FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3117687561> ?p ?o ?g. }

• W3117687561 abstract "Convolutional Networks have dominated the field of computer vision for the last ten years, exhibiting extremely powerful feature extraction capabilities and outstanding classification performance. The main strategy to prolong this trend relies on further upscaling networks in size. However, costs increase rapidly while performance improvements may be marginal. We hypothesise that adding heterogeneous sources of information may be more cost-effective to a CNN than building a bigger network. In this paper, an ensemble method is proposed for accurate image classification, fusing automatically detected features through Convolutional Neural Network architectures with a set of manually defined statistical indicators. Through a combination of the predictions of a CNN and a secondary classifier trained on statistical features, better classification performance can be cheaply achieved. We test multiple learning algorithms and CNN architectures on a diverse number of datasets to validate our proposal, making public all our code and data via GitHub. According to our results, the inclusion of additional indicators and an ensemble classification approach helps to increase the performance in 8 of 9 datasets, with a remarkable increase of more than 10% precision in two of them." @default.
• W3117687561 created "2021-01-05" @default.
• W3117687561 creator A5030022807 @default.
• W3117687561 creator A5040465870 @default.
• W3117687561 creator A5068081385 @default.
• W3117687561 creator A5084942207 @default.
• W3117687561 date "2020-12-20" @default.
• W3117687561 modified "2023-10-01" @default.
• W3117687561 title "Fusing CNNs and statistical indicators to improve image classification" @default.
• W3117687561 cites W1538131130 @default.
• W3117687561 cites W1686810756 @default.
• W3117687561 cites W1705245392 @default.
• W3117687561 cites W1821462560 @default.
• W3117687561 cites W184846379 @default.
• W3117687561 cites W1991792143 @default.
• W3117687561 cites W1996061706 @default.
• W3117687561 cites W1999311199 @default.
• W3117687561 cites W2004254965 @default.
• W3117687561 cites W2014418634 @default.
• W3117687561 cites W2020426296 @default.
• W3117687561 cites W2029169758 @default.
• W3117687561 cites W2031775731 @default.
• W3117687561 cites W2044465660 @default.
• W3117687561 cites W2071039340 @default.
• W3117687561 cites W2077658674 @default.
• W3117687561 cites W2087016914 @default.
• W3117687561 cites W2095649164 @default.
• W3117687561 cites W2101234009 @default.
• W3117687561 cites W2112504244 @default.
• W3117687561 cites W2119531715 @default.
• W3117687561 cites W2119821739 @default.
• W3117687561 cites W2120846928 @default.
• W3117687561 cites W2127789936 @default.
• W3117687561 cites W2137664016 @default.
• W3117687561 cites W2138011018 @default.
• W3117687561 cites W2156749117 @default.
• W3117687561 cites W2163352848 @default.
• W3117687561 cites W2163814366 @default.
• W3117687561 cites W2183341477 @default.
• W3117687561 cites W2194775991 @default.
• W3117687561 cites W2274287116 @default.
• W3117687561 cites W2279098554 @default.
• W3117687561 cites W2279781308 @default.
• W3117687561 cites W2280764670 @default.
• W3117687561 cites W2533598788 @default.
• W3117687561 cites W2563823404 @default.
• W3117687561 cites W2565516711 @default.
• W3117687561 cites W2612445135 @default.
• W3117687561 cites W2613227812 @default.
• W3117687561 cites W2618530766 @default.
• W3117687561 cites W2736941579 @default.
• W3117687561 cites W2766839578 @default.
• W3117687561 cites W2774571784 @default.
• W3117687561 cites W2776154048 @default.
• W3117687561 cites W2776637495 @default.
• W3117687561 cites W2785430118 @default.
• W3117687561 cites W2793708128 @default.
• W3117687561 cites W2799742832 @default.
• W3117687561 cites W2799899460 @default.
• W3117687561 cites W2901299405 @default.
• W3117687561 cites W2911964244 @default.
• W3117687561 cites W2941380944 @default.
• W3117687561 cites W2947576068 @default.
• W3117687561 cites W2952054889 @default.
• W3117687561 cites W2955425717 @default.
• W3117687561 cites W2962953743 @default.
• W3117687561 cites W2963125010 @default.
• W3117687561 cites W2963363373 @default.
• W3117687561 cites W2963446712 @default.
• W3117687561 cites W2964233199 @default.
• W3117687561 cites W2969364300 @default.
• W3117687561 cites W2974874674 @default.
• W3117687561 cites W2985754007 @default.
• W3117687561 cites W2990440987 @default.
• W3117687561 cites W2997428643 @default.
• W3117687561 cites W2997495997 @default.
• W3117687561 cites W3004983395 @default.
• W3117687561 cites W3008809756 @default.
• W3117687561 cites W3030163527 @default.
• W3117687561 cites W3037032032 @default.
• W3117687561 cites W3039690871 @default.
• W3117687561 cites W3048672684 @default.
• W3117687561 cites W3083390138 @default.
• W3117687561 cites W3128999341 @default.
• W3117687561 cites W3149698317 @default.
• W3117687561 cites W3155832727 @default.
• W3117687561 cites W14333344 @default.
• W3117687561 hasPublicationYear "2020" @default.
• W3117687561 type Work @default.
• W3117687561 sameAs 3117687561 @default.
• W3117687561 citedByCount "0" @default.
• W3117687561 crossrefType "posted-content" @default.
• W3117687561 hasAuthorship W3117687561A5030022807 @default.
• W3117687561 hasAuthorship W3117687561A5040465870 @default.
• W3117687561 hasAuthorship W3117687561A5068081385 @default.
• W3117687561 hasAuthorship W3117687561A5084942207 @default.
• W3117687561 hasConcept C111919701 @default.
• W3117687561 hasConcept C115961682 @default.
• W3117687561 hasConcept C119857082 @default.
• W3117687561 hasConcept C124101348 @default.

• next