Matches in SemOpenAlex for { <https://semopenalex.org/work/W4280517621> ?p ?o ?g. }
- W4280517621 endingPage "103454" @default.
- W4280517621 startingPage "103454" @default.
- W4280517621 abstract "This paper studies the problem of Generalized Zero-shot Learning (G-ZSL), whose goal is to classify instances from both seen and unseen classes at the test time. We propose a novel domain division method to solve G-ZSL. Some previous models with domain division operations only calibrate the confident prediction of source classes (W-SVM (Scheirer et al., 2014)) or take target-class instances as outliers (Socher et al., 2013). In contrast, we propose to directly estimate and fine-tune the decision boundary between the source and the target classes. Specifically, we put forward a framework that enables to learn compositional domains by splitting the instances into Source, Target, and Uncertain domains and perform recognition in each domain, where the uncertain domain contains instances whose labels cannot be confidently predicted. We use two statistical tools, namely, bootstrapping and Kolmogorov–Smirnov (K–S) Test, to learn the compositional domains for G-ZSL. We validate our method extensively on multiple G-ZSL benchmarks, on which it achieves state-of-the-art performances. The codes are available on https://github.com/hendrydong/demo_zsl_domain_division." @default.
- W4280517621 created "2022-05-22" @default.
- W4280517621 creator A5003418019 @default.
- W4280517621 creator A5053011888 @default.
- W4280517621 creator A5061778641 @default.
- W4280517621 creator A5070302452 @default.
- W4280517621 creator A5084959430 @default.
- W4280517621 date "2022-08-01" @default.
- W4280517621 modified "2023-09-30" @default.
- W4280517621 title "Learning the Compositional Domains for Generalized Zero-shot Learning" @default.
- W4280517621 cites W1999245030 @default.
- W4280517621 cites W2018459374 @default.
- W4280517621 cites W2040305989 @default.
- W4280517621 cites W2100332042 @default.
- W4280517621 cites W2117897510 @default.
- W4280517621 cites W2119880843 @default.
- W4280517621 cites W2128532956 @default.
- W4280517621 cites W2132870739 @default.
- W4280517621 cites W2134604967 @default.
- W4280517621 cites W2141350700 @default.
- W4280517621 cites W2144182447 @default.
- W4280517621 cites W2289084343 @default.
- W4280517621 cites W2560129302 @default.
- W4280517621 cites W2883124384 @default.
- W4280517621 cites W2887567284 @default.
- W4280517621 cites W2924476266 @default.
- W4280517621 cites W2955087950 @default.
- W4280517621 cites W2963149653 @default.
- W4280517621 cites W2963325024 @default.
- W4280517621 cites W2963545832 @default.
- W4280517621 cites W2963846885 @default.
- W4280517621 cites W2963955422 @default.
- W4280517621 cites W2963960318 @default.
- W4280517621 cites W2979571231 @default.
- W4280517621 cites W2982407353 @default.
- W4280517621 cites W3034730995 @default.
- W4280517621 cites W3035655772 @default.
- W4280517621 cites W3098046716 @default.
- W4280517621 cites W3102616566 @default.
- W4280517621 cites W4212883601 @default.
- W4280517621 cites W4255375128 @default.
- W4280517621 cites W88868203 @default.
- W4280517621 doi "https://doi.org/10.1016/j.cviu.2022.103454" @default.
- W4280517621 hasPublicationYear "2022" @default.
- W4280517621 type Work @default.
- W4280517621 citedByCount "1" @default.
- W4280517621 countsByYear W42805176212023 @default.
- W4280517621 crossrefType "journal-article" @default.
- W4280517621 hasAuthorship W4280517621A5003418019 @default.
- W4280517621 hasAuthorship W4280517621A5053011888 @default.
- W4280517621 hasAuthorship W4280517621A5061778641 @default.
- W4280517621 hasAuthorship W4280517621A5070302452 @default.
- W4280517621 hasAuthorship W4280517621A5084959430 @default.
- W4280517621 hasConcept C11413529 @default.
- W4280517621 hasConcept C119857082 @default.
- W4280517621 hasConcept C12267149 @default.
- W4280517621 hasConcept C134306372 @default.
- W4280517621 hasConcept C153180895 @default.
- W4280517621 hasConcept C154945302 @default.
- W4280517621 hasConcept C2777212361 @default.
- W4280517621 hasConcept C33923547 @default.
- W4280517621 hasConcept C36503486 @default.
- W4280517621 hasConcept C41008148 @default.
- W4280517621 hasConcept C42023084 @default.
- W4280517621 hasConcept C60798267 @default.
- W4280517621 hasConcept C62354387 @default.
- W4280517621 hasConcept C79337645 @default.
- W4280517621 hasConcept C94375191 @default.
- W4280517621 hasConceptScore W4280517621C11413529 @default.
- W4280517621 hasConceptScore W4280517621C119857082 @default.
- W4280517621 hasConceptScore W4280517621C12267149 @default.
- W4280517621 hasConceptScore W4280517621C134306372 @default.
- W4280517621 hasConceptScore W4280517621C153180895 @default.
- W4280517621 hasConceptScore W4280517621C154945302 @default.
- W4280517621 hasConceptScore W4280517621C2777212361 @default.
- W4280517621 hasConceptScore W4280517621C33923547 @default.
- W4280517621 hasConceptScore W4280517621C36503486 @default.
- W4280517621 hasConceptScore W4280517621C41008148 @default.
- W4280517621 hasConceptScore W4280517621C42023084 @default.
- W4280517621 hasConceptScore W4280517621C60798267 @default.
- W4280517621 hasConceptScore W4280517621C62354387 @default.
- W4280517621 hasConceptScore W4280517621C79337645 @default.
- W4280517621 hasConceptScore W4280517621C94375191 @default.
- W4280517621 hasLocation W42805176211 @default.
- W4280517621 hasOpenAccess W4280517621 @default.
- W4280517621 hasPrimaryLocation W42805176211 @default.
- W4280517621 hasRelatedWork W2041399278 @default.
- W4280517621 hasRelatedWork W2056016498 @default.
- W4280517621 hasRelatedWork W2128276860 @default.
- W4280517621 hasRelatedWork W2136184105 @default.
- W4280517621 hasRelatedWork W2294344737 @default.
- W4280517621 hasRelatedWork W2336974148 @default.
- W4280517621 hasRelatedWork W2382626645 @default.
- W4280517621 hasRelatedWork W3013515612 @default.
- W4280517621 hasRelatedWork W2187500075 @default.
- W4280517621 hasRelatedWork W2345184372 @default.
- W4280517621 hasVolume "221" @default.
- W4280517621 isParatext "false" @default.