FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3173151551> ?p ?o ?g. }

• W3173151551 endingPage "1" @default.
• W3173151551 startingPage "1" @default.
• W3173151551 abstract "Deep supervised learning has achieved great success in the last decade. However, its defects of heavy dependence on manual labels and vulnerability to attacks have driven people to find other paradigms. As an alternative, self-supervised learning (SSL) attracts many researchers for its soaring performance on representation learning in the last several years. Self-supervised representation learning leverages input data itself as supervision and benefits almost all types of downstream tasks. In this survey, we take a look into new self-supervised learning methods for representation in computer vision, natural language processing, and graph learning. We comprehensively review the existing empirical methods and summarize them into three main categories according to their objectives: generative, contrastive, and generative-contrastive (adversarial). We further collect related theoretical analyses on self-supervised learning to provide deeper thoughts on why self-supervised learning works. Finally, we briefly discuss open problems and future directions for self-supervised learning. An outline slide for the survey is provided." @default.
• W3173151551 created "2021-07-05" @default.
• W3173151551 creator A5016224961 @default.
• W3173151551 creator A5017947172 @default.
• W3173151551 creator A5029595402 @default.
• W3173151551 creator A5044791875 @default.
• W3173151551 creator A5060102585 @default.
• W3173151551 creator A5076409244 @default.
• W3173151551 creator A5077209408 @default.
• W3173151551 date "2021-01-01" @default.
• W3173151551 modified "2023-10-18" @default.
• W3173151551 title "Self-supervised Learning: Generative or Contrastive" @default.
• W3173151551 cites W1903029394 @default.
• W3173151551 cites W1932742904 @default.
• W3173151551 cites W2022322548 @default.
• W3173151551 cites W2102605133 @default.
• W3173151551 cites W2108598243 @default.
• W3173151551 cites W2194775991 @default.
• W3173151551 cites W2270070752 @default.
• W3173151551 cites W2308529009 @default.
• W3173151551 cites W2321533354 @default.
• W3173151551 cites W2326925005 @default.
• W3173151551 cites W2493916176 @default.
• W3173151551 cites W2518754566 @default.
• W3173151551 cites W2558661413 @default.
• W3173151551 cites W2599837529 @default.
• W3173151551 cites W2607500032 @default.
• W3173151551 cites W2612769033 @default.
• W3173151551 cites W2640408555 @default.
• W3173151551 cites W2738588019 @default.
• W3173151551 cites W2788919350 @default.
• W3173151551 cites W2792234394 @default.
• W3173151551 cites W2798991696 @default.
• W3173151551 cites W2808856341 @default.
• W3173151551 cites W2809583854 @default.
• W3173151551 cites W2883725317 @default.
• W3173151551 cites W2889787757 @default.
• W3173151551 cites W2906943923 @default.
• W3173151551 cites W2919115771 @default.
• W3173151551 cites W2949182780 @default.
• W3173151551 cites W2952205826 @default.
• W3173151551 cites W2953356739 @default.
• W3173151551 cites W2962756421 @default.
• W3173151551 cites W2962770929 @default.
• W3173151551 cites W2962852342 @default.
• W3173151551 cites W2962904108 @default.
• W3173151551 cites W2962922117 @default.
• W3173151551 cites W2963073614 @default.
• W3173151551 cites W2963169753 @default.
• W3173151551 cites W2963261224 @default.
• W3173151551 cites W2963420272 @default.
• W3173151551 cites W2963465221 @default.
• W3173151551 cites W2963470893 @default.
• W3173151551 cites W2963748441 @default.
• W3173151551 cites W2963826423 @default.
• W3173151551 cites W2964060161 @default.
• W3173151551 cites W2964110616 @default.
• W3173151551 cites W2966694634 @default.
• W3173151551 cites W2970641574 @default.
• W3173151551 cites W2985951359 @default.
• W3173151551 cites W2998269939 @default.
• W3173151551 cites W2998388430 @default.
• W3173151551 cites W3011411500 @default.
• W3173151551 cites W3011574394 @default.
• W3173151551 cites W3012871709 @default.
• W3173151551 cites W3035160371 @default.
• W3173151551 cites W3035164673 @default.
• W3173151551 cites W3080997787 @default.
• W3173151551 cites W3099152386 @default.
• W3173151551 cites W3099700870 @default.
• W3173151551 cites W3104038788 @default.
• W3173151551 cites W3104097132 @default.
• W3173151551 cites W3105705953 @default.
• W3173151551 cites W343636949 @default.
• W3173151551 doi "https://doi.org/10.1109/tkde.2021.3090866" @default.
• W3173151551 hasPublicationYear "2021" @default.
• W3173151551 type Work @default.
• W3173151551 sameAs 3173151551 @default.
• W3173151551 citedByCount "316" @default.
• W3173151551 countsByYear W31731515512020 @default.
• W3173151551 countsByYear W31731515512021 @default.
• W3173151551 countsByYear W31731515512022 @default.
• W3173151551 countsByYear W31731515512023 @default.
• W3173151551 crossrefType "journal-article" @default.
• W3173151551 hasAuthorship W3173151551A5016224961 @default.
• W3173151551 hasAuthorship W3173151551A5017947172 @default.
• W3173151551 hasAuthorship W3173151551A5029595402 @default.
• W3173151551 hasAuthorship W3173151551A5044791875 @default.
• W3173151551 hasAuthorship W3173151551A5060102585 @default.
• W3173151551 hasAuthorship W3173151551A5076409244 @default.
• W3173151551 hasAuthorship W3173151551A5077209408 @default.
• W3173151551 hasBestOaLocation W31731515512 @default.
• W3173151551 hasConcept C119857082 @default.
• W3173151551 hasConcept C132525143 @default.
• W3173151551 hasConcept C136389625 @default.
• W3173151551 hasConcept C154945302 @default.
• W3173151551 hasConcept C17744445 @default.
• W3173151551 hasConcept C199539241 @default.

• next