Matches in SemOpenAlex for { <https://semopenalex.org/work/W2964204277> ?p ?o ?g. }
Showing items 1 to 73 of
73
with 100 items per page.
- W2964204277 abstract "The success of deep learning in medical imaging is mostly achieved at the cost of a large labeled data set. Semi-supervised learning (SSL) provides a promising solution by leveraging the structure of unlabeled data to improve learning from a small set of labeled data. Self-ensembling is a simple approach used in SSL to encourage consensus among ensemble predictions of unknown labels, improving generalization of the model by making it more insensitive to the latent space. Currently, such an ensemble is obtained by randomization such as dropout regularization and random data augmentation. In this work, we hypothesize -- from the generalization perspective -- that self-ensembling can be improved by exploiting the stochasticity of a disentangled latent space. To this end, we present a stacked SSL model that utilizes unsupervised disentangled representation learning as the stochastic embedding for self-ensembling. We evaluate the presented model for multi-label classification using chest X-ray images, demonstrating its improved performance over related SSL models as well as the interpretability of its disentangled representations." @default.
- W2964204277 created "2019-07-30" @default.
- W2964204277 creator A5008803380 @default.
- W2964204277 creator A5013194814 @default.
- W2964204277 creator A5045732749 @default.
- W2964204277 creator A5049509565 @default.
- W2964204277 date "2019-07-22" @default.
- W2964204277 modified "2023-09-23" @default.
- W2964204277 title "Semi-Supervised Learning by Disentangling and Self-Ensembling Over Stochastic Latent Space" @default.
- W2964204277 cites W1959608418 @default.
- W2964204277 cites W2108501770 @default.
- W2964204277 cites W2548275288 @default.
- W2964204277 cites W2592929672 @default.
- W2964204277 cites W2789122432 @default.
- W2964204277 cites W2806321514 @default.
- W2964204277 cites W2963466845 @default.
- W2964204277 cites W3100945164 @default.
- W2964204277 cites W2530816535 @default.
- W2964204277 cites W2963229033 @default.
- W2964204277 doi "https://doi.org/10.48550/arxiv.1907.09607" @default.
- W2964204277 hasPublicationYear "2019" @default.
- W2964204277 type Work @default.
- W2964204277 sameAs 2964204277 @default.
- W2964204277 citedByCount "0" @default.
- W2964204277 crossrefType "posted-content" @default.
- W2964204277 hasAuthorship W2964204277A5008803380 @default.
- W2964204277 hasAuthorship W2964204277A5013194814 @default.
- W2964204277 hasAuthorship W2964204277A5045732749 @default.
- W2964204277 hasAuthorship W2964204277A5049509565 @default.
- W2964204277 hasBestOaLocation W29642042771 @default.
- W2964204277 hasConcept C119857082 @default.
- W2964204277 hasConcept C134306372 @default.
- W2964204277 hasConcept C153180895 @default.
- W2964204277 hasConcept C154945302 @default.
- W2964204277 hasConcept C177148314 @default.
- W2964204277 hasConcept C2776135515 @default.
- W2964204277 hasConcept C2781067378 @default.
- W2964204277 hasConcept C33923547 @default.
- W2964204277 hasConcept C41008148 @default.
- W2964204277 hasConcept C41608201 @default.
- W2964204277 hasConcept C45942800 @default.
- W2964204277 hasConcept C58973888 @default.
- W2964204277 hasConcept C59404180 @default.
- W2964204277 hasConceptScore W2964204277C119857082 @default.
- W2964204277 hasConceptScore W2964204277C134306372 @default.
- W2964204277 hasConceptScore W2964204277C153180895 @default.
- W2964204277 hasConceptScore W2964204277C154945302 @default.
- W2964204277 hasConceptScore W2964204277C177148314 @default.
- W2964204277 hasConceptScore W2964204277C2776135515 @default.
- W2964204277 hasConceptScore W2964204277C2781067378 @default.
- W2964204277 hasConceptScore W2964204277C33923547 @default.
- W2964204277 hasConceptScore W2964204277C41008148 @default.
- W2964204277 hasConceptScore W2964204277C41608201 @default.
- W2964204277 hasConceptScore W2964204277C45942800 @default.
- W2964204277 hasConceptScore W2964204277C58973888 @default.
- W2964204277 hasConceptScore W2964204277C59404180 @default.
- W2964204277 hasLocation W29642042771 @default.
- W2964204277 hasOpenAccess W2964204277 @default.
- W2964204277 hasPrimaryLocation W29642042771 @default.
- W2964204277 hasRelatedWork W2908875379 @default.
- W2964204277 hasRelatedWork W2948220209 @default.
- W2964204277 hasRelatedWork W2964204277 @default.
- W2964204277 hasRelatedWork W2994796525 @default.
- W2964204277 hasRelatedWork W3013699712 @default.
- W2964204277 hasRelatedWork W3129604848 @default.
- W2964204277 hasRelatedWork W3191046242 @default.
- W2964204277 hasRelatedWork W4213165337 @default.
- W2964204277 hasRelatedWork W4213225422 @default.
- W2964204277 hasRelatedWork W1501932982 @default.
- W2964204277 isParatext "false" @default.
- W2964204277 isRetracted "false" @default.
- W2964204277 magId "2964204277" @default.
- W2964204277 workType "article" @default.