FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3043447622> ?p ?o ?g. }

• W3043447622 abstract "Domain generalization models learn to generalize to previously unseen domains, but suffer from prediction uncertainty and domain shift. In this paper, we address both problems. We introduce a probabilistic meta-learning model for domain generalization, in which classifier parameters shared across domains are modeled as distributions. This enables better handling of prediction uncertainty on unseen domains. To deal with domain shift, we learn domain-invariant representations by the proposed principle of meta variational information bottleneck, we call MetaVIB. MetaVIB is derived from novel variational bounds of mutual information, by leveraging the meta-learning setting of domain generalization. Through episodic training, MetaVIB learns to gradually narrow domain gaps to establish domain-invariant representations, while simultaneously maximizing prediction accuracy. We conduct experiments on three benchmarks for cross-domain visual recognition. Comprehensive ablation studies validate the benefits of MetaVIB for domain generalization. The comparison results demonstrate our method outperforms previous approaches consistently." @default.
• W3043447622 created "2020-07-23" @default.
• W3043447622 creator A5024508073 @default.
• W3043447622 creator A5026486701 @default.
• W3043447622 creator A5042967567 @default.
• W3043447622 creator A5077690631 @default.
• W3043447622 creator A5082634513 @default.
• W3043447622 creator A5086749611 @default.
• W3043447622 creator A5087073763 @default.
• W3043447622 date "2020-07-15" @default.
• W3043447622 modified "2023-09-23" @default.
• W3043447622 title "Learning to Learn with Variational Information Bottleneck for Domain Generalization" @default.
• W3043447622 cites W1486056878 @default.
• W3043447622 cites W1522301498 @default.
• W3043447622 cites W1576445103 @default.
• W3043447622 cites W1686946872 @default.
• W3043447622 cites W1909320841 @default.
• W3043447622 cites W1920962657 @default.
• W3043447622 cites W1959608418 @default.
• W3043447622 cites W1982522767 @default.
• W3043447622 cites W2031342017 @default.
• W3043447622 cites W2031489346 @default.
• W3043447622 cites W2089217417 @default.
• W3043447622 cites W2110764733 @default.
• W3043447622 cites W2112796928 @default.
• W3043447622 cites W2126151240 @default.
• W3043447622 cites W2145680191 @default.
• W3043447622 cites W2155858138 @default.
• W3043447622 cites W2163605009 @default.
• W3043447622 cites W2187089797 @default.
• W3043447622 cites W2511131004 @default.
• W3043447622 cites W2578437730 @default.
• W3043447622 cites W2593634001 @default.
• W3043447622 cites W2601450892 @default.
• W3043447622 cites W2604763608 @default.
• W3043447622 cites W2753160622 @default.
• W3043447622 cites W2763549966 @default.
• W3043447622 cites W2770468159 @default.
• W3043447622 cites W2785885194 @default.
• W3043447622 cites W2787226294 @default.
• W3043447622 cites W2787705367 @default.
• W3043447622 cites W2794363191 @default.
• W3043447622 cites W2795900505 @default.
• W3043447622 cites W2798658180 @default.
• W3043447622 cites W2880214242 @default.
• W3043447622 cites W2889965839 @default.
• W3043447622 cites W2892623062 @default.
• W3043447622 cites W2892806280 @default.
• W3043447622 cites W2894728917 @default.
• W3043447622 cites W2912528108 @default.
• W3043447622 cites W2948974578 @default.
• W3043447622 cites W2949436635 @default.
• W3043447622 cites W2949517868 @default.
• W3043447622 cites W2958360136 @default.
• W3043447622 cites W2962810352 @default.
• W3043447622 cites W2963341924 @default.
• W3043447622 cites W2963371846 @default.
• W3043447622 cites W2963446520 @default.
• W3043447622 cites W2963775850 @default.
• W3043447622 cites W2964041897 @default.
• W3043447622 cites W2964078140 @default.
• W3043447622 cites W2964105864 @default.
• W3043447622 cites W2964160479 @default.
• W3043447622 cites W2964184826 @default.
• W3043447622 cites W2970119729 @default.
• W3043447622 cites W2981368934 @default.
• W3043447622 cites W2997756007 @default.
• W3043447622 cites W99485931 @default.
• W3043447622 doi "https://doi.org/10.48550/arxiv.2007.07645" @default.
• W3043447622 hasPublicationYear "2020" @default.
• W3043447622 type Work @default.
• W3043447622 sameAs 3043447622 @default.
• W3043447622 citedByCount "1" @default.
• W3043447622 countsByYear W30434476222021 @default.
• W3043447622 crossrefType "posted-content" @default.
• W3043447622 hasAuthorship W3043447622A5024508073 @default.
• W3043447622 hasAuthorship W3043447622A5026486701 @default.
• W3043447622 hasAuthorship W3043447622A5042967567 @default.
• W3043447622 hasAuthorship W3043447622A5077690631 @default.
• W3043447622 hasAuthorship W3043447622A5082634513 @default.
• W3043447622 hasAuthorship W3043447622A5086749611 @default.
• W3043447622 hasAuthorship W3043447622A5087073763 @default.
• W3043447622 hasBestOaLocation W30434476221 @default.
• W3043447622 hasConcept C11413529 @default.
• W3043447622 hasConcept C119857082 @default.
• W3043447622 hasConcept C134306372 @default.
• W3043447622 hasConcept C149635348 @default.
• W3043447622 hasConcept C152139883 @default.
• W3043447622 hasConcept C154945302 @default.
• W3043447622 hasConcept C177148314 @default.
• W3043447622 hasConcept C190470478 @default.
• W3043447622 hasConcept C2780513914 @default.
• W3043447622 hasConcept C33923547 @default.
• W3043447622 hasConcept C36503486 @default.
• W3043447622 hasConcept C37914503 @default.
• W3043447622 hasConcept C41008148 @default.
• W3043447622 hasConcept C49937458 @default.
• W3043447622 hasConcept C60008888 @default.
• W3043447622 hasConcept C95623464 @default.
• W3043447622 hasConceptScore W3043447622C11413529 @default.

• next