Matches in SemOpenAlex for { <https://semopenalex.org/work/W3186381566> ?p ?o ?g. }
Showing items 1 to 96 of
96
with 100 items per page.
- W3186381566 abstract "Standard zero-shot learning (ZSL) methods use a large number of seen categories to predict very few unseen categories while maintaining unified data splits and evaluation metrics. This has enabled the research community to advance notably towards formulating a standard benchmark ZSL algorithm. However, the most substantial impact of ZSL lies in enabling the prediction of a large number of unseen categories from very few seen categories within a specific domain. This permits the collection and annotation of training data for only a few previously seen categories, thereby significantly mitigating the training data collection and annotation process. We address the difficult problem of predicting a large number of unseen object categories from very few previously seen categories and propose a framework that enables us to examine the limits of inferring several unseen object categories from very few previously seen object categories, i.e., the limits of ZSL. We examine the functional dependence of the classification accuracy of unseen object classes on the number and types of previously seen classes and determine the minimum number and types of previously seen classes required to achieve a prespecified classification accuracy for the unseen classes on three standard ZSL data sets. An experimental comparison of the proposed framework to a prominent ZSL technique on these data sets shows that the proposed framework achieves higher classification accuracy on average while providing valuable insights into the unseen class inference process." @default.
- W3186381566 created "2021-08-02" @default.
- W3186381566 creator A5064001163 @default.
- W3186381566 creator A5064473585 @default.
- W3186381566 creator A5076312988 @default.
- W3186381566 date "2021-06-01" @default.
- W3186381566 modified "2023-09-27" @default.
- W3186381566 title "Exploring the Limits of Zero-Shot Learning - How Low Can You Go?" @default.
- W3186381566 cites W1595749721 @default.
- W3186381566 cites W1960364170 @default.
- W3186381566 cites W1987971958 @default.
- W3186381566 cites W2070148066 @default.
- W3186381566 cites W2081580037 @default.
- W3186381566 cites W2108598243 @default.
- W3186381566 cites W2109317801 @default.
- W3186381566 cites W2119880843 @default.
- W3186381566 cites W2124033848 @default.
- W3186381566 cites W2128532956 @default.
- W3186381566 cites W2141350700 @default.
- W3186381566 cites W2153579005 @default.
- W3186381566 cites W2156406284 @default.
- W3186381566 cites W2165232124 @default.
- W3186381566 cites W2187089797 @default.
- W3186381566 cites W2194775991 @default.
- W3186381566 cites W2250539671 @default.
- W3186381566 cites W2334493732 @default.
- W3186381566 cites W2493916176 @default.
- W3186381566 cites W2596142952 @default.
- W3186381566 cites W2963486920 @default.
- W3186381566 cites W2963960318 @default.
- W3186381566 cites W2964086552 @default.
- W3186381566 cites W2964149421 @default.
- W3186381566 cites W2964307109 @default.
- W3186381566 cites W2978753875 @default.
- W3186381566 cites W2979571231 @default.
- W3186381566 cites W3089741414 @default.
- W3186381566 cites W3100093508 @default.
- W3186381566 cites W3109728025 @default.
- W3186381566 cites W3132516639 @default.
- W3186381566 cites W652269744 @default.
- W3186381566 cites W93016980 @default.
- W3186381566 cites W14333344 @default.
- W3186381566 doi "https://doi.org/10.1109/cvprw53098.2021.00187" @default.
- W3186381566 hasPublicationYear "2021" @default.
- W3186381566 type Work @default.
- W3186381566 sameAs 3186381566 @default.
- W3186381566 citedByCount "0" @default.
- W3186381566 crossrefType "proceedings-article" @default.
- W3186381566 hasAuthorship W3186381566A5064001163 @default.
- W3186381566 hasAuthorship W3186381566A5064473585 @default.
- W3186381566 hasAuthorship W3186381566A5076312988 @default.
- W3186381566 hasConcept C111919701 @default.
- W3186381566 hasConcept C119857082 @default.
- W3186381566 hasConcept C124101348 @default.
- W3186381566 hasConcept C13280743 @default.
- W3186381566 hasConcept C153180895 @default.
- W3186381566 hasConcept C154945302 @default.
- W3186381566 hasConcept C185798385 @default.
- W3186381566 hasConcept C205649164 @default.
- W3186381566 hasConcept C2776214188 @default.
- W3186381566 hasConcept C2776321320 @default.
- W3186381566 hasConcept C2777212361 @default.
- W3186381566 hasConcept C2781238097 @default.
- W3186381566 hasConcept C41008148 @default.
- W3186381566 hasConcept C98045186 @default.
- W3186381566 hasConceptScore W3186381566C111919701 @default.
- W3186381566 hasConceptScore W3186381566C119857082 @default.
- W3186381566 hasConceptScore W3186381566C124101348 @default.
- W3186381566 hasConceptScore W3186381566C13280743 @default.
- W3186381566 hasConceptScore W3186381566C153180895 @default.
- W3186381566 hasConceptScore W3186381566C154945302 @default.
- W3186381566 hasConceptScore W3186381566C185798385 @default.
- W3186381566 hasConceptScore W3186381566C205649164 @default.
- W3186381566 hasConceptScore W3186381566C2776214188 @default.
- W3186381566 hasConceptScore W3186381566C2776321320 @default.
- W3186381566 hasConceptScore W3186381566C2777212361 @default.
- W3186381566 hasConceptScore W3186381566C2781238097 @default.
- W3186381566 hasConceptScore W3186381566C41008148 @default.
- W3186381566 hasConceptScore W3186381566C98045186 @default.
- W3186381566 hasLocation W31863815661 @default.
- W3186381566 hasOpenAccess W3186381566 @default.
- W3186381566 hasPrimaryLocation W31863815661 @default.
- W3186381566 hasRelatedWork W1969663039 @default.
- W3186381566 hasRelatedWork W2015107660 @default.
- W3186381566 hasRelatedWork W2511279186 @default.
- W3186381566 hasRelatedWork W2536452361 @default.
- W3186381566 hasRelatedWork W2756241593 @default.
- W3186381566 hasRelatedWork W2963058055 @default.
- W3186381566 hasRelatedWork W2994725031 @default.
- W3186381566 hasRelatedWork W3081076175 @default.
- W3186381566 hasRelatedWork W3136652852 @default.
- W3186381566 hasRelatedWork W4307964207 @default.
- W3186381566 isParatext "false" @default.
- W3186381566 isRetracted "false" @default.
- W3186381566 magId "3186381566" @default.
- W3186381566 workType "article" @default.