Matches in SemOpenAlex for { <https://semopenalex.org/work/W2487510721> ?p ?o ?g. }
Showing items 1 to 86 of
86
with 100 items per page.
- W2487510721 abstract "One of the key challenges in machine learning is to design a computationally efficient multi-class classifier while maintaining the output accuracy and performance. In this paper, we present a tree-based classifier: Attention Tree (ATree) for large-scale image classification that uses recursive Adaboost training to construct a visual attention hierarchy. The proposed attention model is inspired from the biological 'selective tuning mechanism for cortical visual processing'. We exploit the inherent feature similarity across images in datasets to identify the input variability and use recursive optimization procedure, to determine data partitioning at each node, thereby, learning the attention hierarchy. A set of binary classifiers is organized on top of the learnt hierarchy to minimize the overall test-time complexity. The attention model maximizes the margins for the binary classifiers for optimal decision boundary modelling, leading to better performance at minimal complexity. The proposed framework has been evaluated on both Caltech-256 and SUN datasets and achieves accuracy improvement over state-of-the-art tree-based methods at significantly lower computational cost." @default.
- W2487510721 created "2016-08-23" @default.
- W2487510721 creator A5029882806 @default.
- W2487510721 creator A5050310538 @default.
- W2487510721 date "2016-08-01" @default.
- W2487510721 modified "2023-09-27" @default.
- W2487510721 title "Attention Tree: Learning Hierarchies of Visual Features for Large-Scale Image Recognition." @default.
- W2487510721 cites W1546961578 @default.
- W2487510721 cites W1677182931 @default.
- W2487510721 cites W2025862220 @default.
- W2487510721 cites W2063739784 @default.
- W2487510721 cites W2091350393 @default.
- W2487510721 cites W2116339064 @default.
- W2487510721 cites W2191618812 @default.
- W2487510721 hasPublicationYear "2016" @default.
- W2487510721 type Work @default.
- W2487510721 sameAs 2487510721 @default.
- W2487510721 citedByCount "0" @default.
- W2487510721 crossrefType "posted-content" @default.
- W2487510721 hasAuthorship W2487510721A5029882806 @default.
- W2487510721 hasAuthorship W2487510721A5050310538 @default.
- W2487510721 hasConcept C11413529 @default.
- W2487510721 hasConcept C119857082 @default.
- W2487510721 hasConcept C12267149 @default.
- W2487510721 hasConcept C153180895 @default.
- W2487510721 hasConcept C154945302 @default.
- W2487510721 hasConcept C162324750 @default.
- W2487510721 hasConcept C163797641 @default.
- W2487510721 hasConcept C179799912 @default.
- W2487510721 hasConcept C197855036 @default.
- W2487510721 hasConcept C199360897 @default.
- W2487510721 hasConcept C2781289151 @default.
- W2487510721 hasConcept C31170391 @default.
- W2487510721 hasConcept C34447519 @default.
- W2487510721 hasConcept C41008148 @default.
- W2487510721 hasConcept C42023084 @default.
- W2487510721 hasConcept C66905080 @default.
- W2487510721 hasConcept C73752529 @default.
- W2487510721 hasConcept C84525736 @default.
- W2487510721 hasConcept C95623464 @default.
- W2487510721 hasConceptScore W2487510721C11413529 @default.
- W2487510721 hasConceptScore W2487510721C119857082 @default.
- W2487510721 hasConceptScore W2487510721C12267149 @default.
- W2487510721 hasConceptScore W2487510721C153180895 @default.
- W2487510721 hasConceptScore W2487510721C154945302 @default.
- W2487510721 hasConceptScore W2487510721C162324750 @default.
- W2487510721 hasConceptScore W2487510721C163797641 @default.
- W2487510721 hasConceptScore W2487510721C179799912 @default.
- W2487510721 hasConceptScore W2487510721C197855036 @default.
- W2487510721 hasConceptScore W2487510721C199360897 @default.
- W2487510721 hasConceptScore W2487510721C2781289151 @default.
- W2487510721 hasConceptScore W2487510721C31170391 @default.
- W2487510721 hasConceptScore W2487510721C34447519 @default.
- W2487510721 hasConceptScore W2487510721C41008148 @default.
- W2487510721 hasConceptScore W2487510721C42023084 @default.
- W2487510721 hasConceptScore W2487510721C66905080 @default.
- W2487510721 hasConceptScore W2487510721C73752529 @default.
- W2487510721 hasConceptScore W2487510721C84525736 @default.
- W2487510721 hasConceptScore W2487510721C95623464 @default.
- W2487510721 hasLocation W24875107211 @default.
- W2487510721 hasOpenAccess W2487510721 @default.
- W2487510721 hasPrimaryLocation W24875107211 @default.
- W2487510721 hasRelatedWork W180670077 @default.
- W2487510721 hasRelatedWork W2025081100 @default.
- W2487510721 hasRelatedWork W2030771549 @default.
- W2487510721 hasRelatedWork W2032250608 @default.
- W2487510721 hasRelatedWork W2077551920 @default.
- W2487510721 hasRelatedWork W2107010062 @default.
- W2487510721 hasRelatedWork W2128304800 @default.
- W2487510721 hasRelatedWork W2158003960 @default.
- W2487510721 hasRelatedWork W2183238986 @default.
- W2487510721 hasRelatedWork W2340646070 @default.
- W2487510721 hasRelatedWork W2468718006 @default.
- W2487510721 hasRelatedWork W2512569467 @default.
- W2487510721 hasRelatedWork W2765611817 @default.
- W2487510721 hasRelatedWork W2789160147 @default.
- W2487510721 hasRelatedWork W2902859454 @default.
- W2487510721 hasRelatedWork W2969065665 @default.
- W2487510721 hasRelatedWork W3006767546 @default.
- W2487510721 hasRelatedWork W3134591977 @default.
- W2487510721 hasRelatedWork W3190568003 @default.
- W2487510721 hasRelatedWork W3086807020 @default.
- W2487510721 isParatext "false" @default.
- W2487510721 isRetracted "false" @default.
- W2487510721 magId "2487510721" @default.
- W2487510721 workType "article" @default.