Matches in SemOpenAlex for { <https://semopenalex.org/work/W3170802076> ?p ?o ?g. }
Showing items 1 to 98 of
98
with 100 items per page.
- W3170802076 endingPage "107234" @default.
- W3170802076 startingPage "107234" @default.
- W3170802076 abstract "Noise label exists widely in real-world data, resulting in the degradation of classification performance. Popular methods require a known noise distribution or additional cleaning supervision, which is usually unavailable in practical scenarios. This paper presents a theoretical statistical method and designs a label confidence inference (LISR) algorithm to handle this issue. For data distribution, we define a statistical function for label inconsistency and analyze its relationship with neighbor radius. For data representation, we define trusted-neighbor, nearest-trusted-neighbor and untrusted-neighbor. For noisy label recognition, we present three inference methods to predict the labels and their confidence. The LISR algorithm establishes a practical statistical model, queries the initial trusted instances, iteratively searches for the trusted instances and corrects labels. We conducted experiments on synthetic, UCI and classic image datasets. The results of significance test verified the effectiveness of LISR and its superiority to the state-of-the-art noise label learning algorithms." @default.
- W3170802076 created "2021-06-22" @default.
- W3170802076 creator A5015102287 @default.
- W3170802076 creator A5018381716 @default.
- W3170802076 creator A5060138472 @default.
- W3170802076 date "2021-09-01" @default.
- W3170802076 modified "2023-10-17" @default.
- W3170802076 title "Noise label learning through label confidence statistical inference" @default.
- W3170802076 cites W1514928307 @default.
- W3170802076 cites W1975128126 @default.
- W3170802076 cites W1980210065 @default.
- W3170802076 cites W1982032418 @default.
- W3170802076 cites W2019863495 @default.
- W3170802076 cites W2024046085 @default.
- W3170802076 cites W2167460663 @default.
- W3170802076 cites W2746791238 @default.
- W3170802076 cites W2767094803 @default.
- W3170802076 cites W2789942211 @default.
- W3170802076 cites W2897194080 @default.
- W3170802076 cites W2962762068 @default.
- W3170802076 cites W2963697299 @default.
- W3170802076 cites W2964159205 @default.
- W3170802076 cites W2964273174 @default.
- W3170802076 cites W2964292098 @default.
- W3170802076 cites W2981952612 @default.
- W3170802076 cites W2985817549 @default.
- W3170802076 cites W3035716296 @default.
- W3170802076 cites W3110687497 @default.
- W3170802076 cites W3175103763 @default.
- W3170802076 cites W4236137412 @default.
- W3170802076 cites W4244259635 @default.
- W3170802076 doi "https://doi.org/10.1016/j.knosys.2021.107234" @default.
- W3170802076 hasPublicationYear "2021" @default.
- W3170802076 type Work @default.
- W3170802076 sameAs 3170802076 @default.
- W3170802076 citedByCount "2" @default.
- W3170802076 countsByYear W31708020762022 @default.
- W3170802076 countsByYear W31708020762023 @default.
- W3170802076 crossrefType "journal-article" @default.
- W3170802076 hasAuthorship W3170802076A5015102287 @default.
- W3170802076 hasAuthorship W3170802076A5018381716 @default.
- W3170802076 hasAuthorship W3170802076A5060138472 @default.
- W3170802076 hasConcept C105795698 @default.
- W3170802076 hasConcept C113238511 @default.
- W3170802076 hasConcept C11413529 @default.
- W3170802076 hasConcept C115961682 @default.
- W3170802076 hasConcept C119857082 @default.
- W3170802076 hasConcept C124101348 @default.
- W3170802076 hasConcept C134261354 @default.
- W3170802076 hasConcept C153180895 @default.
- W3170802076 hasConcept C154945302 @default.
- W3170802076 hasConcept C17744445 @default.
- W3170802076 hasConcept C199539241 @default.
- W3170802076 hasConcept C2776214188 @default.
- W3170802076 hasConcept C2776359362 @default.
- W3170802076 hasConcept C33923547 @default.
- W3170802076 hasConcept C41008148 @default.
- W3170802076 hasConcept C94625758 @default.
- W3170802076 hasConcept C99498987 @default.
- W3170802076 hasConceptScore W3170802076C105795698 @default.
- W3170802076 hasConceptScore W3170802076C113238511 @default.
- W3170802076 hasConceptScore W3170802076C11413529 @default.
- W3170802076 hasConceptScore W3170802076C115961682 @default.
- W3170802076 hasConceptScore W3170802076C119857082 @default.
- W3170802076 hasConceptScore W3170802076C124101348 @default.
- W3170802076 hasConceptScore W3170802076C134261354 @default.
- W3170802076 hasConceptScore W3170802076C153180895 @default.
- W3170802076 hasConceptScore W3170802076C154945302 @default.
- W3170802076 hasConceptScore W3170802076C17744445 @default.
- W3170802076 hasConceptScore W3170802076C199539241 @default.
- W3170802076 hasConceptScore W3170802076C2776214188 @default.
- W3170802076 hasConceptScore W3170802076C2776359362 @default.
- W3170802076 hasConceptScore W3170802076C33923547 @default.
- W3170802076 hasConceptScore W3170802076C41008148 @default.
- W3170802076 hasConceptScore W3170802076C94625758 @default.
- W3170802076 hasConceptScore W3170802076C99498987 @default.
- W3170802076 hasFunder F4320321001 @default.
- W3170802076 hasFunder F4320335476 @default.
- W3170802076 hasLocation W31708020761 @default.
- W3170802076 hasOpenAccess W3170802076 @default.
- W3170802076 hasPrimaryLocation W31708020761 @default.
- W3170802076 hasRelatedWork W2058818547 @default.
- W3170802076 hasRelatedWork W2146076056 @default.
- W3170802076 hasRelatedWork W2167440101 @default.
- W3170802076 hasRelatedWork W2511279186 @default.
- W3170802076 hasRelatedWork W2883887418 @default.
- W3170802076 hasRelatedWork W2981347089 @default.
- W3170802076 hasRelatedWork W3021364800 @default.
- W3170802076 hasRelatedWork W3116896278 @default.
- W3170802076 hasRelatedWork W3203501097 @default.
- W3170802076 hasRelatedWork W4286960226 @default.
- W3170802076 hasVolume "227" @default.
- W3170802076 isParatext "false" @default.
- W3170802076 isRetracted "false" @default.
- W3170802076 magId "3170802076" @default.
- W3170802076 workType "article" @default.