Matches in SemOpenAlex for { <https://semopenalex.org/work/W4213205638> ?p ?o ?g. }
Showing items 1 to 83 of
83
with 100 items per page.
- W4213205638 abstract "Representation learning is one of the canonical objectives of most deep learning models. However, the learning of real-world clinical data is often compromised by their inherently imbalanced or long-tailed distribution wherein a few classes have significantly larger numbers of training instances than do the other classes. In this study, we investigated the representation learning of such long-tailed data distributions by the use of a deep mutual ensemble generative adversarial network. Our proposed framework consists of multiple powerful pre-trained discriminator networks that transfer knowledge to multiple individual untrained generator networks. During the training process, each generator learns to collaborate with the other generators. Additionally, each generator receives feedback from the individual discriminators in an adversarial manner. Especially, we explored the use of mutual information shared between the independent generators that makes our framework robust against misclassification of long-tailed data distributions in medical image analysis. We evaluated our proposed framework on four public datasets that represented different medical imaging modalities and imbalance ratios. Our experimental results show that our proposed framework benefits from ensemble learning and shared mutual learning, and achieves compelling results on several medical imaging benchmarks. Thus, our approach offers potential advantages over traditional deep learning in real-world applications." @default.
- W4213205638 created "2022-02-24" @default.
- W4213205638 creator A5001158728 @default.
- W4213205638 creator A5007340702 @default.
- W4213205638 creator A5069072700 @default.
- W4213205638 creator A5076635383 @default.
- W4213205638 date "2022-04-04" @default.
- W4213205638 modified "2023-10-06" @default.
- W4213205638 title "Deep mutual GANs: representation learning from multiple experts" @default.
- W4213205638 doi "https://doi.org/10.1117/12.2612968" @default.
- W4213205638 hasPublicationYear "2022" @default.
- W4213205638 type Work @default.
- W4213205638 citedByCount "1" @default.
- W4213205638 countsByYear W42132056382023 @default.
- W4213205638 crossrefType "proceedings-article" @default.
- W4213205638 hasAuthorship W4213205638A5001158728 @default.
- W4213205638 hasAuthorship W4213205638A5007340702 @default.
- W4213205638 hasAuthorship W4213205638A5069072700 @default.
- W4213205638 hasAuthorship W4213205638A5076635383 @default.
- W4213205638 hasConcept C108583219 @default.
- W4213205638 hasConcept C111919701 @default.
- W4213205638 hasConcept C119857082 @default.
- W4213205638 hasConcept C121332964 @default.
- W4213205638 hasConcept C144024400 @default.
- W4213205638 hasConcept C150899416 @default.
- W4213205638 hasConcept C152139883 @default.
- W4213205638 hasConcept C154945302 @default.
- W4213205638 hasConcept C163258240 @default.
- W4213205638 hasConcept C17744445 @default.
- W4213205638 hasConcept C199539241 @default.
- W4213205638 hasConcept C2776359362 @default.
- W4213205638 hasConcept C2779803651 @default.
- W4213205638 hasConcept C2779903281 @default.
- W4213205638 hasConcept C2780992000 @default.
- W4213205638 hasConcept C36289849 @default.
- W4213205638 hasConcept C37736160 @default.
- W4213205638 hasConcept C41008148 @default.
- W4213205638 hasConcept C59404180 @default.
- W4213205638 hasConcept C62520636 @default.
- W4213205638 hasConcept C76155785 @default.
- W4213205638 hasConcept C94625758 @default.
- W4213205638 hasConcept C94915269 @default.
- W4213205638 hasConcept C98045186 @default.
- W4213205638 hasConceptScore W4213205638C108583219 @default.
- W4213205638 hasConceptScore W4213205638C111919701 @default.
- W4213205638 hasConceptScore W4213205638C119857082 @default.
- W4213205638 hasConceptScore W4213205638C121332964 @default.
- W4213205638 hasConceptScore W4213205638C144024400 @default.
- W4213205638 hasConceptScore W4213205638C150899416 @default.
- W4213205638 hasConceptScore W4213205638C152139883 @default.
- W4213205638 hasConceptScore W4213205638C154945302 @default.
- W4213205638 hasConceptScore W4213205638C163258240 @default.
- W4213205638 hasConceptScore W4213205638C17744445 @default.
- W4213205638 hasConceptScore W4213205638C199539241 @default.
- W4213205638 hasConceptScore W4213205638C2776359362 @default.
- W4213205638 hasConceptScore W4213205638C2779803651 @default.
- W4213205638 hasConceptScore W4213205638C2779903281 @default.
- W4213205638 hasConceptScore W4213205638C2780992000 @default.
- W4213205638 hasConceptScore W4213205638C36289849 @default.
- W4213205638 hasConceptScore W4213205638C37736160 @default.
- W4213205638 hasConceptScore W4213205638C41008148 @default.
- W4213205638 hasConceptScore W4213205638C59404180 @default.
- W4213205638 hasConceptScore W4213205638C62520636 @default.
- W4213205638 hasConceptScore W4213205638C76155785 @default.
- W4213205638 hasConceptScore W4213205638C94625758 @default.
- W4213205638 hasConceptScore W4213205638C94915269 @default.
- W4213205638 hasConceptScore W4213205638C98045186 @default.
- W4213205638 hasLocation W42132056381 @default.
- W4213205638 hasOpenAccess W4213205638 @default.
- W4213205638 hasPrimaryLocation W42132056381 @default.
- W4213205638 hasRelatedWork W2946016983 @default.
- W4213205638 hasRelatedWork W2960456850 @default.
- W4213205638 hasRelatedWork W3013160594 @default.
- W4213205638 hasRelatedWork W3031818154 @default.
- W4213205638 hasRelatedWork W4213299466 @default.
- W4213205638 hasRelatedWork W4281382123 @default.
- W4213205638 hasRelatedWork W4312200629 @default.
- W4213205638 hasRelatedWork W4318834068 @default.
- W4213205638 hasRelatedWork W4318957922 @default.
- W4213205638 hasRelatedWork W4321854312 @default.
- W4213205638 isParatext "false" @default.
- W4213205638 isRetracted "false" @default.
- W4213205638 workType "article" @default.