Matches in SemOpenAlex for { <https://semopenalex.org/work/W3204258583> ?p ?o ?g. }
Showing items 1 to 82 of
82
with 100 items per page.
- W3204258583 endingPage "536" @default.
- W3204258583 startingPage "526" @default.
- W3204258583 abstract "This paper presents a weakly supervised image segmentation method that adopts tight bounding box annotations. It proposes generalized multiple instance learning (MIL) and smooth maximum approximation to integrate the bounding box tightness prior into the deep neural network in an end-to-end manner. In generalized MIL, positive bags are defined by parallel crossing lines with a set of different angles, and negative bags are defined as individual pixels outside of any bounding boxes. Two variants of smooth maximum approximation, i.e., $alpha$-softmax function and $alpha$-quasimax function, are exploited to conquer the numeral instability introduced by maximum function of bag prediction. The proposed approach was evaluated on two pubic medical datasets using Dice coefficient. The results demonstrate that it outperforms the state-of-the-art methods. The codes are available at url{https://github.com/wangjuan313/wsis-boundingbox}." @default.
- W3204258583 created "2021-10-11" @default.
- W3204258583 creator A5028343047 @default.
- W3204258583 creator A5033594246 @default.
- W3204258583 date "2021-01-01" @default.
- W3204258583 modified "2023-10-09" @default.
- W3204258583 title "Bounding Box Tightness Prior for Weakly Supervised Image Segmentation" @default.
- W3204258583 cites W1901129140 @default.
- W3204258583 cites W1903029394 @default.
- W3204258583 cites W2106033751 @default.
- W3204258583 cites W2124351162 @default.
- W3204258583 cites W2168804568 @default.
- W3204258583 cites W2337429362 @default.
- W3204258583 cites W2396622801 @default.
- W3204258583 cites W2552414813 @default.
- W3204258583 cites W2791723176 @default.
- W3204258583 cites W2962867364 @default.
- W3204258583 cites W2964309882 @default.
- W3204258583 cites W3034930876 @default.
- W3204258583 cites W611457968 @default.
- W3204258583 doi "https://doi.org/10.1007/978-3-030-87196-3_49" @default.
- W3204258583 hasPublicationYear "2021" @default.
- W3204258583 type Work @default.
- W3204258583 sameAs 3204258583 @default.
- W3204258583 citedByCount "16" @default.
- W3204258583 countsByYear W32042585832021 @default.
- W3204258583 countsByYear W32042585832022 @default.
- W3204258583 countsByYear W32042585832023 @default.
- W3204258583 crossrefType "book-chapter" @default.
- W3204258583 hasAuthorship W3204258583A5028343047 @default.
- W3204258583 hasAuthorship W3204258583A5033594246 @default.
- W3204258583 hasBestOaLocation W32042585832 @default.
- W3204258583 hasConcept C11413529 @default.
- W3204258583 hasConcept C115961682 @default.
- W3204258583 hasConcept C124504099 @default.
- W3204258583 hasConcept C14036430 @default.
- W3204258583 hasConcept C147037132 @default.
- W3204258583 hasConcept C153180895 @default.
- W3204258583 hasConcept C154945302 @default.
- W3204258583 hasConcept C160633673 @default.
- W3204258583 hasConcept C188441871 @default.
- W3204258583 hasConcept C41008148 @default.
- W3204258583 hasConcept C63584917 @default.
- W3204258583 hasConcept C78458016 @default.
- W3204258583 hasConcept C81363708 @default.
- W3204258583 hasConcept C86803240 @default.
- W3204258583 hasConcept C89600930 @default.
- W3204258583 hasConceptScore W3204258583C11413529 @default.
- W3204258583 hasConceptScore W3204258583C115961682 @default.
- W3204258583 hasConceptScore W3204258583C124504099 @default.
- W3204258583 hasConceptScore W3204258583C14036430 @default.
- W3204258583 hasConceptScore W3204258583C147037132 @default.
- W3204258583 hasConceptScore W3204258583C153180895 @default.
- W3204258583 hasConceptScore W3204258583C154945302 @default.
- W3204258583 hasConceptScore W3204258583C160633673 @default.
- W3204258583 hasConceptScore W3204258583C188441871 @default.
- W3204258583 hasConceptScore W3204258583C41008148 @default.
- W3204258583 hasConceptScore W3204258583C63584917 @default.
- W3204258583 hasConceptScore W3204258583C78458016 @default.
- W3204258583 hasConceptScore W3204258583C81363708 @default.
- W3204258583 hasConceptScore W3204258583C86803240 @default.
- W3204258583 hasConceptScore W3204258583C89600930 @default.
- W3204258583 hasLocation W32042585831 @default.
- W3204258583 hasLocation W32042585832 @default.
- W3204258583 hasOpenAccess W3204258583 @default.
- W3204258583 hasPrimaryLocation W32042585831 @default.
- W3204258583 hasRelatedWork W1971158690 @default.
- W3204258583 hasRelatedWork W2090047635 @default.
- W3204258583 hasRelatedWork W2756241593 @default.
- W3204258583 hasRelatedWork W2758063741 @default.
- W3204258583 hasRelatedWork W2907667403 @default.
- W3204258583 hasRelatedWork W2977314777 @default.
- W3204258583 hasRelatedWork W4206297187 @default.
- W3204258583 hasRelatedWork W4212766161 @default.
- W3204258583 hasRelatedWork W4313854567 @default.
- W3204258583 hasRelatedWork W3090693157 @default.
- W3204258583 isParatext "false" @default.
- W3204258583 isRetracted "false" @default.
- W3204258583 magId "3204258583" @default.
- W3204258583 workType "book-chapter" @default.