Matches in SemOpenAlex for { <https://semopenalex.org/work/W3173486383> ?p ?o ?g. }
Showing items 1 to 93 of
93
with 100 items per page.
- W3173486383 endingPage "3592" @default.
- W3173486383 startingPage "3580" @default.
- W3173486383 abstract "With the development of deep learning, medical image classification has been significantly improved. However, deep learning requires massive data with labels. While labeling the samples by human experts is expensive and time-consuming, collecting labels from crowd-sourcing suffers from the noises which may degenerate the accuracy of classifiers. Therefore, approaches that can effectively handle label noises are highly desired. Unfortunately, recent progress on handling label noise in deep learning has gone largely unnoticed by the medical image. To fill the gap, this paper proposes a noise-tolerant medical image classification framework named Co-Correcting, which significantly improves classification accuracy and obtains more accurate labels through dual-network mutual learning, label probability estimation, and curriculum label correcting. On two representative medical image datasets and the MNIST dataset, we test six latest Learning-with-Noisy-Labels methods and conduct comparative studies. The experiments show that Co-Correcting achieves the best accuracy and generalization under different noise ratios in various tasks. Our project can be found at: https://github.com/JiarunLiu/Co-Correcting." @default.
- W3173486383 created "2021-07-05" @default.
- W3173486383 creator A5022951423 @default.
- W3173486383 creator A5049640298 @default.
- W3173486383 creator A5058575676 @default.
- W3173486383 date "2021-12-01" @default.
- W3173486383 modified "2023-10-09" @default.
- W3173486383 title "Co-Correcting: Noise-Tolerant Medical Image Classification via Mutual Label Correction" @default.
- W3173486383 cites W1514928307 @default.
- W3173486383 cites W2296073425 @default.
- W3173486383 cites W2403681572 @default.
- W3173486383 cites W2553156677 @default.
- W3173486383 cites W2581082771 @default.
- W3173486383 cites W2772723798 @default.
- W3173486383 cites W2788633781 @default.
- W3173486383 cites W2798830774 @default.
- W3173486383 cites W2806389172 @default.
- W3173486383 cites W2806857275 @default.
- W3173486383 cites W2809006044 @default.
- W3173486383 cites W2887842788 @default.
- W3173486383 cites W2912934043 @default.
- W3173486383 cites W2963967185 @default.
- W3173486383 cites W2964159205 @default.
- W3173486383 cites W2964274690 @default.
- W3173486383 cites W2964292098 @default.
- W3173486383 cites W2967052791 @default.
- W3173486383 cites W2980154109 @default.
- W3173486383 cites W3036586801 @default.
- W3173486383 cites W3091002423 @default.
- W3173486383 cites W4288083516 @default.
- W3173486383 doi "https://doi.org/10.1109/tmi.2021.3091178" @default.
- W3173486383 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/34152981" @default.
- W3173486383 hasPublicationYear "2021" @default.
- W3173486383 type Work @default.
- W3173486383 sameAs 3173486383 @default.
- W3173486383 citedByCount "10" @default.
- W3173486383 countsByYear W31734863832022 @default.
- W3173486383 countsByYear W31734863832023 @default.
- W3173486383 crossrefType "journal-article" @default.
- W3173486383 hasAuthorship W3173486383A5022951423 @default.
- W3173486383 hasAuthorship W3173486383A5049640298 @default.
- W3173486383 hasAuthorship W3173486383A5058575676 @default.
- W3173486383 hasBestOaLocation W31734863832 @default.
- W3173486383 hasConcept C108583219 @default.
- W3173486383 hasConcept C115961682 @default.
- W3173486383 hasConcept C119857082 @default.
- W3173486383 hasConcept C134306372 @default.
- W3173486383 hasConcept C153180895 @default.
- W3173486383 hasConcept C154945302 @default.
- W3173486383 hasConcept C177148314 @default.
- W3173486383 hasConcept C190502265 @default.
- W3173486383 hasConcept C31601959 @default.
- W3173486383 hasConcept C33923547 @default.
- W3173486383 hasConcept C41008148 @default.
- W3173486383 hasConcept C75294576 @default.
- W3173486383 hasConcept C99498987 @default.
- W3173486383 hasConceptScore W3173486383C108583219 @default.
- W3173486383 hasConceptScore W3173486383C115961682 @default.
- W3173486383 hasConceptScore W3173486383C119857082 @default.
- W3173486383 hasConceptScore W3173486383C134306372 @default.
- W3173486383 hasConceptScore W3173486383C153180895 @default.
- W3173486383 hasConceptScore W3173486383C154945302 @default.
- W3173486383 hasConceptScore W3173486383C177148314 @default.
- W3173486383 hasConceptScore W3173486383C190502265 @default.
- W3173486383 hasConceptScore W3173486383C31601959 @default.
- W3173486383 hasConceptScore W3173486383C33923547 @default.
- W3173486383 hasConceptScore W3173486383C41008148 @default.
- W3173486383 hasConceptScore W3173486383C75294576 @default.
- W3173486383 hasConceptScore W3173486383C99498987 @default.
- W3173486383 hasIssue "12" @default.
- W3173486383 hasLocation W31734863831 @default.
- W3173486383 hasLocation W31734863832 @default.
- W3173486383 hasLocation W31734863833 @default.
- W3173486383 hasLocation W31734863834 @default.
- W3173486383 hasOpenAccess W3173486383 @default.
- W3173486383 hasPrimaryLocation W31734863831 @default.
- W3173486383 hasRelatedWork W2950475743 @default.
- W3173486383 hasRelatedWork W3003847115 @default.
- W3173486383 hasRelatedWork W3024479225 @default.
- W3173486383 hasRelatedWork W3041443116 @default.
- W3173486383 hasRelatedWork W3133954817 @default.
- W3173486383 hasRelatedWork W3162343139 @default.
- W3173486383 hasRelatedWork W3171371563 @default.
- W3173486383 hasRelatedWork W4206451978 @default.
- W3173486383 hasRelatedWork W4386603768 @default.
- W3173486383 hasRelatedWork W4387163578 @default.
- W3173486383 hasVolume "40" @default.
- W3173486383 isParatext "false" @default.
- W3173486383 isRetracted "false" @default.
- W3173486383 magId "3173486383" @default.
- W3173486383 workType "article" @default.