Matches in SemOpenAlex for { <https://semopenalex.org/work/W3210700258> ?p ?o ?g. }
Showing items 1 to 96 of
96
with 100 items per page.
- W3210700258 abstract "Prototype learning has been widely explored for few-shot segmentation. Existing methods typically learn the prototype from the foreground features of all support images, which rarely consider the background similarities between the query images and the support images. This unbalanced prototype learning strategy limits its capability to mutually correct the segmentation errors between the foreground and background. In this paper, we propose a Complementary Prototype Learning and Cascaded Refinement (CPLCR) network for few-shot segmentation. Firstly, both the foreground and background features of the support images are used to learn our complementary prototypes. Then, the foreground and background similarity maps are jointly derived between the query image feature and our complementary prototypes, which capture more comprehensive prior information. Finally, we fuse the query image feature, foreground prototype and the foreground/background similarity maps together, and feed them to a cascaded refinement module, which recursively reuses the output of previous iteration to refine the segmentation result. Extensive experimental results show that the proposed CPLCR model outperforms many state-of-the-art methods for 1-shot and 5-shot segmentation." @default.
- W3210700258 created "2021-11-08" @default.
- W3210700258 creator A5008589907 @default.
- W3210700258 creator A5016590465 @default.
- W3210700258 creator A5022134460 @default.
- W3210700258 creator A5044954967 @default.
- W3210700258 creator A5075737786 @default.
- W3210700258 creator A5077165659 @default.
- W3210700258 creator A5090911749 @default.
- W3210700258 date "2021-01-01" @default.
- W3210700258 modified "2023-10-18" @default.
- W3210700258 title "Few-Shot Segmentation via Complementary Prototype Learning and Cascaded Refinement" @default.
- W3210700258 cites W1903029394 @default.
- W3210700258 cites W2031489346 @default.
- W3210700258 cites W2144794286 @default.
- W3210700258 cites W2560023338 @default.
- W3210700258 cites W2799213142 @default.
- W3210700258 cites W2941198294 @default.
- W3210700258 cites W2963078159 @default.
- W3210700258 cites W2963599420 @default.
- W3210700258 cites W2963881378 @default.
- W3210700258 cites W2981787211 @default.
- W3210700258 cites W2983850069 @default.
- W3210700258 cites W2990230185 @default.
- W3210700258 cites W2994528761 @default.
- W3210700258 cites W3000932375 @default.
- W3210700258 cites W3033502887 @default.
- W3210700258 cites W3106906018 @default.
- W3210700258 cites W3108189450 @default.
- W3210700258 cites W3116921958 @default.
- W3210700258 doi "https://doi.org/10.1007/978-3-030-88013-2_40" @default.
- W3210700258 hasPublicationYear "2021" @default.
- W3210700258 type Work @default.
- W3210700258 sameAs 3210700258 @default.
- W3210700258 citedByCount "0" @default.
- W3210700258 crossrefType "book-chapter" @default.
- W3210700258 hasAuthorship W3210700258A5008589907 @default.
- W3210700258 hasAuthorship W3210700258A5016590465 @default.
- W3210700258 hasAuthorship W3210700258A5022134460 @default.
- W3210700258 hasAuthorship W3210700258A5044954967 @default.
- W3210700258 hasAuthorship W3210700258A5075737786 @default.
- W3210700258 hasAuthorship W3210700258A5077165659 @default.
- W3210700258 hasAuthorship W3210700258A5090911749 @default.
- W3210700258 hasConcept C103278499 @default.
- W3210700258 hasConcept C115961682 @default.
- W3210700258 hasConcept C119599485 @default.
- W3210700258 hasConcept C124504099 @default.
- W3210700258 hasConcept C127413603 @default.
- W3210700258 hasConcept C138885662 @default.
- W3210700258 hasConcept C141353440 @default.
- W3210700258 hasConcept C153180895 @default.
- W3210700258 hasConcept C154945302 @default.
- W3210700258 hasConcept C178790620 @default.
- W3210700258 hasConcept C185592680 @default.
- W3210700258 hasConcept C2776401178 @default.
- W3210700258 hasConcept C2778344882 @default.
- W3210700258 hasConcept C31972630 @default.
- W3210700258 hasConcept C41008148 @default.
- W3210700258 hasConcept C41895202 @default.
- W3210700258 hasConcept C65885262 @default.
- W3210700258 hasConcept C89600930 @default.
- W3210700258 hasConceptScore W3210700258C103278499 @default.
- W3210700258 hasConceptScore W3210700258C115961682 @default.
- W3210700258 hasConceptScore W3210700258C119599485 @default.
- W3210700258 hasConceptScore W3210700258C124504099 @default.
- W3210700258 hasConceptScore W3210700258C127413603 @default.
- W3210700258 hasConceptScore W3210700258C138885662 @default.
- W3210700258 hasConceptScore W3210700258C141353440 @default.
- W3210700258 hasConceptScore W3210700258C153180895 @default.
- W3210700258 hasConceptScore W3210700258C154945302 @default.
- W3210700258 hasConceptScore W3210700258C178790620 @default.
- W3210700258 hasConceptScore W3210700258C185592680 @default.
- W3210700258 hasConceptScore W3210700258C2776401178 @default.
- W3210700258 hasConceptScore W3210700258C2778344882 @default.
- W3210700258 hasConceptScore W3210700258C31972630 @default.
- W3210700258 hasConceptScore W3210700258C41008148 @default.
- W3210700258 hasConceptScore W3210700258C41895202 @default.
- W3210700258 hasConceptScore W3210700258C65885262 @default.
- W3210700258 hasConceptScore W3210700258C89600930 @default.
- W3210700258 hasLocation W32107002581 @default.
- W3210700258 hasOpenAccess W3210700258 @default.
- W3210700258 hasPrimaryLocation W32107002581 @default.
- W3210700258 hasRelatedWork W10746426 @default.
- W3210700258 hasRelatedWork W1086665 @default.
- W3210700258 hasRelatedWork W12703013 @default.
- W3210700258 hasRelatedWork W3542719 @default.
- W3210700258 hasRelatedWork W4017595 @default.
- W3210700258 hasRelatedWork W5859415 @default.
- W3210700258 hasRelatedWork W6212567 @default.
- W3210700258 hasRelatedWork W6426610 @default.
- W3210700258 hasRelatedWork W7433150 @default.
- W3210700258 hasRelatedWork W7789328 @default.
- W3210700258 isParatext "false" @default.
- W3210700258 isRetracted "false" @default.
- W3210700258 magId "3210700258" @default.
- W3210700258 workType "book-chapter" @default.