Matches in SemOpenAlex for { <https://semopenalex.org/work/W3213333886> ?p ?o ?g. }
Showing items 1 to 78 of
78
with 100 items per page.
- W3213333886 abstract "Label noise will degenerate the performance of deep learning algorithms because deep neural networks easily overfit label errors. Let X and Y denote the instance and clean label, respectively. When Y is a cause of X, according to which many datasets have been constructed, e.g., SVHN and CIFAR, the distributions of P(X) and P(Y|X) are entangled. This means that the unsupervised instances are helpful to learn the classifier and thus reduce the side effect of label noise. However, it remains elusive on how to exploit the causal information to handle the label noise problem. In this paper, by leveraging a structural causal model, we propose a novel generative approach for instance-dependent label-noise learning. In particular, we show that properly modeling the instances will contribute to the identifiability of the label noise transition matrix and thus lead to a better classifier. Empirically, our method outperforms all state-of-the-art methods on both synthetic and real-world label-noise datasets." @default.
- W3213333886 created "2021-11-22" @default.
- W3213333886 creator A5007098537 @default.
- W3213333886 creator A5016038041 @default.
- W3213333886 creator A5047240103 @default.
- W3213333886 creator A5048671543 @default.
- W3213333886 creator A5065250332 @default.
- W3213333886 creator A5091227928 @default.
- W3213333886 date "2021-12-06" @default.
- W3213333886 modified "2023-09-24" @default.
- W3213333886 title "Instance-dependent Label-noise Learning under a Structural Causal Model" @default.
- W3213333886 hasPublicationYear "2021" @default.
- W3213333886 type Work @default.
- W3213333886 sameAs 3213333886 @default.
- W3213333886 citedByCount "0" @default.
- W3213333886 crossrefType "proceedings-article" @default.
- W3213333886 hasAuthorship W3213333886A5007098537 @default.
- W3213333886 hasAuthorship W3213333886A5016038041 @default.
- W3213333886 hasAuthorship W3213333886A5047240103 @default.
- W3213333886 hasAuthorship W3213333886A5048671543 @default.
- W3213333886 hasAuthorship W3213333886A5065250332 @default.
- W3213333886 hasAuthorship W3213333886A5091227928 @default.
- W3213333886 hasConcept C115961682 @default.
- W3213333886 hasConcept C119857082 @default.
- W3213333886 hasConcept C122770356 @default.
- W3213333886 hasConcept C153180895 @default.
- W3213333886 hasConcept C154945302 @default.
- W3213333886 hasConcept C165696696 @default.
- W3213333886 hasConcept C167966045 @default.
- W3213333886 hasConcept C22019652 @default.
- W3213333886 hasConcept C38652104 @default.
- W3213333886 hasConcept C39890363 @default.
- W3213333886 hasConcept C41008148 @default.
- W3213333886 hasConcept C50644808 @default.
- W3213333886 hasConcept C95623464 @default.
- W3213333886 hasConcept C99498987 @default.
- W3213333886 hasConceptScore W3213333886C115961682 @default.
- W3213333886 hasConceptScore W3213333886C119857082 @default.
- W3213333886 hasConceptScore W3213333886C122770356 @default.
- W3213333886 hasConceptScore W3213333886C153180895 @default.
- W3213333886 hasConceptScore W3213333886C154945302 @default.
- W3213333886 hasConceptScore W3213333886C165696696 @default.
- W3213333886 hasConceptScore W3213333886C167966045 @default.
- W3213333886 hasConceptScore W3213333886C22019652 @default.
- W3213333886 hasConceptScore W3213333886C38652104 @default.
- W3213333886 hasConceptScore W3213333886C39890363 @default.
- W3213333886 hasConceptScore W3213333886C41008148 @default.
- W3213333886 hasConceptScore W3213333886C50644808 @default.
- W3213333886 hasConceptScore W3213333886C95623464 @default.
- W3213333886 hasConceptScore W3213333886C99498987 @default.
- W3213333886 hasLocation W32133338861 @default.
- W3213333886 hasOpenAccess W3213333886 @default.
- W3213333886 hasPrimaryLocation W32133338861 @default.
- W3213333886 hasRelatedWork W2034103635 @default.
- W3213333886 hasRelatedWork W2034845197 @default.
- W3213333886 hasRelatedWork W2045260043 @default.
- W3213333886 hasRelatedWork W2164682059 @default.
- W3213333886 hasRelatedWork W2239675528 @default.
- W3213333886 hasRelatedWork W2611052687 @default.
- W3213333886 hasRelatedWork W2751120573 @default.
- W3213333886 hasRelatedWork W2789377002 @default.
- W3213333886 hasRelatedWork W2899087822 @default.
- W3213333886 hasRelatedWork W2899719558 @default.
- W3213333886 hasRelatedWork W2900455508 @default.
- W3213333886 hasRelatedWork W2947049994 @default.
- W3213333886 hasRelatedWork W2971204242 @default.
- W3213333886 hasRelatedWork W3012148446 @default.
- W3213333886 hasRelatedWork W3041563847 @default.
- W3213333886 hasRelatedWork W3059989571 @default.
- W3213333886 hasRelatedWork W3126623270 @default.
- W3213333886 hasRelatedWork W3196904728 @default.
- W3213333886 hasRelatedWork W3209562741 @default.
- W3213333886 hasRelatedWork W3213358055 @default.
- W3213333886 hasVolume "34" @default.
- W3213333886 isParatext "false" @default.
- W3213333886 isRetracted "false" @default.
- W3213333886 magId "3213333886" @default.
- W3213333886 workType "article" @default.