Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386075720> ?p ?o ?g. }
- W4386075720 abstract "Click-based interactive segmentation (IS) aims to extract the target objects under user interaction. For this task, most of the current deep learning (DL)-based methods mainly follow the general pipelines of semantic segmentation. Albeit achieving promising performance, they do not fully and explicitly utilize and propagate the click information, inevitably leading to unsatisfactory segmentation results, even at clicked points. Against this issue, in this paper, we propose to formulate the IS task as a Gaussian process (GP)-based pixel-wise binary classification model on each image. To solve this model, we utilize amortized variational inference to approximate the intractable GP posterior in a data-driven manner and then decouple the approximated GP posterior into double space forms for efficient sampling with linear complexity. Then, we correspondingly construct a GP classification framework, named GPCIS, which is integrated with the deep kernel learning mechanism for more flexibility. The main specificities of the proposed GPCIS lie in: 1) Under the explicit guidance of the derived GP posterior, the information contained in clicks can be finely propagated to the entire image and then boost the segmentation; 2) The accuracy of predictions at clicks has good theoretical support. These merits of GPCIS as well as its good generality and high efficiency are substantiated by comprehensive experiments on several benchmarks, as compared with representative methods both quantitatively and qualitatively. Codes will be released at https://github.com/zmhhlnz/GPCIS_CVPR2023." @default.
- W4386075720 created "2023-08-23" @default.
- W4386075720 creator A5033020983 @default.
- W4386075720 creator A5045656118 @default.
- W4386075720 creator A5051649145 @default.
- W4386075720 creator A5066261801 @default.
- W4386075720 creator A5077647946 @default.
- W4386075720 creator A5085129889 @default.
- W4386075720 creator A5091017287 @default.
- W4386075720 date "2023-06-01" @default.
- W4386075720 modified "2023-09-26" @default.
- W4386075720 title "Interactive Segmentation as Gaussian Process Classification" @default.
- W4386075720 cites W1903029394 @default.
- W4386075720 cites W1995911388 @default.
- W4386075720 cites W2003192903 @default.
- W4386075720 cites W2031489346 @default.
- W4386075720 cites W2036084078 @default.
- W4386075720 cites W2116719896 @default.
- W4386075720 cites W2124351162 @default.
- W4386075720 cites W2125637308 @default.
- W4386075720 cites W2144794286 @default.
- W4386075720 cites W2168555635 @default.
- W4386075720 cites W218164292 @default.
- W4386075720 cites W2194775991 @default.
- W4386075720 cites W2300469113 @default.
- W4386075720 cites W2412782625 @default.
- W4386075720 cites W2470139095 @default.
- W4386075720 cites W2496132042 @default.
- W4386075720 cites W2531409750 @default.
- W4386075720 cites W2609825896 @default.
- W4386075720 cites W2776163999 @default.
- W4386075720 cites W2795276939 @default.
- W4386075720 cites W2798769484 @default.
- W4386075720 cites W2948553897 @default.
- W4386075720 cites W2963446712 @default.
- W4386075720 cites W2967279867 @default.
- W4386075720 cites W2979394918 @default.
- W4386075720 cites W3000508506 @default.
- W4386075720 cites W3014641072 @default.
- W4386075720 cites W3034278117 @default.
- W4386075720 cites W3034550159 @default.
- W4386075720 cites W3034586976 @default.
- W4386075720 cites W4214588164 @default.
- W4386075720 cites W4312336332 @default.
- W4386075720 cites W4312603257 @default.
- W4386075720 doi "https://doi.org/10.1109/cvpr52729.2023.01867" @default.
- W4386075720 hasPublicationYear "2023" @default.
- W4386075720 type Work @default.
- W4386075720 citedByCount "0" @default.
- W4386075720 crossrefType "proceedings-article" @default.
- W4386075720 hasAuthorship W4386075720A5033020983 @default.
- W4386075720 hasAuthorship W4386075720A5045656118 @default.
- W4386075720 hasAuthorship W4386075720A5051649145 @default.
- W4386075720 hasAuthorship W4386075720A5066261801 @default.
- W4386075720 hasAuthorship W4386075720A5077647946 @default.
- W4386075720 hasAuthorship W4386075720A5085129889 @default.
- W4386075720 hasAuthorship W4386075720A5091017287 @default.
- W4386075720 hasConcept C105795698 @default.
- W4386075720 hasConcept C111919701 @default.
- W4386075720 hasConcept C114614502 @default.
- W4386075720 hasConcept C119857082 @default.
- W4386075720 hasConcept C121332964 @default.
- W4386075720 hasConcept C12267149 @default.
- W4386075720 hasConcept C124504099 @default.
- W4386075720 hasConcept C153180895 @default.
- W4386075720 hasConcept C154945302 @default.
- W4386075720 hasConcept C15744967 @default.
- W4386075720 hasConcept C162324750 @default.
- W4386075720 hasConcept C163716315 @default.
- W4386075720 hasConcept C187736073 @default.
- W4386075720 hasConcept C199360897 @default.
- W4386075720 hasConcept C2776214188 @default.
- W4386075720 hasConcept C2780451532 @default.
- W4386075720 hasConcept C2780598303 @default.
- W4386075720 hasConcept C2780767217 @default.
- W4386075720 hasConcept C33923547 @default.
- W4386075720 hasConcept C41008148 @default.
- W4386075720 hasConcept C43521106 @default.
- W4386075720 hasConcept C542102704 @default.
- W4386075720 hasConcept C61326573 @default.
- W4386075720 hasConcept C62520636 @default.
- W4386075720 hasConcept C65885262 @default.
- W4386075720 hasConcept C66905080 @default.
- W4386075720 hasConcept C74193536 @default.
- W4386075720 hasConcept C89600930 @default.
- W4386075720 hasConcept C98045186 @default.
- W4386075720 hasConceptScore W4386075720C105795698 @default.
- W4386075720 hasConceptScore W4386075720C111919701 @default.
- W4386075720 hasConceptScore W4386075720C114614502 @default.
- W4386075720 hasConceptScore W4386075720C119857082 @default.
- W4386075720 hasConceptScore W4386075720C121332964 @default.
- W4386075720 hasConceptScore W4386075720C12267149 @default.
- W4386075720 hasConceptScore W4386075720C124504099 @default.
- W4386075720 hasConceptScore W4386075720C153180895 @default.
- W4386075720 hasConceptScore W4386075720C154945302 @default.
- W4386075720 hasConceptScore W4386075720C15744967 @default.
- W4386075720 hasConceptScore W4386075720C162324750 @default.
- W4386075720 hasConceptScore W4386075720C163716315 @default.
- W4386075720 hasConceptScore W4386075720C187736073 @default.
- W4386075720 hasConceptScore W4386075720C199360897 @default.