FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4387121213> ?p ?o ?g. }

• W4387121213 endingPage "e1601" @default.
• W4387121213 startingPage "e1601" @default.
• W4387121213 abstract "Transfer learning involves using previously learnt knowledge of a model task in addressing another task. However, this process works well when the tasks are closely related. It is, therefore, important to select data points that are closely relevant to the previous task and fine-tune the suitable pre-trained model's layers for effective transfer. This work utilises the least divergent textural features of the target datasets and pre-trained model's layers, minimising the lost knowledge during the transfer learning process. This study extends previous works on selecting data points with good textural features and dynamically selected layers using divergence measures by combining them into one model pipeline. Five pre-trained models are used: ResNet50, DenseNet169, InceptionV3, VGG16 and MobileNetV2 on nine datasets: CIFAR-10, CIFAR-100, MNIST, Fashion-MNIST, Stanford Dogs, Caltech 256, ISIC 2016, ChestX-ray8 and MIT Indoor Scenes. Experimental results show that data points with lower textural feature divergence and layers with more positive weights give better accuracy than other data points and layers. The data points with lower divergence give an average improvement of 3.54% to 6.75%, while the layers improve by 2.42% to 13.04% for the CIFAR-100 dataset. Combining the two methods gives an extra accuracy improvement of 1.56%. This combined approach shows that data points with lower divergence from the source dataset samples can lead to a better adaptation for the target task. The results also demonstrate that selecting layers with more positive weights reduces instances of trial and error in selecting fine-tuning layers for pre-trained models." @default.
• W4387121213 created "2023-09-29" @default.
• W4387121213 creator A5028125445 @default.
• W4387121213 creator A5048860507 @default.
• W4387121213 creator A5071357744 @default.
• W4387121213 date "2023-09-28" @default.
• W4387121213 modified "2023-10-11" @default.
• W4387121213 title "Improved transfer learning using textural features conflation and dynamically fine-tuned layers" @default.
• W4387121213 cites W1586052137 @default.
• W4387121213 cites W1994302565 @default.
• W4387121213 cites W2008984713 @default.
• W4387121213 cites W2015249336 @default.
• W4387121213 cites W2044465660 @default.
• W4387121213 cites W2073172894 @default.
• W4387121213 cites W2143668817 @default.
• W4387121213 cites W2152690956 @default.
• W4387121213 cites W2192146613 @default.
• W4387121213 cites W2590822257 @default.
• W4387121213 cites W2593825114 @default.
• W4387121213 cites W2780360157 @default.
• W4387121213 cites W2892961888 @default.
• W4387121213 cites W2935033494 @default.
• W4387121213 cites W2963767194 @default.
• W4387121213 cites W2963934397 @default.
• W4387121213 cites W2968867485 @default.
• W4387121213 cites W2972887897 @default.
• W4387121213 cites W2988660047 @default.
• W4387121213 cites W2997788524 @default.
• W4387121213 cites W2998072408 @default.
• W4387121213 cites W2998957378 @default.
• W4387121213 cites W3009371949 @default.
• W4387121213 cites W3016244615 @default.
• W4387121213 cites W3025853597 @default.
• W4387121213 cites W3028737903 @default.
• W4387121213 cites W3035256099 @default.
• W4387121213 cites W3041133507 @default.
• W4387121213 cites W3048864164 @default.
• W4387121213 cites W3092197865 @default.
• W4387121213 cites W3096015486 @default.
• W4387121213 cites W3107935573 @default.
• W4387121213 cites W3120128936 @default.
• W4387121213 cites W3124174388 @default.
• W4387121213 cites W3149097960 @default.
• W4387121213 cites W3180815602 @default.
• W4387121213 cites W3195354253 @default.
• W4387121213 cites W3216932077 @default.
• W4387121213 cites W4223899585 @default.
• W4387121213 cites W4255747608 @default.
• W4387121213 cites W4285022937 @default.
• W4387121213 cites W4285393991 @default.
• W4387121213 cites W4287557095 @default.
• W4387121213 cites W4306369316 @default.
• W4387121213 cites W4310191038 @default.
• W4387121213 cites W4311304837 @default.
• W4387121213 cites W4312188028 @default.
• W4387121213 cites W4321457716 @default.
• W4387121213 cites W4321492520 @default.
• W4387121213 cites W4375854091 @default.
• W4387121213 doi "https://doi.org/10.7717/peerj-cs.1601" @default.
• W4387121213 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37810335" @default.
• W4387121213 hasPublicationYear "2023" @default.
• W4387121213 type Work @default.
• W4387121213 citedByCount "0" @default.
• W4387121213 crossrefType "journal-article" @default.
• W4387121213 hasAuthorship W4387121213A5028125445 @default.
• W4387121213 hasAuthorship W4387121213A5048860507 @default.
• W4387121213 hasAuthorship W4387121213A5071357744 @default.
• W4387121213 hasBestOaLocation W43871212131 @default.
• W4387121213 hasConcept C111919701 @default.
• W4387121213 hasConcept C119857082 @default.
• W4387121213 hasConcept C120665830 @default.
• W4387121213 hasConcept C121332964 @default.
• W4387121213 hasConcept C138885662 @default.
• W4387121213 hasConcept C139807058 @default.
• W4387121213 hasConcept C150899416 @default.
• W4387121213 hasConcept C153180895 @default.
• W4387121213 hasConcept C154945302 @default.
• W4387121213 hasConcept C162324750 @default.
• W4387121213 hasConcept C187736073 @default.
• W4387121213 hasConcept C190502265 @default.
• W4387121213 hasConcept C199360897 @default.
• W4387121213 hasConcept C207390915 @default.
• W4387121213 hasConcept C2776401178 @default.
• W4387121213 hasConcept C2780451532 @default.
• W4387121213 hasConcept C41008148 @default.
• W4387121213 hasConcept C41895202 @default.
• W4387121213 hasConcept C43521106 @default.
• W4387121213 hasConcept C50644808 @default.
• W4387121213 hasConcept C98045186 @default.
• W4387121213 hasConceptScore W4387121213C111919701 @default.
• W4387121213 hasConceptScore W4387121213C119857082 @default.
• W4387121213 hasConceptScore W4387121213C120665830 @default.
• W4387121213 hasConceptScore W4387121213C121332964 @default.
• W4387121213 hasConceptScore W4387121213C138885662 @default.
• W4387121213 hasConceptScore W4387121213C139807058 @default.
• W4387121213 hasConceptScore W4387121213C150899416 @default.
• W4387121213 hasConceptScore W4387121213C153180895 @default.
• W4387121213 hasConceptScore W4387121213C154945302 @default.

• next