FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3214999242> ?p ?o ?g. }

• W3214999242 endingPage "746" @default.
• W3214999242 startingPage "729" @default.
• W3214999242 abstract "Existing salient instance detection (SID) methods typically learn from pixel-level annotated datasets. In this paper, we present the first weakly-supervised approach to the SID problem. Although weak supervision has been considered in general saliency detection, it is mainly based on using class labels for object localization. However, it is non-trivial to use only class labels to learn instance-aware saliency information, as salient instances with high semantic affinities may not be easily separated by the labels. As the subitizing information provides an instant judgement on the number of salient items, it is naturally related to detecting salient instances and may help separate instances of the same class while grouping different parts of the same instance. Inspired by this observation, we propose to use class and subitizing labels as weak supervision for the SID problem. We propose a novel weakly-supervised network with three branches: a Saliency Detection Branch leveraging class consistency information to locate candidate objects; a Boundary Detection Branch exploiting class discrepancy information to delineate object boundaries; and a Centroid Detection Branch using subitizing information to detect salient instance centroids. This complementary information is then fused to produce a salient instance map. To facilitate the learning process, we further propose a progressive training scheme to reduce label noise and the corresponding noise learned by the model, via reciprocating the model with progressive salient instance prediction and model refreshing. Our extensive evaluations show that the proposed method plays favorably against carefully designed baseline methods adapted from related tasks." @default.
• W3214999242 created "2021-12-06" @default.
• W3214999242 creator A5006197413 @default.
• W3214999242 creator A5020527092 @default.
• W3214999242 creator A5025567094 @default.
• W3214999242 creator A5025820603 @default.
• W3214999242 creator A5068792201 @default.
• W3214999242 date "2022-01-31" @default.
• W3214999242 modified "2023-10-13" @default.
• W3214999242 title "Learning to Detect Instance-Level Salient Objects Using Complementary Image Labels" @default.
• W3214999242 cites W1507506748 @default.
• W3214999242 cites W1905882502 @default.
• W3214999242 cites W1954128991 @default.
• W3214999242 cites W1982075130 @default.
• W3214999242 cites W1991367009 @default.
• W3214999242 cites W2031489346 @default.
• W3214999242 cites W2039313011 @default.
• W3214999242 cites W2066624635 @default.
• W3214999242 cites W2086791339 @default.
• W3214999242 cites W2100470808 @default.
• W3214999242 cites W2157554677 @default.
• W3214999242 cites W2161185676 @default.
• W3214999242 cites W2194775991 @default.
• W3214999242 cites W2294182682 @default.
• W3214999242 cites W2295107390 @default.
• W3214999242 cites W2300687442 @default.
• W3214999242 cites W2312198368 @default.
• W3214999242 cites W2422471819 @default.
• W3214999242 cites W2565639579 @default.
• W3214999242 cites W2605929543 @default.
• W3214999242 cites W2740667773 @default.
• W3214999242 cites W2744613561 @default.
• W3214999242 cites W2772161954 @default.
• W3214999242 cites W2777511827 @default.
• W3214999242 cites W2798825526 @default.
• W3214999242 cites W2799074129 @default.
• W3214999242 cites W2884585870 @default.
• W3214999242 cites W2895251968 @default.
• W3214999242 cites W2948447329 @default.
• W3214999242 cites W2948500402 @default.
• W3214999242 cites W2953433552 @default.
• W3214999242 cites W2955058313 @default.
• W3214999242 cites W2955278847 @default.
• W3214999242 cites W2962758679 @default.
• W3214999242 cites W2962867364 @default.
• W3214999242 cites W2963136160 @default.
• W3214999242 cites W2963299740 @default.
• W3214999242 cites W2963311325 @default.
• W3214999242 cites W2963312801 @default.
• W3214999242 cites W2963685207 @default.
• W3214999242 cites W2963706010 @default.
• W3214999242 cites W2963775509 @default.
• W3214999242 cites W2963915286 @default.
• W3214999242 cites W2964352379 @default.
• W3214999242 cites W2986390834 @default.
• W3214999242 cites W2986825110 @default.
• W3214999242 cites W2987701848 @default.
• W3214999242 cites W2990984982 @default.
• W3214999242 cites W2996884277 @default.
• W3214999242 cites W2996959377 @default.
• W3214999242 cites W2998449272 @default.
• W3214999242 cites W3034185160 @default.
• W3214999242 cites W3034453930 @default.
• W3214999242 cites W3034965397 @default.
• W3214999242 cites W3035290198 @default.
• W3214999242 cites W3035422681 @default.
• W3214999242 cites W3091093964 @default.
• W3214999242 cites W3098241816 @default.
• W3214999242 cites W3107944836 @default.
• W3214999242 cites W3108318504 @default.
• W3214999242 cites W3109623941 @default.
• W3214999242 cites W3156154235 @default.
• W3214999242 cites W3210097264 @default.
• W3214999242 doi "https://doi.org/10.1007/s11263-021-01553-w" @default.
• W3214999242 hasPublicationYear "2022" @default.
• W3214999242 type Work @default.
• W3214999242 sameAs 3214999242 @default.
• W3214999242 citedByCount "9" @default.
• W3214999242 countsByYear W32149992422022 @default.
• W3214999242 countsByYear W32149992422023 @default.
• W3214999242 crossrefType "journal-article" @default.
• W3214999242 hasAuthorship W3214999242A5006197413 @default.
• W3214999242 hasAuthorship W3214999242A5020527092 @default.
• W3214999242 hasAuthorship W3214999242A5025567094 @default.
• W3214999242 hasAuthorship W3214999242A5025820603 @default.
• W3214999242 hasAuthorship W3214999242A5068792201 @default.
• W3214999242 hasBestOaLocation W32149992422 @default.
• W3214999242 hasConcept C115961682 @default.
• W3214999242 hasConcept C146599234 @default.
• W3214999242 hasConcept C153180895 @default.
• W3214999242 hasConcept C154945302 @default.
• W3214999242 hasConcept C2776436953 @default.
• W3214999242 hasConcept C2777212361 @default.
• W3214999242 hasConcept C2780719617 @default.
• W3214999242 hasConcept C41008148 @default.
• W3214999242 hasConcept C99498987 @default.
• W3214999242 hasConceptScore W3214999242C115961682 @default.
• W3214999242 hasConceptScore W3214999242C146599234 @default.

• next