Matches in SemOpenAlex for { <https://semopenalex.org/work/W4312635568> ?p ?o ?g. }
- W4312635568 endingPage "52" @default.
- W4312635568 startingPage "36" @default.
- W4312635568 abstract "Few-shot segmentation (FSS) aims to segment objects in a given query image with only a few labelled support images. The limited support information makes it an extremely challenging task. Most previous best-performing methods adopt prototypical learning or affinity learning. Nevertheless, they either neglect to further utilize support pixels for facilitating segmentation and lose spatial information, or are not robust to noisy pixels and computationally expensive. In this work, we propose a novel end-to-end adaptive agent transformer (AAFormer) to integrate prototypical and affinity learning to exploit the complementarity between them via a transformer encoder-decoder architecture, including a representation encoder, an agent learning decoder and an agent matching decoder. The proposed AAFormer enjoys several merits. First, to learn agent tokens well without any explicit supervision, and to make agent tokens capable of dividing different objects into diverse parts in an adaptive manner, we customize the agent learning decoder according to the three characteristics of context awareness, spatial awareness and diversity. Second, the proposed agent matching decoder is responsible for decomposing the direct pixel-level matching matrix into two more computationally-friendly matrices to suppress the noisy pixels. Extensive experimental results on two standard benchmarks demonstrate that our AAFormer performs favorably against state-of-the-art FSS methods." @default.
- W4312635568 created "2023-01-05" @default.
- W4312635568 creator A5011634228 @default.
- W4312635568 creator A5050423772 @default.
- W4312635568 creator A5077558876 @default.
- W4312635568 creator A5091384842 @default.
- W4312635568 date "2022-01-01" @default.
- W4312635568 modified "2023-10-06" @default.
- W4312635568 title "Adaptive Agent Transformer for Few-Shot Segmentation" @default.
- W4312635568 cites W1507506748 @default.
- W4312635568 cites W1861492603 @default.
- W4312635568 cites W1903029394 @default.
- W4312635568 cites W2031489346 @default.
- W4312635568 cites W2117539524 @default.
- W4312635568 cites W2194775991 @default.
- W4312635568 cites W2412782625 @default.
- W4312635568 cites W2560023338 @default.
- W4312635568 cites W2963078159 @default.
- W4312635568 cites W2963599420 @default.
- W4312635568 cites W2964309882 @default.
- W4312635568 cites W2981787211 @default.
- W4312635568 cites W2983850069 @default.
- W4312635568 cites W2990230185 @default.
- W4312635568 cites W3033502887 @default.
- W4312635568 cites W3094901756 @default.
- W4312635568 cites W3096609285 @default.
- W4312635568 cites W3106906018 @default.
- W4312635568 cites W3107884359 @default.
- W4312635568 cites W3108187451 @default.
- W4312635568 cites W3108189450 @default.
- W4312635568 cites W3166574225 @default.
- W4312635568 cites W3167044851 @default.
- W4312635568 cites W3167453437 @default.
- W4312635568 cites W3167559252 @default.
- W4312635568 cites W3169024950 @default.
- W4312635568 cites W3170841864 @default.
- W4312635568 cites W3171581326 @default.
- W4312635568 cites W3176065502 @default.
- W4312635568 cites W3203637842 @default.
- W4312635568 cites W3204077273 @default.
- W4312635568 cites W4214893857 @default.
- W4312635568 cites W4214951593 @default.
- W4312635568 cites W4312815172 @default.
- W4312635568 doi "https://doi.org/10.1007/978-3-031-19818-2_3" @default.
- W4312635568 hasPublicationYear "2022" @default.
- W4312635568 type Work @default.
- W4312635568 citedByCount "3" @default.
- W4312635568 countsByYear W43126355682023 @default.
- W4312635568 crossrefType "book-chapter" @default.
- W4312635568 hasAuthorship W4312635568A5011634228 @default.
- W4312635568 hasAuthorship W4312635568A5050423772 @default.
- W4312635568 hasAuthorship W4312635568A5077558876 @default.
- W4312635568 hasAuthorship W4312635568A5091384842 @default.
- W4312635568 hasConcept C111919701 @default.
- W4312635568 hasConcept C118505674 @default.
- W4312635568 hasConcept C119857082 @default.
- W4312635568 hasConcept C121332964 @default.
- W4312635568 hasConcept C124504099 @default.
- W4312635568 hasConcept C153180895 @default.
- W4312635568 hasConcept C154945302 @default.
- W4312635568 hasConcept C160633673 @default.
- W4312635568 hasConcept C165696696 @default.
- W4312635568 hasConcept C165801399 @default.
- W4312635568 hasConcept C31972630 @default.
- W4312635568 hasConcept C38652104 @default.
- W4312635568 hasConcept C41008148 @default.
- W4312635568 hasConcept C62520636 @default.
- W4312635568 hasConcept C66322947 @default.
- W4312635568 hasConcept C89600930 @default.
- W4312635568 hasConcept C97541855 @default.
- W4312635568 hasConceptScore W4312635568C111919701 @default.
- W4312635568 hasConceptScore W4312635568C118505674 @default.
- W4312635568 hasConceptScore W4312635568C119857082 @default.
- W4312635568 hasConceptScore W4312635568C121332964 @default.
- W4312635568 hasConceptScore W4312635568C124504099 @default.
- W4312635568 hasConceptScore W4312635568C153180895 @default.
- W4312635568 hasConceptScore W4312635568C154945302 @default.
- W4312635568 hasConceptScore W4312635568C160633673 @default.
- W4312635568 hasConceptScore W4312635568C165696696 @default.
- W4312635568 hasConceptScore W4312635568C165801399 @default.
- W4312635568 hasConceptScore W4312635568C31972630 @default.
- W4312635568 hasConceptScore W4312635568C38652104 @default.
- W4312635568 hasConceptScore W4312635568C41008148 @default.
- W4312635568 hasConceptScore W4312635568C62520636 @default.
- W4312635568 hasConceptScore W4312635568C66322947 @default.
- W4312635568 hasConceptScore W4312635568C89600930 @default.
- W4312635568 hasConceptScore W4312635568C97541855 @default.
- W4312635568 hasLocation W43126355681 @default.
- W4312635568 hasOpenAccess W4312635568 @default.
- W4312635568 hasPrimaryLocation W43126355681 @default.
- W4312635568 hasRelatedWork W121273120 @default.
- W4312635568 hasRelatedWork W1669643531 @default.
- W4312635568 hasRelatedWork W2005437358 @default.
- W4312635568 hasRelatedWork W2008656436 @default.
- W4312635568 hasRelatedWork W2023558673 @default.
- W4312635568 hasRelatedWork W2134924024 @default.
- W4312635568 hasRelatedWork W2337415362 @default.
- W4312635568 hasRelatedWork W2517104666 @default.