Matches in SemOpenAlex for { <https://semopenalex.org/work/W2520171856> ?p ?o ?g. }
Showing items 1 to 75 of
75
with 100 items per page.
- W2520171856 endingPage "599" @default.
- W2520171856 startingPage "585" @default.
- W2520171856 abstract "In structured prediction, it is standard procedure to discriminatively train a single model that is then used to make a single prediction for each input. This practice is simple but risky in many ways. For instance, models are often designed with tractability rather than faithfulness in mind. To hedge against such model misspecification, it may be useful to train multiple models that all are a reasonable fit to the training data, but at least one of which may hopefully make more valid predictions than the single model in standard procedure. We propose the Coulomb Structured SVM (CSSVM) as a means to obtain at training time a full ensemble of different models. At test time, these models can run in parallel and independently to make diverse predictions. We demonstrate on challenging tasks from computer vision that some of these diverse predictions have significantly lower task loss than that of a single model, and improve over state-of-the-art diversity encouraging approaches." @default.
- W2520171856 created "2016-09-23" @default.
- W2520171856 creator A5011308250 @default.
- W2520171856 creator A5020048224 @default.
- W2520171856 creator A5087166497 @default.
- W2520171856 date "2016-01-01" @default.
- W2520171856 modified "2023-10-14" @default.
- W2520171856 title "Learning Diverse Models: The Coulomb Structured Support Vector Machine" @default.
- W2520171856 cites W1492409332 @default.
- W2520171856 cites W1964884769 @default.
- W2520171856 cites W1980551704 @default.
- W2520171856 cites W2000028107 @default.
- W2520171856 cites W2012292069 @default.
- W2520171856 cites W2018044188 @default.
- W2520171856 cites W2019288156 @default.
- W2520171856 cites W2021102663 @default.
- W2520171856 cites W2024152572 @default.
- W2520171856 cites W2031489346 @default.
- W2520171856 cites W2068321739 @default.
- W2520171856 cites W2084196626 @default.
- W2520171856 cites W2106317217 @default.
- W2520171856 cites W2129085190 @default.
- W2520171856 cites W2138779671 @default.
- W2520171856 cites W2161278885 @default.
- W2520171856 cites W2162980292 @default.
- W2520171856 cites W2164918853 @default.
- W2520171856 cites W2203676611 @default.
- W2520171856 cites W2210014073 @default.
- W2520171856 cites W2216735140 @default.
- W2520171856 cites W3035438594 @default.
- W2520171856 doi "https://doi.org/10.1007/978-3-319-46487-9_36" @default.
- W2520171856 hasPublicationYear "2016" @default.
- W2520171856 type Work @default.
- W2520171856 sameAs 2520171856 @default.
- W2520171856 citedByCount "4" @default.
- W2520171856 countsByYear W25201718562017 @default.
- W2520171856 countsByYear W25201718562021 @default.
- W2520171856 countsByYear W25201718562022 @default.
- W2520171856 crossrefType "book-chapter" @default.
- W2520171856 hasAuthorship W2520171856A5011308250 @default.
- W2520171856 hasAuthorship W2520171856A5020048224 @default.
- W2520171856 hasAuthorship W2520171856A5087166497 @default.
- W2520171856 hasConcept C121332964 @default.
- W2520171856 hasConcept C12267149 @default.
- W2520171856 hasConcept C147120987 @default.
- W2520171856 hasConcept C154945302 @default.
- W2520171856 hasConcept C185544564 @default.
- W2520171856 hasConcept C41008148 @default.
- W2520171856 hasConcept C9342510 @default.
- W2520171856 hasConceptScore W2520171856C121332964 @default.
- W2520171856 hasConceptScore W2520171856C12267149 @default.
- W2520171856 hasConceptScore W2520171856C147120987 @default.
- W2520171856 hasConceptScore W2520171856C154945302 @default.
- W2520171856 hasConceptScore W2520171856C185544564 @default.
- W2520171856 hasConceptScore W2520171856C41008148 @default.
- W2520171856 hasConceptScore W2520171856C9342510 @default.
- W2520171856 hasLocation W25201718561 @default.
- W2520171856 hasOpenAccess W2520171856 @default.
- W2520171856 hasPrimaryLocation W25201718561 @default.
- W2520171856 hasRelatedWork W169774068 @default.
- W2520171856 hasRelatedWork W1855281999 @default.
- W2520171856 hasRelatedWork W2101819884 @default.
- W2520171856 hasRelatedWork W2109197306 @default.
- W2520171856 hasRelatedWork W2153189372 @default.
- W2520171856 hasRelatedWork W2355927362 @default.
- W2520171856 hasRelatedWork W2772879096 @default.
- W2520171856 hasRelatedWork W2937631562 @default.
- W2520171856 hasRelatedWork W3174451172 @default.
- W2520171856 hasRelatedWork W4285503465 @default.
- W2520171856 isParatext "false" @default.
- W2520171856 isRetracted "false" @default.
- W2520171856 magId "2520171856" @default.
- W2520171856 workType "book-chapter" @default.