Matches in SemOpenAlex for { <https://semopenalex.org/work/W2897169468> ?p ?o ?g. }
- W2897169468 abstract "As attribute leaning brings mid-level semantic properties for objects, it can benefit many traditional learning problems in multimedia and computer vision communities. When facing the huge number of attributes, it is extremely challenging to automatically design a generalizable neural network for other attribute learning tasks. Even for a specific attribute domain, the exploration of the neural network architecture is always optimized by a combination of heuristics and grid search, from which there is a large space of possible choices to be searched. In this paper, Generalizable Attribute Learning Model (GALM) is proposed to automatically design the neural networks for generalizable attribute learning. The main novelty of GALM is that it fully exploits the Multi-Task Learning and Reinforcement Learning to speed up the search procedure. With the help of parameter sharing, GALM is able to transfer the pre-searched architecture to different attribute domains. In experiments, we comprehensively evaluate GALM on 251 attributes from three domains: animals, objects, and scenes. Extensive experimental results demonstrate that GALM significantly outperforms the state-of-the-art attribute learning approaches and previous neural architecture search methods on two generalizable attribute learning scenarios." @default.
- W2897169468 created "2018-10-26" @default.
- W2897169468 creator A5011680564 @default.
- W2897169468 creator A5021639720 @default.
- W2897169468 creator A5031882367 @default.
- W2897169468 creator A5053836350 @default.
- W2897169468 creator A5058898461 @default.
- W2897169468 creator A5062546146 @default.
- W2897169468 date "2018-10-15" @default.
- W2897169468 modified "2023-09-25" @default.
- W2897169468 title "Learning to Transfer" @default.
- W2897169468 cites W1954735160 @default.
- W2897169468 cites W2001723402 @default.
- W2897169468 cites W2028285070 @default.
- W2897169468 cites W2032699694 @default.
- W2897169468 cites W2098411764 @default.
- W2897169468 cites W2109317801 @default.
- W2897169468 cites W2123921497 @default.
- W2897169468 cites W2128532956 @default.
- W2897169468 cites W2139594308 @default.
- W2897169468 cites W2161381512 @default.
- W2897169468 cites W2201155408 @default.
- W2897169468 cites W2214409633 @default.
- W2897169468 cites W2289084343 @default.
- W2897169468 cites W2294130536 @default.
- W2897169468 cites W2526377930 @default.
- W2897169468 cites W2563032747 @default.
- W2897169468 cites W2605124728 @default.
- W2897169468 cites W2764273117 @default.
- W2897169468 cites W2773706593 @default.
- W2897169468 cites W2788721900 @default.
- W2897169468 cites W2962974137 @default.
- W2897169468 cites W2963097270 @default.
- W2897169468 cites W2964081807 @default.
- W2897169468 cites W2964086552 @default.
- W2897169468 cites W3143107425 @default.
- W2897169468 cites W4230563027 @default.
- W2897169468 doi "https://doi.org/10.1145/3240508.3240518" @default.
- W2897169468 hasPublicationYear "2018" @default.
- W2897169468 type Work @default.
- W2897169468 sameAs 2897169468 @default.
- W2897169468 citedByCount "15" @default.
- W2897169468 countsByYear W28971694682019 @default.
- W2897169468 countsByYear W28971694682021 @default.
- W2897169468 countsByYear W28971694682022 @default.
- W2897169468 countsByYear W28971694682023 @default.
- W2897169468 crossrefType "proceedings-article" @default.
- W2897169468 hasAuthorship W2897169468A5011680564 @default.
- W2897169468 hasAuthorship W2897169468A5021639720 @default.
- W2897169468 hasAuthorship W2897169468A5031882367 @default.
- W2897169468 hasAuthorship W2897169468A5053836350 @default.
- W2897169468 hasAuthorship W2897169468A5058898461 @default.
- W2897169468 hasAuthorship W2897169468A5062546146 @default.
- W2897169468 hasConcept C111919701 @default.
- W2897169468 hasConcept C119857082 @default.
- W2897169468 hasConcept C127705205 @default.
- W2897169468 hasConcept C134306372 @default.
- W2897169468 hasConcept C138885662 @default.
- W2897169468 hasConcept C150899416 @default.
- W2897169468 hasConcept C154945302 @default.
- W2897169468 hasConcept C162324750 @default.
- W2897169468 hasConcept C165696696 @default.
- W2897169468 hasConcept C187736073 @default.
- W2897169468 hasConcept C188888258 @default.
- W2897169468 hasConcept C19966478 @default.
- W2897169468 hasConcept C27206212 @default.
- W2897169468 hasConcept C2778738651 @default.
- W2897169468 hasConcept C2780451532 @default.
- W2897169468 hasConcept C28006648 @default.
- W2897169468 hasConcept C33923547 @default.
- W2897169468 hasConcept C36503486 @default.
- W2897169468 hasConcept C38652104 @default.
- W2897169468 hasConcept C41008148 @default.
- W2897169468 hasConcept C50644808 @default.
- W2897169468 hasConcept C77075516 @default.
- W2897169468 hasConcept C90509273 @default.
- W2897169468 hasConcept C97541855 @default.
- W2897169468 hasConceptScore W2897169468C111919701 @default.
- W2897169468 hasConceptScore W2897169468C119857082 @default.
- W2897169468 hasConceptScore W2897169468C127705205 @default.
- W2897169468 hasConceptScore W2897169468C134306372 @default.
- W2897169468 hasConceptScore W2897169468C138885662 @default.
- W2897169468 hasConceptScore W2897169468C150899416 @default.
- W2897169468 hasConceptScore W2897169468C154945302 @default.
- W2897169468 hasConceptScore W2897169468C162324750 @default.
- W2897169468 hasConceptScore W2897169468C165696696 @default.
- W2897169468 hasConceptScore W2897169468C187736073 @default.
- W2897169468 hasConceptScore W2897169468C188888258 @default.
- W2897169468 hasConceptScore W2897169468C19966478 @default.
- W2897169468 hasConceptScore W2897169468C27206212 @default.
- W2897169468 hasConceptScore W2897169468C2778738651 @default.
- W2897169468 hasConceptScore W2897169468C2780451532 @default.
- W2897169468 hasConceptScore W2897169468C28006648 @default.
- W2897169468 hasConceptScore W2897169468C33923547 @default.
- W2897169468 hasConceptScore W2897169468C36503486 @default.
- W2897169468 hasConceptScore W2897169468C38652104 @default.
- W2897169468 hasConceptScore W2897169468C41008148 @default.
- W2897169468 hasConceptScore W2897169468C50644808 @default.
- W2897169468 hasConceptScore W2897169468C77075516 @default.
- W2897169468 hasConceptScore W2897169468C90509273 @default.