Matches in SemOpenAlex for { <https://semopenalex.org/work/W4312578467> ?p ?o ?g. }
- W4312578467 endingPage "18" @default.
- W4312578467 startingPage "1" @default.
- W4312578467 abstract "In contrast to the fully supervised methods using pixel-wise mask labels, box-supervised instance segmentation takes advantage of the simple box annotations, which has recently attracted a lot of research attentions. In this paper, we propose a novel single-shot box-supervised instance segmentation approach, which integrates the classical level set model with deep neural network delicately. Specifically, our proposed method iteratively learns a series of level sets through a continuous Chan-Vese energy-based function in an end-to-end fashion. A simple mask supervised SOLOv2 model is adapted to predict the instance-aware mask map as the level set for each instance. Both the input image and its deep features are employed as the input data to evolve the level set curves, where a box projection function is employed to obtain the initial boundary. By minimizing the fully differentiable energy function, the level set for each instance is iteratively optimized within its corresponding bounding box annotation. The experimental results on four challenging benchmarks demonstrate the leading performance of our proposed approach to robust instance segmentation in various scenarios. The code is available at: https://github.com/LiWentomng/boxlevelset ." @default.
- W4312578467 created "2023-01-05" @default.
- W4312578467 creator A5024965898 @default.
- W4312578467 creator A5029242626 @default.
- W4312578467 creator A5032279676 @default.
- W4312578467 creator A5049876086 @default.
- W4312578467 creator A5062252650 @default.
- W4312578467 creator A5067722197 @default.
- W4312578467 date "2022-01-01" @default.
- W4312578467 modified "2023-10-05" @default.
- W4312578467 title "Box-Supervised Instance Segmentation with Level Set Evolution" @default.
- W4312578467 cites W1861492603 @default.
- W4312578467 cites W1977946246 @default.
- W4312578467 cites W1991113069 @default.
- W4312578467 cites W2009767800 @default.
- W4312578467 cites W2031489346 @default.
- W4312578467 cites W2065350495 @default.
- W4312578467 cites W2090440060 @default.
- W4312578467 cites W2104095591 @default.
- W4312578467 cites W2108598243 @default.
- W4312578467 cites W2114487471 @default.
- W4312578467 cites W2116040950 @default.
- W4312578467 cites W2124351162 @default.
- W4312578467 cites W2144794286 @default.
- W4312578467 cites W2149184914 @default.
- W4312578467 cites W2165734775 @default.
- W4312578467 cites W2168804568 @default.
- W4312578467 cites W2194775991 @default.
- W4312578467 cites W2552414813 @default.
- W4312578467 cites W2740652190 @default.
- W4312578467 cites W2905110727 @default.
- W4312578467 cites W2920326761 @default.
- W4312578467 cites W2962914239 @default.
- W4312578467 cites W2963150697 @default.
- W4312578467 cites W2963323244 @default.
- W4312578467 cites W2963351448 @default.
- W4312578467 cites W2965289249 @default.
- W4312578467 cites W2993182889 @default.
- W4312578467 cites W2996868574 @default.
- W4312578467 cites W3003507346 @default.
- W4312578467 cites W3034826836 @default.
- W4312578467 cites W3035358681 @default.
- W4312578467 cites W3035709993 @default.
- W4312578467 cites W3082755608 @default.
- W4312578467 cites W3103562302 @default.
- W4312578467 cites W3106546328 @default.
- W4312578467 cites W3106651317 @default.
- W4312578467 cites W3109073404 @default.
- W4312578467 cites W3110576324 @default.
- W4312578467 cites W3169200952 @default.
- W4312578467 cites W3176692018 @default.
- W4312578467 cites W3177388720 @default.
- W4312578467 cites W3180169285 @default.
- W4312578467 cites W3203318343 @default.
- W4312578467 cites W3211330693 @default.
- W4312578467 cites W4313151123 @default.
- W4312578467 doi "https://doi.org/10.1007/978-3-031-19818-2_1" @default.
- W4312578467 hasPublicationYear "2022" @default.
- W4312578467 type Work @default.
- W4312578467 citedByCount "3" @default.
- W4312578467 countsByYear W43125784672023 @default.
- W4312578467 crossrefType "book-chapter" @default.
- W4312578467 hasAuthorship W4312578467A5024965898 @default.
- W4312578467 hasAuthorship W4312578467A5029242626 @default.
- W4312578467 hasAuthorship W4312578467A5032279676 @default.
- W4312578467 hasAuthorship W4312578467A5049876086 @default.
- W4312578467 hasAuthorship W4312578467A5062252650 @default.
- W4312578467 hasAuthorship W4312578467A5067722197 @default.
- W4312578467 hasBestOaLocation W43125784672 @default.
- W4312578467 hasConcept C105795698 @default.
- W4312578467 hasConcept C108583219 @default.
- W4312578467 hasConcept C11413529 @default.
- W4312578467 hasConcept C115961682 @default.
- W4312578467 hasConcept C124504099 @default.
- W4312578467 hasConcept C134306372 @default.
- W4312578467 hasConcept C136389625 @default.
- W4312578467 hasConcept C14036430 @default.
- W4312578467 hasConcept C147037132 @default.
- W4312578467 hasConcept C153180895 @default.
- W4312578467 hasConcept C154945302 @default.
- W4312578467 hasConcept C177264268 @default.
- W4312578467 hasConcept C186370098 @default.
- W4312578467 hasConcept C199360897 @default.
- W4312578467 hasConcept C33923547 @default.
- W4312578467 hasConcept C41008148 @default.
- W4312578467 hasConcept C50644808 @default.
- W4312578467 hasConcept C57493831 @default.
- W4312578467 hasConcept C62354387 @default.
- W4312578467 hasConcept C78458016 @default.
- W4312578467 hasConcept C86803240 @default.
- W4312578467 hasConcept C89600930 @default.
- W4312578467 hasConceptScore W4312578467C105795698 @default.
- W4312578467 hasConceptScore W4312578467C108583219 @default.
- W4312578467 hasConceptScore W4312578467C11413529 @default.
- W4312578467 hasConceptScore W4312578467C115961682 @default.
- W4312578467 hasConceptScore W4312578467C124504099 @default.
- W4312578467 hasConceptScore W4312578467C134306372 @default.
- W4312578467 hasConceptScore W4312578467C136389625 @default.