FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3190526140> ?p ?o ?g. }

• W3190526140 abstract "When confronted with objects of unknown types in an image, humans can effortlessly and precisely tell their visual boundaries. This recognition mechanism and underlying generalization capability seem to contrast to state-of-the-art image segmentation networks that rely on large-scale category-aware annotated training samples. In this paper, we make an attempt towards building models that explicitly account for visual boundary knowledge, in hope to reduce the training effort on segmenting unseen categories. Specifically, we investigate a new task termed as Boundary Knowledge Translation (BKT). Given a set of fully labeled categories, BKT aims to translate the visual boundary knowledge learned from the labeled categories, to a set of novel categories, each of which is provided only a few labeled samples. To this end, we propose a Translation Segmentation Network (Trans-Net), which comprises a segmentation network and two boundary discriminators. The segmentation network, combined with a boundary-aware self-supervised mechanism, is devised to conduct foreground segmentation, while the two discriminators work together in an adversarial manner to ensure an accurate segmentation of the novel categories under light supervision. Exhaustive experiments demonstrate that, with only tens of labeled samples as guidance, Trans-Net achieves close results on par with fully supervised methods." @default.
• W3190526140 created "2021-08-16" @default.
• W3190526140 creator A5000368429 @default.
• W3190526140 creator A5015574447 @default.
• W3190526140 creator A5026532752 @default.
• W3190526140 creator A5043914348 @default.
• W3190526140 creator A5048922656 @default.
• W3190526140 creator A5049119167 @default.
• W3190526140 creator A5060524512 @default.
• W3190526140 date "2021-08-01" @default.
• W3190526140 modified "2023-10-16" @default.
• W3190526140 title "Visual Boundary Knowledge Translation for Foreground Segmentation" @default.
• W3190526140 cites W1580389772 @default.
• W3190526140 cites W1797268635 @default.
• W3190526140 cites W1901129140 @default.
• W3190526140 cites W2002781701 @default.
• W3190526140 cites W2037954058 @default.
• W3190526140 cites W2087100776 @default.
• W3190526140 cites W2114705035 @default.
• W3190526140 cites W2125215748 @default.
• W3190526140 cites W2171378720 @default.
• W3190526140 cites W2221898772 @default.
• W3190526140 cites W2266390837 @default.
• W3190526140 cites W2294182682 @default.
• W3190526140 cites W2518599539 @default.
• W3190526140 cites W2552414813 @default.
• W3190526140 cites W2554423077 @default.
• W3190526140 cites W2560023338 @default.
• W3190526140 cites W2565639579 @default.
• W3190526140 cites W2598666589 @default.
• W3190526140 cites W2630837129 @default.
• W3190526140 cites W2738820721 @default.
• W3190526140 cites W2741237521 @default.
• W3190526140 cites W2757094569 @default.
• W3190526140 cites W2778764040 @default.
• W3190526140 cites W2799166040 @default.
• W3190526140 cites W2807912089 @default.
• W3190526140 cites W2886773299 @default.
• W3190526140 cites W2901575041 @default.
• W3190526140 cites W2955828465 @default.
• W3190526140 cites W2957414648 @default.
• W3190526140 cites W2961348656 @default.
• W3190526140 cites W2962872526 @default.
• W3190526140 cites W2962879692 @default.
• W3190526140 cites W2963078159 @default.
• W3190526140 cites W2963194837 @default.
• W3190526140 cites W2963299740 @default.
• W3190526140 cites W2963341924 @default.
• W3190526140 cites W2963458902 @default.
• W3190526140 cites W2963483401 @default.
• W3190526140 cites W2963599420 @default.
• W3190526140 cites W2970653639 @default.
• W3190526140 cites W2972107091 @default.
• W3190526140 cites W2982531732 @default.
• W3190526140 cites W2989484703 @default.
• W3190526140 cites W2989684653 @default.
• W3190526140 cites W2990230185 @default.
• W3190526140 cites W2991471181 @default.
• W3190526140 cites W2994528761 @default.
• W3190526140 cites W2997225633 @default.
• W3190526140 cites W2999607073 @default.
• W3190526140 cites W3033502887 @default.
• W3190526140 cites W3101639073 @default.
• W3190526140 cites W3105636206 @default.
• W3190526140 doi "https://doi.org/10.48550/arxiv.2108.00379" @default.
• W3190526140 hasPublicationYear "2021" @default.
• W3190526140 type Work @default.
• W3190526140 sameAs 3190526140 @default.
• W3190526140 citedByCount "0" @default.
• W3190526140 crossrefType "posted-content" @default.
• W3190526140 hasAuthorship W3190526140A5000368429 @default.
• W3190526140 hasAuthorship W3190526140A5015574447 @default.
• W3190526140 hasAuthorship W3190526140A5026532752 @default.
• W3190526140 hasAuthorship W3190526140A5043914348 @default.
• W3190526140 hasAuthorship W3190526140A5048922656 @default.
• W3190526140 hasAuthorship W3190526140A5049119167 @default.
• W3190526140 hasAuthorship W3190526140A5060524512 @default.
• W3190526140 hasBestOaLocation W31905261401 @default.
• W3190526140 hasConcept C104317684 @default.
• W3190526140 hasConcept C105580179 @default.
• W3190526140 hasConcept C119857082 @default.
• W3190526140 hasConcept C124504099 @default.
• W3190526140 hasConcept C125308379 @default.
• W3190526140 hasConcept C134306372 @default.
• W3190526140 hasConcept C144133560 @default.
• W3190526140 hasConcept C149364088 @default.
• W3190526140 hasConcept C153180895 @default.
• W3190526140 hasConcept C154945302 @default.
• W3190526140 hasConcept C162324750 @default.
• W3190526140 hasConcept C162853370 @default.
• W3190526140 hasConcept C177148314 @default.
• W3190526140 hasConcept C177264268 @default.
• W3190526140 hasConcept C185592680 @default.
• W3190526140 hasConcept C187736073 @default.
• W3190526140 hasConcept C199360897 @default.
• W3190526140 hasConcept C204321447 @default.
• W3190526140 hasConcept C2780451532 @default.
• W3190526140 hasConcept C33923547 @default.
• W3190526140 hasConcept C41008148 @default.
• W3190526140 hasConcept C55493867 @default.

• next