Matches in SemOpenAlex for { <https://semopenalex.org/work/W2914250053> ?p ?o ?g. }
Showing items 1 to 81 of
81
with 100 items per page.
- W2914250053 abstract "In many real-world prediction tasks, class labels include information about the relative ordering between labels, which is not captured by commonly-used loss functions such as multi-category cross-entropy. Recently, the deep learning community adopted ordinal regression frameworks to take such ordering information into account. Neural networks were equipped with ordinal regression capabilities by transforming ordinal targets into binary classification subtasks. However, this method suffers from inconsistencies among the different binary classifiers. To resolve these inconsistencies, we propose the COnsistent RAnk Logits (CORAL) framework with strong theoretical guarantees for rank-monotonicity and consistent confidence scores. Moreover, the proposed method is architecture-agnostic and can extend arbitrary state-of-the-art deep neural network classifiers for ordinal regression tasks. The empirical evaluation of the proposed rank-consistent method on a range of face-image datasets for age prediction shows a substantial reduction of the prediction error compared to the reference ordinal regression network." @default.
- W2914250053 created "2019-02-21" @default.
- W2914250053 creator A5052667764 @default.
- W2914250053 creator A5053156269 @default.
- W2914250053 creator A5056930369 @default.
- W2914250053 date "2019-01-20" @default.
- W2914250053 modified "2023-09-24" @default.
- W2914250053 title "Rank Consistent Logits for Ordinal Regression with Convolutional Neural Networks" @default.
- W2914250053 hasPublicationYear "2019" @default.
- W2914250053 type Work @default.
- W2914250053 sameAs 2914250053 @default.
- W2914250053 citedByCount "0" @default.
- W2914250053 crossrefType "posted-content" @default.
- W2914250053 hasAuthorship W2914250053A5052667764 @default.
- W2914250053 hasAuthorship W2914250053A5053156269 @default.
- W2914250053 hasAuthorship W2914250053A5056930369 @default.
- W2914250053 hasConcept C105795698 @default.
- W2914250053 hasConcept C106301342 @default.
- W2914250053 hasConcept C110313322 @default.
- W2914250053 hasConcept C114614502 @default.
- W2914250053 hasConcept C119857082 @default.
- W2914250053 hasConcept C121332964 @default.
- W2914250053 hasConcept C12267149 @default.
- W2914250053 hasConcept C153180895 @default.
- W2914250053 hasConcept C154945302 @default.
- W2914250053 hasConcept C164226766 @default.
- W2914250053 hasConcept C167981619 @default.
- W2914250053 hasConcept C33923547 @default.
- W2914250053 hasConcept C41008148 @default.
- W2914250053 hasConcept C50644808 @default.
- W2914250053 hasConcept C62520636 @default.
- W2914250053 hasConcept C66905080 @default.
- W2914250053 hasConcept C81363708 @default.
- W2914250053 hasConcept C83546350 @default.
- W2914250053 hasConcept C85461838 @default.
- W2914250053 hasConceptScore W2914250053C105795698 @default.
- W2914250053 hasConceptScore W2914250053C106301342 @default.
- W2914250053 hasConceptScore W2914250053C110313322 @default.
- W2914250053 hasConceptScore W2914250053C114614502 @default.
- W2914250053 hasConceptScore W2914250053C119857082 @default.
- W2914250053 hasConceptScore W2914250053C121332964 @default.
- W2914250053 hasConceptScore W2914250053C12267149 @default.
- W2914250053 hasConceptScore W2914250053C153180895 @default.
- W2914250053 hasConceptScore W2914250053C154945302 @default.
- W2914250053 hasConceptScore W2914250053C164226766 @default.
- W2914250053 hasConceptScore W2914250053C167981619 @default.
- W2914250053 hasConceptScore W2914250053C33923547 @default.
- W2914250053 hasConceptScore W2914250053C41008148 @default.
- W2914250053 hasConceptScore W2914250053C50644808 @default.
- W2914250053 hasConceptScore W2914250053C62520636 @default.
- W2914250053 hasConceptScore W2914250053C66905080 @default.
- W2914250053 hasConceptScore W2914250053C81363708 @default.
- W2914250053 hasConceptScore W2914250053C83546350 @default.
- W2914250053 hasConceptScore W2914250053C85461838 @default.
- W2914250053 hasLocation W29142500531 @default.
- W2914250053 hasOpenAccess W2914250053 @default.
- W2914250053 hasPrimaryLocation W29142500531 @default.
- W2914250053 hasRelatedWork W1480144585 @default.
- W2914250053 hasRelatedWork W1984083244 @default.
- W2914250053 hasRelatedWork W2058475745 @default.
- W2914250053 hasRelatedWork W2067001387 @default.
- W2914250053 hasRelatedWork W2151447451 @default.
- W2914250053 hasRelatedWork W2280768717 @default.
- W2914250053 hasRelatedWork W2612220790 @default.
- W2914250053 hasRelatedWork W2744942261 @default.
- W2914250053 hasRelatedWork W2915064910 @default.
- W2914250053 hasRelatedWork W2945885813 @default.
- W2914250053 hasRelatedWork W2969911045 @default.
- W2914250053 hasRelatedWork W2993906597 @default.
- W2914250053 hasRelatedWork W3093316401 @default.
- W2914250053 hasRelatedWork W3097760447 @default.
- W2914250053 hasRelatedWork W3099723579 @default.
- W2914250053 hasRelatedWork W3118537478 @default.
- W2914250053 hasRelatedWork W3152788889 @default.
- W2914250053 hasRelatedWork W3210452439 @default.
- W2914250053 hasRelatedWork W3211775500 @default.
- W2914250053 hasRelatedWork W33026131 @default.
- W2914250053 isParatext "false" @default.
- W2914250053 isRetracted "false" @default.
- W2914250053 magId "2914250053" @default.
- W2914250053 workType "article" @default.