FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3100689571> ?p ?o ?g. }

• W3100689571 abstract "Since convolutional neural networks (CNNs) can easily overfit noisy labels, which are ubiquitous in visual classification tasks, it has been a great challenge to train CNNs against them robustly. Various methods have been proposed for this challenge. However, none of them pay attention to the difference between representation and classifier learning of CNNs. Thus, inspired by the observation that classifier is more robust to noisy labels while representation is much more fragile, and by the recent advances of self-supervised representation learning (SSRL) technologies, we design a new method, i.e., CS$^3$NL, to obtain representation by SSRL without labels and train the classifier directly with noisy labels. Extensive experiments are performed on both synthetic and real benchmark datasets. Results demonstrate that the proposed method can beat the state-of-the-art ones by a large margin, especially under a high noisy level." @default.
• W3100689571 created "2020-11-23" @default.
• W3100689571 creator A5056829939 @default.
• W3100689571 creator A5072484211 @default.
• W3100689571 date "2020-11-16" @default.
• W3100689571 modified "2023-09-25" @default.
• W3100689571 title "Combining Self-Supervised and Supervised Learning with Noisy Labels" @default.
• W3100689571 cites W1554944419 @default.
• W3100689571 cites W2059471177 @default.
• W3100689571 cites W2112796928 @default.
• W3100689571 cites W2117539524 @default.
• W3100689571 cites W2156909104 @default.
• W3100689571 cites W2194775991 @default.
• W3100689571 cites W2599207826 @default.
• W3100689571 cites W2604156156 @default.
• W3100689571 cites W2606321545 @default.
• W3100689571 cites W2743473392 @default.
• W3100689571 cites W2765407302 @default.
• W3100689571 cites W2786808285 @default.
• W3100689571 cites W2795282075 @default.
• W3100689571 cites W2896457183 @default.
• W3100689571 cites W2906871406 @default.
• W3100689571 cites W2909793444 @default.
• W3100689571 cites W2912237282 @default.
• W3100689571 cites W2913520548 @default.
• W3100689571 cites W2920830204 @default.
• W3100689571 cites W2935850529 @default.
• W3100689571 cites W2948606739 @default.
• W3100689571 cites W2951548327 @default.
• W3100689571 cites W2951863938 @default.
• W3100689571 cites W2952361104 @default.
• W3100689571 cites W2962742544 @default.
• W3100689571 cites W2963081269 @default.
• W3100689571 cites W2963207607 @default.
• W3100689571 cites W2963735582 @default.
• W3100689571 cites W2963826056 @default.
• W3100689571 cites W2964096266 @default.
• W3100689571 cites W2964234160 @default.
• W3100689571 cites W2964292098 @default.
• W3100689571 cites W2978625989 @default.
• W3100689571 cites W2981952612 @default.
• W3100689571 cites W2988383494 @default.
• W3100689571 cites W2995315671 @default.
• W3100689571 cites W2996626261 @default.
• W3100689571 cites W2998239226 @default.
• W3100689571 cites W3001197829 @default.
• W3100689571 cites W3005680577 @default.
• W3100689571 cites W3005731330 @default.
• W3100689571 cites W3015606043 @default.
• W3100689571 cites W3035003500 @default.
• W3100689571 cites W3035060554 @default.
• W3100689571 cites W3037062548 @default.
• W3100689571 cites W3039883906 @default.
• W3100689571 cites W3103846556 @default.
• W3100689571 cites W343636949 @default.
• W3100689571 doi "https://doi.org/10.48550/arxiv.2011.08145" @default.
• W3100689571 hasPublicationYear "2020" @default.
• W3100689571 type Work @default.
• W3100689571 sameAs 3100689571 @default.
• W3100689571 citedByCount "6" @default.
• W3100689571 countsByYear W31006895712021 @default.
• W3100689571 crossrefType "posted-content" @default.
• W3100689571 hasAuthorship W3100689571A5056829939 @default.
• W3100689571 hasAuthorship W3100689571A5072484211 @default.
• W3100689571 hasBestOaLocation W31006895711 @default.
• W3100689571 hasConcept C119857082 @default.
• W3100689571 hasConcept C136389625 @default.
• W3100689571 hasConcept C153180895 @default.
• W3100689571 hasConcept C154945302 @default.
• W3100689571 hasConcept C22019652 @default.
• W3100689571 hasConcept C2781170535 @default.
• W3100689571 hasConcept C41008148 @default.
• W3100689571 hasConcept C50644808 @default.
• W3100689571 hasConcept C59404180 @default.
• W3100689571 hasConcept C774472 @default.
• W3100689571 hasConcept C81363708 @default.
• W3100689571 hasConcept C95623464 @default.
• W3100689571 hasConceptScore W3100689571C119857082 @default.
• W3100689571 hasConceptScore W3100689571C136389625 @default.
• W3100689571 hasConceptScore W3100689571C153180895 @default.
• W3100689571 hasConceptScore W3100689571C154945302 @default.
• W3100689571 hasConceptScore W3100689571C22019652 @default.
• W3100689571 hasConceptScore W3100689571C2781170535 @default.
• W3100689571 hasConceptScore W3100689571C41008148 @default.
• W3100689571 hasConceptScore W3100689571C50644808 @default.
• W3100689571 hasConceptScore W3100689571C59404180 @default.
• W3100689571 hasConceptScore W3100689571C774472 @default.
• W3100689571 hasConceptScore W3100689571C81363708 @default.
• W3100689571 hasConceptScore W3100689571C95623464 @default.
• W3100689571 hasLocation W31006895711 @default.
• W3100689571 hasOpenAccess W3100689571 @default.
• W3100689571 hasPrimaryLocation W31006895711 @default.
• W3100689571 hasRelatedWork W2605524926 @default.
• W3100689571 hasRelatedWork W2767651786 @default.
• W3100689571 hasRelatedWork W2905846897 @default.
• W3100689571 hasRelatedWork W2944843851 @default.
• W3100689571 hasRelatedWork W2953328427 @default.
• W3100689571 hasRelatedWork W2964383635 @default.
• W3100689571 hasRelatedWork W2995914718 @default.
• W3100689571 hasRelatedWork W4295514622 @default.

• next