Matches in SemOpenAlex for { <https://semopenalex.org/work/W4382461844> ?p ?o ?g. }
Showing items 1 to 85 of
85
with 100 items per page.
- W4382461844 endingPage "1212" @default.
- W4382461844 startingPage "1205" @default.
- W4382461844 abstract "Recently, the joint learning framework (JOINT) integrates matching based transductive reasoning and online inductive learning to achieve accurate and robust semi-supervised video object segmentation (SVOS). However, using the mask embedding as the label to guide the generation of target features in the two branches may result in inadequate target representation and degrade the performance. Besides, how to reasonably fuse the target features in the two different branches rather than simply adding them together to avoid the adverse effect of one dominant branch has not been investigated. In this paper, we propose a novel framework that emphasizes Learning to Learn Better (LLB) target features for SVOS, termed LLB, where we design the discriminative label generation module (DLGM) and the adaptive fusion module to address these issues. Technically, the DLGM takes the background-filtered frame instead of the target mask as input and adopts a lightweight encoder to generate the target features, which serves as the label of the online few-shot learner and the value of the decoder in the transformer to guide the two branches to learn more discriminative target representation. The adaptive fusion module maintains a learnable gate for each branch, which reweighs the element-wise feature representation and allows an adaptive amount of target information in each branch flowing to the fused target feature, thus preventing one branch from being dominant and making the target feature more robust to distractor. Extensive experiments on public benchmarks show that our proposed LLB method achieves state-of-the-art performance." @default.
- W4382461844 created "2023-06-29" @default.
- W4382461844 creator A5017947172 @default.
- W4382461844 creator A5024278302 @default.
- W4382461844 creator A5063568458 @default.
- W4382461844 creator A5074103823 @default.
- W4382461844 date "2023-06-26" @default.
- W4382461844 modified "2023-09-23" @default.
- W4382461844 title "Learning to Learn Better for Video Object Segmentation" @default.
- W4382461844 doi "https://doi.org/10.1609/aaai.v37i1.25203" @default.
- W4382461844 hasPublicationYear "2023" @default.
- W4382461844 type Work @default.
- W4382461844 citedByCount "0" @default.
- W4382461844 crossrefType "journal-article" @default.
- W4382461844 hasAuthorship W4382461844A5017947172 @default.
- W4382461844 hasAuthorship W4382461844A5024278302 @default.
- W4382461844 hasAuthorship W4382461844A5063568458 @default.
- W4382461844 hasAuthorship W4382461844A5074103823 @default.
- W4382461844 hasBestOaLocation W43824618441 @default.
- W4382461844 hasConcept C101738243 @default.
- W4382461844 hasConcept C108583219 @default.
- W4382461844 hasConcept C111919701 @default.
- W4382461844 hasConcept C118505674 @default.
- W4382461844 hasConcept C119599485 @default.
- W4382461844 hasConcept C127413603 @default.
- W4382461844 hasConcept C138885662 @default.
- W4382461844 hasConcept C153180895 @default.
- W4382461844 hasConcept C154945302 @default.
- W4382461844 hasConcept C165801399 @default.
- W4382461844 hasConcept C17744445 @default.
- W4382461844 hasConcept C199539241 @default.
- W4382461844 hasConcept C2776359362 @default.
- W4382461844 hasConcept C2776401178 @default.
- W4382461844 hasConcept C31972630 @default.
- W4382461844 hasConcept C41008148 @default.
- W4382461844 hasConcept C41608201 @default.
- W4382461844 hasConcept C41895202 @default.
- W4382461844 hasConcept C59404180 @default.
- W4382461844 hasConcept C66322947 @default.
- W4382461844 hasConcept C89600930 @default.
- W4382461844 hasConcept C94625758 @default.
- W4382461844 hasConcept C97931131 @default.
- W4382461844 hasConceptScore W4382461844C101738243 @default.
- W4382461844 hasConceptScore W4382461844C108583219 @default.
- W4382461844 hasConceptScore W4382461844C111919701 @default.
- W4382461844 hasConceptScore W4382461844C118505674 @default.
- W4382461844 hasConceptScore W4382461844C119599485 @default.
- W4382461844 hasConceptScore W4382461844C127413603 @default.
- W4382461844 hasConceptScore W4382461844C138885662 @default.
- W4382461844 hasConceptScore W4382461844C153180895 @default.
- W4382461844 hasConceptScore W4382461844C154945302 @default.
- W4382461844 hasConceptScore W4382461844C165801399 @default.
- W4382461844 hasConceptScore W4382461844C17744445 @default.
- W4382461844 hasConceptScore W4382461844C199539241 @default.
- W4382461844 hasConceptScore W4382461844C2776359362 @default.
- W4382461844 hasConceptScore W4382461844C2776401178 @default.
- W4382461844 hasConceptScore W4382461844C31972630 @default.
- W4382461844 hasConceptScore W4382461844C41008148 @default.
- W4382461844 hasConceptScore W4382461844C41608201 @default.
- W4382461844 hasConceptScore W4382461844C41895202 @default.
- W4382461844 hasConceptScore W4382461844C59404180 @default.
- W4382461844 hasConceptScore W4382461844C66322947 @default.
- W4382461844 hasConceptScore W4382461844C89600930 @default.
- W4382461844 hasConceptScore W4382461844C94625758 @default.
- W4382461844 hasConceptScore W4382461844C97931131 @default.
- W4382461844 hasIssue "1" @default.
- W4382461844 hasLocation W43824618441 @default.
- W4382461844 hasOpenAccess W4382461844 @default.
- W4382461844 hasPrimaryLocation W43824618441 @default.
- W4382461844 hasRelatedWork W2467256294 @default.
- W4382461844 hasRelatedWork W2546942002 @default.
- W4382461844 hasRelatedWork W2785535669 @default.
- W4382461844 hasRelatedWork W2805177060 @default.
- W4382461844 hasRelatedWork W2998168123 @default.
- W4382461844 hasRelatedWork W3126201013 @default.
- W4382461844 hasRelatedWork W3136048210 @default.
- W4382461844 hasRelatedWork W4224919531 @default.
- W4382461844 hasRelatedWork W4287995534 @default.
- W4382461844 hasRelatedWork W4297904004 @default.
- W4382461844 hasVolume "37" @default.
- W4382461844 isParatext "false" @default.
- W4382461844 isRetracted "false" @default.
- W4382461844 workType "article" @default.