Matches in SemOpenAlex for { <https://semopenalex.org/work/W3211966350> ?p ?o ?g. }
Showing items 1 to 96 of
96
with 100 items per page.
- W3211966350 abstract "Automatic surface inspection (ASI) to identify defects in manufactured items plays an important role in ensuring the production quality in industrial manufacturing processes. Various approaches have been proposed for this purpose, and the majority of them use supervised learning. Supervised learning requires labelled data for training. Obtaining a large amount of labelled data is a difficult, and time consuming task. On the other hand, Semi-supervised learning approaches become popular for ASI, as they make use of both labelled and unlabelled data. In this work, we propose a Convolutional Neural Network based semi-supervised learning approach for the recognition of steel surface defects. Our approach predicts the labels of the unlabelled data, and weights them based on their prediction confidence. These weighted samples are then used with their corresponding predicted labels, together with the labelled data for training the network. Our approach mainly differs from the existing approaches in the way the unlabelled samples are weighted when training the network. We propose to weight the samples based on how confidently they are predicted. We propose a margin-based approach to determine the prediction confidence. Experimental results on a public steel surface detection dataset (NEU surface defects) show that the proposed method can achieve a state-of-the-art accuracy of 99.15 ±0.08%, which is competitive compared to the performance achieved by fully supervised deep learning approaches, but ours with only 10% of labelled training data compared to the supervised learning approaches. In addition, comparison with recently proposed semi supervised learning approaches for ASI shows the effectiveness of our approach." @default.
- W3211966350 created "2021-11-22" @default.
- W3211966350 creator A5024392066 @default.
- W3211966350 creator A5034948659 @default.
- W3211966350 date "2021-08-11" @default.
- W3211966350 modified "2023-10-16" @default.
- W3211966350 title "A Semi-Supervised Deep Learning Approach for the Classification of Steel Surface Defects" @default.
- W3211966350 cites W1986306729 @default.
- W3211966350 cites W2012496675 @default.
- W3211966350 cites W2088478449 @default.
- W3211966350 cites W2092072518 @default.
- W3211966350 cites W211198884 @default.
- W3211966350 cites W2125629257 @default.
- W3211966350 cites W2194775991 @default.
- W3211966350 cites W234388709 @default.
- W3211966350 cites W2526017544 @default.
- W3211966350 cites W2588054711 @default.
- W3211966350 cites W2589306531 @default.
- W3211966350 cites W2591544917 @default.
- W3211966350 cites W2768955070 @default.
- W3211966350 cites W2791709739 @default.
- W3211966350 cites W2890747436 @default.
- W3211966350 cites W2912069721 @default.
- W3211966350 cites W2953868242 @default.
- W3211966350 cites W2964317695 @default.
- W3211966350 cites W2966341653 @default.
- W3211966350 cites W3010618895 @default.
- W3211966350 cites W3012374719 @default.
- W3211966350 cites W3035053225 @default.
- W3211966350 cites W3036833780 @default.
- W3211966350 cites W3047704379 @default.
- W3211966350 cites W3093398859 @default.
- W3211966350 cites W344203161 @default.
- W3211966350 doi "https://doi.org/10.1109/iciafs52090.2021.9606143" @default.
- W3211966350 hasPublicationYear "2021" @default.
- W3211966350 type Work @default.
- W3211966350 sameAs 3211966350 @default.
- W3211966350 citedByCount "4" @default.
- W3211966350 countsByYear W32119663502022 @default.
- W3211966350 countsByYear W32119663502023 @default.
- W3211966350 crossrefType "proceedings-article" @default.
- W3211966350 hasAuthorship W3211966350A5024392066 @default.
- W3211966350 hasAuthorship W3211966350A5034948659 @default.
- W3211966350 hasConcept C108583219 @default.
- W3211966350 hasConcept C119857082 @default.
- W3211966350 hasConcept C127413603 @default.
- W3211966350 hasConcept C136389625 @default.
- W3211966350 hasConcept C153180895 @default.
- W3211966350 hasConcept C154945302 @default.
- W3211966350 hasConcept C176217482 @default.
- W3211966350 hasConcept C201995342 @default.
- W3211966350 hasConcept C21547014 @default.
- W3211966350 hasConcept C24756922 @default.
- W3211966350 hasConcept C2776145971 @default.
- W3211966350 hasConcept C2780451532 @default.
- W3211966350 hasConcept C41008148 @default.
- W3211966350 hasConcept C42199009 @default.
- W3211966350 hasConcept C50644808 @default.
- W3211966350 hasConcept C58973888 @default.
- W3211966350 hasConcept C774472 @default.
- W3211966350 hasConcept C81363708 @default.
- W3211966350 hasConceptScore W3211966350C108583219 @default.
- W3211966350 hasConceptScore W3211966350C119857082 @default.
- W3211966350 hasConceptScore W3211966350C127413603 @default.
- W3211966350 hasConceptScore W3211966350C136389625 @default.
- W3211966350 hasConceptScore W3211966350C153180895 @default.
- W3211966350 hasConceptScore W3211966350C154945302 @default.
- W3211966350 hasConceptScore W3211966350C176217482 @default.
- W3211966350 hasConceptScore W3211966350C201995342 @default.
- W3211966350 hasConceptScore W3211966350C21547014 @default.
- W3211966350 hasConceptScore W3211966350C24756922 @default.
- W3211966350 hasConceptScore W3211966350C2776145971 @default.
- W3211966350 hasConceptScore W3211966350C2780451532 @default.
- W3211966350 hasConceptScore W3211966350C41008148 @default.
- W3211966350 hasConceptScore W3211966350C42199009 @default.
- W3211966350 hasConceptScore W3211966350C50644808 @default.
- W3211966350 hasConceptScore W3211966350C58973888 @default.
- W3211966350 hasConceptScore W3211966350C774472 @default.
- W3211966350 hasConceptScore W3211966350C81363708 @default.
- W3211966350 hasLocation W32119663501 @default.
- W3211966350 hasOpenAccess W3211966350 @default.
- W3211966350 hasPrimaryLocation W32119663501 @default.
- W3211966350 hasRelatedWork W1756896031 @default.
- W3211966350 hasRelatedWork W2531570999 @default.
- W3211966350 hasRelatedWork W2597787948 @default.
- W3211966350 hasRelatedWork W2795261237 @default.
- W3211966350 hasRelatedWork W3162567751 @default.
- W3211966350 hasRelatedWork W3173641157 @default.
- W3211966350 hasRelatedWork W3211966350 @default.
- W3211966350 hasRelatedWork W4220686584 @default.
- W3211966350 hasRelatedWork W4246751904 @default.
- W3211966350 hasRelatedWork W4312414840 @default.
- W3211966350 isParatext "false" @default.
- W3211966350 isRetracted "false" @default.
- W3211966350 magId "3211966350" @default.
- W3211966350 workType "article" @default.