FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4366995877> ?p ?o ?g. }

• W4366995877 endingPage "11255" @default.
• W4366995877 startingPage "11240" @default.
• W4366995877 abstract "Open-set domain adaptation (OSDA) aims to transfer knowledge from a label-rich source domain to a label-scarce target domain while addressing disturbances from irrelevant target classes not present in the source data. However, most OSDA approaches are limited due to the lack of essential theoretical analysis of generalization bound, reliance on the coexistence of source and target data during adaptation, and failure to accurately estimate model predictions' uncertainty. To address these limitations, the Progressive Graph Learning (PGL) framework is proposed. PGL decomposes the target hypothesis space into shared and unknown subspaces and progressively pseudo-labels the most confident known samples from the target domain for hypothesis adaptation. PGL guarantees a tight upper bound of the target error by integrating a graph neural network with episodic training and leveraging adversarial learning to close the gap between the source and target distributions. The proposed approach also tackles a more realistic source-free open-set domain adaptation (SF-OSDA) setting that makes no assumptions about the coexistence of source and target domains. In a two-stage framework, the SF-PGL model' uniformly selects the most confident target instances from each category at a fixed ratio, and the confidence thresholds in each class weigh the classification loss in the adaptation step. The proposed methods are evaluated on benchmark image classification and action recognition datasets, where they demonstrate superiority and flexibility in recognizing both shared and unknown categories. Additionally, balanced pseudo-labeling plays a significant role in improving calibration, making the trained model less prone to over- or under-confident predictions on the target data." @default.
• W4366995877 created "2023-04-27" @default.
• W4366995877 creator A5014648528 @default.
• W4366995877 creator A5033319802 @default.
• W4366995877 creator A5033462059 @default.
• W4366995877 creator A5063603492 @default.
• W4366995877 creator A5078170935 @default.
• W4366995877 date "2023-09-01" @default.
• W4366995877 modified "2023-10-16" @default.
• W4366995877 title "Source-Free Progressive Graph Learning for Open-Set Domain Adaptation" @default.
• W4366995877 cites W1032927584 @default.
• W4366995877 cites W1498368596 @default.
• W4366995877 cites W2064447488 @default.
• W4366995877 cites W2096943734 @default.
• W4366995877 cites W2098824882 @default.
• W4366995877 cites W2126579184 @default.
• W4366995877 cites W2145680191 @default.
• W4366995877 cites W2165698076 @default.
• W4366995877 cites W2171370495 @default.
• W4366995877 cites W2194775991 @default.
• W4366995877 cites W2248269543 @default.
• W4366995877 cites W2296073425 @default.
• W4366995877 cites W2478454054 @default.
• W4366995877 cites W2593768305 @default.
• W4366995877 cites W2627183927 @default.
• W4366995877 cites W2779610669 @default.
• W4366995877 cites W2793888044 @default.
• W4366995877 cites W2798593490 @default.
• W4366995877 cites W2801477643 @default.
• W4366995877 cites W2901389242 @default.
• W4366995877 cites W2943605315 @default.
• W4366995877 cites W2948069880 @default.
• W4366995877 cites W2948429981 @default.
• W4366995877 cites W2950697450 @default.
• W4366995877 cites W2962687275 @default.
• W4366995877 cites W2962835731 @default.
• W4366995877 cites W2962986791 @default.
• W4366995877 cites W2963943197 @default.
• W4366995877 cites W2981368934 @default.
• W4366995877 cites W2987427063 @default.
• W4366995877 cites W2988501586 @default.
• W4366995877 cites W2998528009 @default.
• W4366995877 cites W3000029975 @default.
• W4366995877 cites W3034454087 @default.
• W4366995877 cites W3083641663 @default.
• W4366995877 cites W3093462691 @default.
• W4366995877 cites W3097526063 @default.
• W4366995877 cites W3103921434 @default.
• W4366995877 cites W3120575095 @default.
• W4366995877 cites W3173352923 @default.
• W4366995877 cites W4226043457 @default.
• W4366995877 doi "https://doi.org/10.1109/tpami.2023.3270288" @default.
• W4366995877 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37097801" @default.
• W4366995877 hasPublicationYear "2023" @default.
• W4366995877 type Work @default.
• W4366995877 citedByCount "0" @default.
• W4366995877 crossrefType "journal-article" @default.
• W4366995877 hasAuthorship W4366995877A5014648528 @default.
• W4366995877 hasAuthorship W4366995877A5033319802 @default.
• W4366995877 hasAuthorship W4366995877A5033462059 @default.
• W4366995877 hasAuthorship W4366995877A5063603492 @default.
• W4366995877 hasAuthorship W4366995877A5078170935 @default.
• W4366995877 hasBestOaLocation W43669958772 @default.
• W4366995877 hasConcept C11413529 @default.
• W4366995877 hasConcept C119857082 @default.
• W4366995877 hasConcept C120665830 @default.
• W4366995877 hasConcept C121332964 @default.
• W4366995877 hasConcept C132525143 @default.
• W4366995877 hasConcept C13280743 @default.
• W4366995877 hasConcept C139807058 @default.
• W4366995877 hasConcept C150899416 @default.
• W4366995877 hasConcept C153180895 @default.
• W4366995877 hasConcept C154945302 @default.
• W4366995877 hasConcept C177264268 @default.
• W4366995877 hasConcept C185798385 @default.
• W4366995877 hasConcept C199360897 @default.
• W4366995877 hasConcept C205649164 @default.
• W4366995877 hasConcept C41008148 @default.
• W4366995877 hasConcept C80444323 @default.
• W4366995877 hasConceptScore W4366995877C11413529 @default.
• W4366995877 hasConceptScore W4366995877C119857082 @default.
• W4366995877 hasConceptScore W4366995877C120665830 @default.
• W4366995877 hasConceptScore W4366995877C121332964 @default.
• W4366995877 hasConceptScore W4366995877C132525143 @default.
• W4366995877 hasConceptScore W4366995877C13280743 @default.
• W4366995877 hasConceptScore W4366995877C139807058 @default.
• W4366995877 hasConceptScore W4366995877C150899416 @default.
• W4366995877 hasConceptScore W4366995877C153180895 @default.
• W4366995877 hasConceptScore W4366995877C154945302 @default.
• W4366995877 hasConceptScore W4366995877C177264268 @default.
• W4366995877 hasConceptScore W4366995877C185798385 @default.
• W4366995877 hasConceptScore W4366995877C199360897 @default.
• W4366995877 hasConceptScore W4366995877C205649164 @default.
• W4366995877 hasConceptScore W4366995877C41008148 @default.
• W4366995877 hasConceptScore W4366995877C80444323 @default.
• W4366995877 hasFunder F4320334704 @default.
• W4366995877 hasIssue "9" @default.
• W4366995877 hasLocation W43669958771 @default.

• next