Matches in SemOpenAlex for { <https://semopenalex.org/work/W3202065448> ?p ?o ?g. }
Showing items 1 to 74 of
74
with 100 items per page.
- W3202065448 abstract "Recently, deep neural networks achieved state-of-the-art results on the automated diagnosis of skin lesions. Both the availability of bigger and better datasets as well as major advancements in Convolutional Neural Network methodologies represent some of the reasons behind these results. While the former is powered by initiatives like the International Skin Imaging Collaboration (ISIC), the latter is potentiated by developments in CNN architectures and the rise of transfer learning. This paper addresses open research questions related to the effectiveness of transfer learning methods in the context of multi-class skin lesion classification. The results indicate that, depending on the way pre-trained models are re-purposed, recent CNN architectures can bring significant performance boosts on the overall performance of deep learning classifiers. Experiments also highlight the importance of a good dataset to train these models, and how class balancing through data augmentation can help ease this requirement. Furthermore, experimentation with different models shows that ensembles can bring an edge over single-model approaches. Finally, this work presents a competitive single- and multi-model approach to the ISIC 2019 challenge." @default.
- W3202065448 created "2021-10-11" @default.
- W3202065448 creator A5003703785 @default.
- W3202065448 creator A5041531122 @default.
- W3202065448 creator A5077541727 @default.
- W3202065448 date "2021-08-25" @default.
- W3202065448 modified "2023-10-18" @default.
- W3202065448 title "Transfer Learning for Skin Lesion Classification using Convolutional Neural Networks" @default.
- W3202065448 cites W2117539524 @default.
- W3202065448 cites W2183341477 @default.
- W3202065448 cites W2194775991 @default.
- W3202065448 cites W2302255633 @default.
- W3202065448 cites W2581082771 @default.
- W3202065448 cites W2786147899 @default.
- W3202065448 cites W2797527544 @default.
- W3202065448 cites W2806853752 @default.
- W3202065448 cites W2890655382 @default.
- W3202065448 cites W2891595725 @default.
- W3202065448 cites W2897340145 @default.
- W3202065448 cites W2903060508 @default.
- W3202065448 cites W2952971376 @default.
- W3202065448 doi "https://doi.org/10.1109/inista52262.2021.9548455" @default.
- W3202065448 hasPublicationYear "2021" @default.
- W3202065448 type Work @default.
- W3202065448 sameAs 3202065448 @default.
- W3202065448 citedByCount "3" @default.
- W3202065448 countsByYear W32020654482022 @default.
- W3202065448 countsByYear W32020654482023 @default.
- W3202065448 crossrefType "proceedings-article" @default.
- W3202065448 hasAuthorship W3202065448A5003703785 @default.
- W3202065448 hasAuthorship W3202065448A5041531122 @default.
- W3202065448 hasAuthorship W3202065448A5077541727 @default.
- W3202065448 hasConcept C108583219 @default.
- W3202065448 hasConcept C119857082 @default.
- W3202065448 hasConcept C150899416 @default.
- W3202065448 hasConcept C151730666 @default.
- W3202065448 hasConcept C154945302 @default.
- W3202065448 hasConcept C162307627 @default.
- W3202065448 hasConcept C2777212361 @default.
- W3202065448 hasConcept C2779343474 @default.
- W3202065448 hasConcept C2984842247 @default.
- W3202065448 hasConcept C41008148 @default.
- W3202065448 hasConcept C81363708 @default.
- W3202065448 hasConcept C86803240 @default.
- W3202065448 hasConceptScore W3202065448C108583219 @default.
- W3202065448 hasConceptScore W3202065448C119857082 @default.
- W3202065448 hasConceptScore W3202065448C150899416 @default.
- W3202065448 hasConceptScore W3202065448C151730666 @default.
- W3202065448 hasConceptScore W3202065448C154945302 @default.
- W3202065448 hasConceptScore W3202065448C162307627 @default.
- W3202065448 hasConceptScore W3202065448C2777212361 @default.
- W3202065448 hasConceptScore W3202065448C2779343474 @default.
- W3202065448 hasConceptScore W3202065448C2984842247 @default.
- W3202065448 hasConceptScore W3202065448C41008148 @default.
- W3202065448 hasConceptScore W3202065448C81363708 @default.
- W3202065448 hasConceptScore W3202065448C86803240 @default.
- W3202065448 hasFunder F4320330374 @default.
- W3202065448 hasLocation W32020654481 @default.
- W3202065448 hasOpenAccess W3202065448 @default.
- W3202065448 hasPrimaryLocation W32020654481 @default.
- W3202065448 hasRelatedWork W2951211570 @default.
- W3202065448 hasRelatedWork W3133861977 @default.
- W3202065448 hasRelatedWork W3167935049 @default.
- W3202065448 hasRelatedWork W3183901164 @default.
- W3202065448 hasRelatedWork W3192840557 @default.
- W3202065448 hasRelatedWork W3193565141 @default.
- W3202065448 hasRelatedWork W4206357785 @default.
- W3202065448 hasRelatedWork W4226493464 @default.
- W3202065448 hasRelatedWork W4281381188 @default.
- W3202065448 hasRelatedWork W4312417841 @default.
- W3202065448 isParatext "false" @default.
- W3202065448 isRetracted "false" @default.
- W3202065448 magId "3202065448" @default.
- W3202065448 workType "article" @default.