FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2972510403> ?p ?o ?g. }

• W2972510403 abstract "We consider the learning from noisy labels (NL) problem which emerges in many real-world applications. In addition to the widely-studied synthetic noise in the NL literature, we also consider the pseudo labels in semi-supervised learning (Semi-SL) as a special case of NL. For both types of noise, we argue that the generalization performance of existing methods is highly coupled with the quality of noisy labels. Therefore, we counter the problem from a novel and unified perspective: learning from the auxiliary clean labels. Specifically, we propose the Rotational-Decoupling Consistency Regularization (RDCR) framework that integrates the consistency-based methods with the self-supervised rotation task to learn noise-tolerant representations. The experiments show that RDCR achieves comparable or superior performance than the state-of-the-art methods under small noise, while outperforms the existing methods significantly when there is large noise." @default.
• W2972510403 created "2019-09-19" @default.
• W2972510403 creator A5007269842 @default.
• W2972510403 creator A5042226175 @default.
• W2972510403 creator A5072905534 @default.
• W2972510403 date "2019-05-23" @default.
• W2972510403 modified "2023-09-27" @default.
• W2972510403 title "Countering Noisy Labels By Learning From Auxiliary Clean Labels" @default.
• W2972510403 cites W1815076433 @default.
• W2972510403 cites W1921293667 @default.
• W2972510403 cites W1983320747 @default.
• W2972510403 cites W2101210369 @default.
• W2972510403 cites W2107878631 @default.
• W2972510403 cites W2129068307 @default.
• W2972510403 cites W2133556223 @default.
• W2972510403 cites W2167460663 @default.
• W2972510403 cites W2169203263 @default.
• W2972510403 cites W2178768799 @default.
• W2972510403 cites W2194775991 @default.
• W2972510403 cites W2321533354 @default.
• W2972510403 cites W2401231614 @default.
• W2972510403 cites W2502312327 @default.
• W2972510403 cites W2518108298 @default.
• W2972510403 cites W2569680626 @default.
• W2972510403 cites W2592691248 @default.
• W2972510403 cites W2599837529 @default.
• W2972510403 cites W2750549109 @default.
• W2972510403 cites W2808139377 @default.
• W2972510403 cites W2909869271 @default.
• W2972510403 cites W2913939497 @default.
• W2972510403 cites W2914448714 @default.
• W2972510403 cites W2924828084 @default.
• W2972510403 cites W2935128472 @default.
• W2972510403 cites W2941387380 @default.
• W2972510403 cites W2948467580 @default.
• W2972510403 cites W2949117887 @default.
• W2972510403 cites W2949702880 @default.
• W2972510403 cites W2950501397 @default.
• W2972510403 cites W2951770173 @default.
• W2972510403 cites W2951863938 @default.
• W2972510403 cites W2953327099 @default.
• W2972510403 cites W2962742544 @default.
• W2972510403 cites W2962743139 @default.
• W2972510403 cites W2962804657 @default.
• W2972510403 cites W2962824366 @default.
• W2972510403 cites W2963041308 @default.
• W2972510403 cites W2963080758 @default.
• W2972510403 cites W2963081269 @default.
• W2972510403 cites W2963173418 @default.
• W2972510403 cites W2963207607 @default.
• W2972510403 cites W2963371670 @default.
• W2972510403 cites W2963430933 @default.
• W2972510403 cites W2963558289 @default.
• W2972510403 cites W2963735582 @default.
• W2972510403 cites W2963789034 @default.
• W2972510403 cites W2963956526 @default.
• W2972510403 cites W2964155802 @default.
• W2972510403 cites W2964218010 @default.
• W2972510403 cites W2964274690 @default.
• W2972510403 cites W2975183019 @default.
• W2972510403 cites W2981952041 @default.
• W2972510403 cites W2998229299 @default.
• W2972510403 cites W3048030262 @default.
• W2972510403 cites W3093222659 @default.
• W2972510403 cites W3118608800 @default.
• W2972510403 cites W3137695714 @default.
• W2972510403 cites W2530816535 @default.
• W2972510403 hasPublicationYear "2019" @default.
• W2972510403 type Work @default.
• W2972510403 sameAs 2972510403 @default.
• W2972510403 citedByCount "3" @default.
• W2972510403 countsByYear W29725104032021 @default.
• W2972510403 crossrefType "posted-content" @default.
• W2972510403 hasAuthorship W2972510403A5007269842 @default.
• W2972510403 hasAuthorship W2972510403A5042226175 @default.
• W2972510403 hasAuthorship W2972510403A5072905534 @default.
• W2972510403 hasConcept C115961682 @default.
• W2972510403 hasConcept C119857082 @default.
• W2972510403 hasConcept C12713177 @default.
• W2972510403 hasConcept C127413603 @default.
• W2972510403 hasConcept C133731056 @default.
• W2972510403 hasConcept C134306372 @default.
• W2972510403 hasConcept C153180895 @default.
• W2972510403 hasConcept C154945302 @default.
• W2972510403 hasConcept C162324750 @default.
• W2972510403 hasConcept C177148314 @default.
• W2972510403 hasConcept C187736073 @default.
• W2972510403 hasConcept C205606062 @default.
• W2972510403 hasConcept C2776135515 @default.
• W2972510403 hasConcept C2776436953 @default.
• W2972510403 hasConcept C2780451532 @default.
• W2972510403 hasConcept C33923547 @default.
• W2972510403 hasConcept C41008148 @default.
• W2972510403 hasConcept C99498987 @default.
• W2972510403 hasConceptScore W2972510403C115961682 @default.
• W2972510403 hasConceptScore W2972510403C119857082 @default.
• W2972510403 hasConceptScore W2972510403C12713177 @default.
• W2972510403 hasConceptScore W2972510403C127413603 @default.
• W2972510403 hasConceptScore W2972510403C133731056 @default.
• W2972510403 hasConceptScore W2972510403C134306372 @default.

• next