2961348656 hasConcept C118505674 @default.
• W2961348656 hasConcept C121332964 @default.
• W2961348656 hasConcept C127413603 @default.
• W2961348656 hasConcept C134306372 @default.
• W2961348656 hasConcept C146849305 @default.
• W2961348656 hasConcept C146978453 @default.
• W2961348656 hasConcept C153180895 @default.
• W2961348656 hasConcept C154945302 @default.
• W2961348656 hasConcept C155512373 @default.
• W2961348656 hasConcept C160633673 @default.
• W2961348656 hasConcept C167981619 @default.
• W2961348656 hasConcept C185592680 @default.

• next