Matches in SemOpenAlex for { <https://semopenalex.org/work/W4298090150> ?p ?o ?g. }
Showing items 1 to 73 of
73
with 100 items per page.
- W4298090150 abstract "Image classification forms an important class of problems in machine learning and is widely used in many realworld applications, such as medicine, ecology, astronomy, and defense. Convolutional neural networks (CNNs) are machine learning techniques designed for inputs with grid structures, e.g., images, whose features are spatially correlated. As such, CNNs have been demonstrated to be highly effective approaches for many image classification problems and have consistently outperformed other approaches in many image classification and object detection competitions. A particular challenge involved in using machine learning for classifying images is measurement data loss in the form of missing pixels, which occurs in settings where scene occlusions are present or where the photodetectors in the imaging system are partially damaged. In such cases, the performance of CNN models tends to deteriorate or becomes unreliable even when the perturbations to the input image are small. In this work, we investigate techniques for improving the performance of CNN models for image classification with missing data. In particular, we explore training on a variety of data alterations that mimic data loss for producing more robust classifiers. By optimizing the categorical cross-entropy loss function, we demonstrate through numerical experiments on the MNIST dataset that training with these synthetic alterations can enhance the classification accuracy of our CNN models." @default.
- W4298090150 created "2022-10-01" @default.
- W4298090150 creator A5005703929 @default.
- W4298090150 creator A5054847250 @default.
- W4298090150 creator A5075301677 @default.
- W4298090150 date "2022-10-03" @default.
- W4298090150 modified "2023-09-30" @default.
- W4298090150 title "Image classification and training with severe data loss" @default.
- W4298090150 cites W1964994226 @default.
- W4298090150 cites W2000983850 @default.
- W4298090150 cites W2045002121 @default.
- W4298090150 cites W2094562791 @default.
- W4298090150 cites W2113665876 @default.
- W4298090150 cites W2119936234 @default.
- W4298090150 cites W2344480160 @default.
- W4298090150 cites W2559324447 @default.
- W4298090150 cites W2561278319 @default.
- W4298090150 cites W2588978745 @default.
- W4298090150 cites W2601438013 @default.
- W4298090150 cites W2777427437 @default.
- W4298090150 cites W2783265781 @default.
- W4298090150 cites W2787894218 @default.
- W4298090150 cites W4233219797 @default.
- W4298090150 cites W4245996949 @default.
- W4298090150 cites W4246376820 @default.
- W4298090150 doi "https://doi.org/10.1117/12.2633172" @default.
- W4298090150 hasPublicationYear "2022" @default.
- W4298090150 type Work @default.
- W4298090150 citedByCount "0" @default.
- W4298090150 crossrefType "proceedings-article" @default.
- W4298090150 hasAuthorship W4298090150A5005703929 @default.
- W4298090150 hasAuthorship W4298090150A5054847250 @default.
- W4298090150 hasAuthorship W4298090150A5075301677 @default.
- W4298090150 hasConcept C108583219 @default.
- W4298090150 hasConcept C115961682 @default.
- W4298090150 hasConcept C119857082 @default.
- W4298090150 hasConcept C153180895 @default.
- W4298090150 hasConcept C154945302 @default.
- W4298090150 hasConcept C160633673 @default.
- W4298090150 hasConcept C190502265 @default.
- W4298090150 hasConcept C2776151529 @default.
- W4298090150 hasConcept C41008148 @default.
- W4298090150 hasConcept C5274069 @default.
- W4298090150 hasConcept C75294576 @default.
- W4298090150 hasConcept C81363708 @default.
- W4298090150 hasConceptScore W4298090150C108583219 @default.
- W4298090150 hasConceptScore W4298090150C115961682 @default.
- W4298090150 hasConceptScore W4298090150C119857082 @default.
- W4298090150 hasConceptScore W4298090150C153180895 @default.
- W4298090150 hasConceptScore W4298090150C154945302 @default.
- W4298090150 hasConceptScore W4298090150C160633673 @default.
- W4298090150 hasConceptScore W4298090150C190502265 @default.
- W4298090150 hasConceptScore W4298090150C2776151529 @default.
- W4298090150 hasConceptScore W4298090150C41008148 @default.
- W4298090150 hasConceptScore W4298090150C5274069 @default.
- W4298090150 hasConceptScore W4298090150C75294576 @default.
- W4298090150 hasConceptScore W4298090150C81363708 @default.
- W4298090150 hasLocation W42980901501 @default.
- W4298090150 hasOpenAccess W4298090150 @default.
- W4298090150 hasPrimaryLocation W42980901501 @default.
- W4298090150 hasRelatedWork W2726121760 @default.
- W4298090150 hasRelatedWork W2732542196 @default.
- W4298090150 hasRelatedWork W2774444957 @default.
- W4298090150 hasRelatedWork W2799614062 @default.
- W4298090150 hasRelatedWork W3214521593 @default.
- W4298090150 hasRelatedWork W4287394362 @default.
- W4298090150 hasRelatedWork W4309224979 @default.
- W4298090150 hasRelatedWork W4311257506 @default.
- W4298090150 hasRelatedWork W4317374280 @default.
- W4298090150 hasRelatedWork W564581980 @default.
- W4298090150 isParatext "false" @default.
- W4298090150 isRetracted "false" @default.
- W4298090150 workType "article" @default.