FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4308889883> ?p ?o ?g. }

• W4308889883 endingPage "102693" @default.
• W4308889883 startingPage "102693" @default.
• W4308889883 abstract "Skin cancer is one of the most common types of malignancy, affecting a large population and causing a heavy economic burden worldwide. Over the last few years, computer-aided diagnosis has been rapidly developed and make great progress in healthcare and medical practices due to the advances in artificial intelligence, particularly with the adoption of convolutional neural networks. However, most studies in skin cancer detection keep pursuing high prediction accuracies without considering the limitation of computing resources on portable devices. In this case, the knowledge distillation (KD) method has been proven as an efficient tool to help improve the adaptability of lightweight models under limited resources, meanwhile keeping a high-level representation capability. To bridge the gap, this study specifically proposes a novel method, termed SSD-KD, that unifies diverse knowledge into a generic KD framework for skin disease classification. Our method models an intra-instance relational feature representation and integrates it with existing KD research. A dual relational knowledge distillation architecture is self-supervised trained while the weighted softened outputs are also exploited to enable the student model to capture richer knowledge from the teacher model. To demonstrate the effectiveness of our method, we conduct experiments on ISIC 2019, a large-scale open-accessed benchmark of skin diseases dermoscopic images. Experiments show that our distilled MobileNetV2 can achieve an accuracy as high as 85% for the classification tasks of 8 different skin diseases with minimal parameters and computing requirements. Ablation studies confirm the effectiveness of our intra- and inter-instance relational knowledge integration strategy. Compared with state-of-the-art knowledge distillation techniques, the proposed method demonstrates improved performance. To the best of our knowledge, this is the first deep knowledge distillation application for multi-disease classification on the large-scale dermoscopy database. Our codes and models are available at https://github.com/enkiwang/Portable-Skin-Lesion-Diagnosis." @default.
• W4308889883 created "2022-11-18" @default.
• W4308889883 creator A5025837094 @default.
• W4308889883 creator A5029801412 @default.
• W4308889883 creator A5031816528 @default.
• W4308889883 creator A5057424890 @default.
• W4308889883 creator A5060231320 @default.
• W4308889883 creator A5087105596 @default.
• W4308889883 date "2023-02-01" @default.
• W4308889883 modified "2023-10-16" @default.
• W4308889883 title "SSD-KD: A self-supervised diverse knowledge distillation method for lightweight skin lesion classification using dermoscopic images" @default.
• W4308889883 cites W2003834444 @default.
• W4308889883 cites W2096457735 @default.
• W4308889883 cites W2194775991 @default.
• W4308889883 cites W2581082771 @default.
• W4308889883 cites W2592929672 @default.
• W4308889883 cites W2739879705 @default.
• W4308889883 cites W2797527544 @default.
• W4308889883 cites W2808402517 @default.
• W4308889883 cites W2891595725 @default.
• W4308889883 cites W2911818805 @default.
• W4308889883 cites W2916845318 @default.
• W4308889883 cites W2944102448 @default.
• W4308889883 cites W2955192706 @default.
• W4308889883 cites W2962858109 @default.
• W4308889883 cites W2963140444 @default.
• W4308889883 cites W2963163009 @default.
• W4308889883 cites W2982242214 @default.
• W4308889883 cites W2986015886 @default.
• W4308889883 cites W3011885901 @default.
• W4308889883 cites W3023371261 @default.
• W4308889883 cites W3024889886 @default.
• W4308889883 cites W3034368386 @default.
• W4308889883 cites W3035524453 @default.
• W4308889883 cites W3036935029 @default.
• W4308889883 cites W3102785203 @default.
• W4308889883 cites W3112557529 @default.
• W4308889883 cites W3123619653 @default.
• W4308889883 cites W3127990383 @default.
• W4308889883 cites W3133356497 @default.
• W4308889883 cites W3156313549 @default.
• W4308889883 cites W3174820339 @default.
• W4308889883 cites W3185556852 @default.
• W4308889883 cites W3198718561 @default.
• W4308889883 cites W3200618987 @default.
• W4308889883 cites W3201046531 @default.
• W4308889883 cites W3215150387 @default.
• W4308889883 cites W4280577324 @default.
• W4308889883 doi "https://doi.org/10.1016/j.media.2022.102693" @default.
• W4308889883 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/36462373" @default.
• W4308889883 hasPublicationYear "2023" @default.
• W4308889883 type Work @default.
• W4308889883 citedByCount "8" @default.
• W4308889883 countsByYear W43088898832022 @default.
• W4308889883 countsByYear W43088898832023 @default.
• W4308889883 crossrefType "journal-article" @default.
• W4308889883 hasAuthorship W4308889883A5025837094 @default.
• W4308889883 hasAuthorship W4308889883A5029801412 @default.
• W4308889883 hasAuthorship W4308889883A5031816528 @default.
• W4308889883 hasAuthorship W4308889883A5057424890 @default.
• W4308889883 hasAuthorship W4308889883A5060231320 @default.
• W4308889883 hasAuthorship W4308889883A5087105596 @default.
• W4308889883 hasBestOaLocation W43088898832 @default.
• W4308889883 hasConcept C119857082 @default.
• W4308889883 hasConcept C127413603 @default.
• W4308889883 hasConcept C13280743 @default.
• W4308889883 hasConcept C138885662 @default.
• W4308889883 hasConcept C153180895 @default.
• W4308889883 hasConcept C154945302 @default.
• W4308889883 hasConcept C185798385 @default.
• W4308889883 hasConcept C205649164 @default.
• W4308889883 hasConcept C2776401178 @default.
• W4308889883 hasConcept C2781018962 @default.
• W4308889883 hasConcept C41008148 @default.
• W4308889883 hasConcept C41895202 @default.
• W4308889883 hasConcept C78519656 @default.
• W4308889883 hasConcept C81363708 @default.
• W4308889883 hasConceptScore W4308889883C119857082 @default.
• W4308889883 hasConceptScore W4308889883C127413603 @default.
• W4308889883 hasConceptScore W4308889883C13280743 @default.
• W4308889883 hasConceptScore W4308889883C138885662 @default.
• W4308889883 hasConceptScore W4308889883C153180895 @default.
• W4308889883 hasConceptScore W4308889883C154945302 @default.
• W4308889883 hasConceptScore W4308889883C185798385 @default.
• W4308889883 hasConceptScore W4308889883C205649164 @default.
• W4308889883 hasConceptScore W4308889883C2776401178 @default.
• W4308889883 hasConceptScore W4308889883C2781018962 @default.
• W4308889883 hasConceptScore W4308889883C41008148 @default.
• W4308889883 hasConceptScore W4308889883C41895202 @default.
• W4308889883 hasConceptScore W4308889883C78519656 @default.
• W4308889883 hasConceptScore W4308889883C81363708 @default.
• W4308889883 hasFunder F4320321001 @default.
• W4308889883 hasFunder F4320334593 @default.
• W4308889883 hasLocation W43088898831 @default.
• W4308889883 hasLocation W43088898832 @default.
• W4308889883 hasLocation W43088898833 @default.
• W4308889883 hasOpenAccess W4308889883 @default.
• W4308889883 hasPrimaryLocation W43088898831 @default.

• next