Matches in SemOpenAlex for { <https://semopenalex.org/work/W4328007082> ?p ?o ?g. }
- W4328007082 endingPage "2897" @default.
- W4328007082 startingPage "2886" @default.
- W4328007082 abstract "Segmentation of skin lesions is a critical step in the process of skin lesion diagnosis. Such segmentation is challenging due to the irregular shape, fuzzy contours and severe noise interference in the skin lesion region. Existing deep learning-based skin lesion segmentation methods are usually computationally expensive, hindering their deployment in dermoscopic devices with poor computational power. To address these challenges, we propose an ultralightweight fully asymmetric convolutional network for skin lesion segmentation, called ULFAC-Net. we use a parallel asymmetric convolutional (PAC) module to extract features instead of the traditional square convolution, and innovatively propose a PAC module with dual attention (Att-PAC) to enhance the feature representation. Based on the PAC and Att-PAC modules, we further propose a lightweight textual information submodule. To balance the number of parameters and performance of the model, we also hand-design an asymmetric encoder-decoder architecture. In this paper, we validate the effectiveness and robustness of the proposed ULFAC-Net on four publicly available skin lesion segmentation datasets (ISIC2018, ISBI2017, ISIC2016 and PH2 datasets). The experimental results show that ULFAC-Net achieves competitive segmentation performance with only 0.842 million(0.842M) parameters and 3.71 gigabytes of floating point operations (GFLOPs) compared to other state-of-the-art methods." @default.
- W4328007082 created "2023-03-22" @default.
- W4328007082 creator A5009175586 @default.
- W4328007082 creator A5034243402 @default.
- W4328007082 creator A5035234802 @default.
- W4328007082 creator A5037162506 @default.
- W4328007082 creator A5044608144 @default.
- W4328007082 creator A5090268445 @default.
- W4328007082 date "2023-06-01" @default.
- W4328007082 modified "2023-10-18" @default.
- W4328007082 title "ULFAC-Net: Ultra-Lightweight Fully Asymmetric Convolutional Network for Skin Lesion Segmentation" @default.
- W4328007082 cites W2031491792 @default.
- W4328007082 cites W2183341477 @default.
- W4328007082 cites W2795587607 @default.
- W4328007082 cites W2884436604 @default.
- W4328007082 cites W2885668531 @default.
- W4328007082 cites W2961217518 @default.
- W4328007082 cites W2962767316 @default.
- W4328007082 cites W2963062226 @default.
- W4328007082 cites W2963881378 @default.
- W4328007082 cites W2963946669 @default.
- W4328007082 cites W2976558185 @default.
- W4328007082 cites W2981609437 @default.
- W4328007082 cites W2994026422 @default.
- W4328007082 cites W3006349040 @default.
- W4328007082 cites W3014419815 @default.
- W4328007082 cites W3015788359 @default.
- W4328007082 cites W3021895818 @default.
- W4328007082 cites W3025800305 @default.
- W4328007082 cites W3027969476 @default.
- W4328007082 cites W3034926724 @default.
- W4328007082 cites W3049710495 @default.
- W4328007082 cites W3096799072 @default.
- W4328007082 cites W3131384866 @default.
- W4328007082 cites W3162496671 @default.
- W4328007082 cites W3170602982 @default.
- W4328007082 cites W3174778426 @default.
- W4328007082 cites W3175649216 @default.
- W4328007082 cites W3176224216 @default.
- W4328007082 cites W3193256763 @default.
- W4328007082 cites W4200015473 @default.
- W4328007082 cites W4205324329 @default.
- W4328007082 cites W4220669396 @default.
- W4328007082 cites W4224234930 @default.
- W4328007082 cites W4226118487 @default.
- W4328007082 cites W4281688409 @default.
- W4328007082 cites W4287729825 @default.
- W4328007082 cites W4315754639 @default.
- W4328007082 doi "https://doi.org/10.1109/jbhi.2023.3259802" @default.
- W4328007082 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37030688" @default.
- W4328007082 hasPublicationYear "2023" @default.
- W4328007082 type Work @default.
- W4328007082 citedByCount "1" @default.
- W4328007082 countsByYear W43280070822023 @default.
- W4328007082 crossrefType "journal-article" @default.
- W4328007082 hasAuthorship W4328007082A5009175586 @default.
- W4328007082 hasAuthorship W4328007082A5034243402 @default.
- W4328007082 hasAuthorship W4328007082A5035234802 @default.
- W4328007082 hasAuthorship W4328007082A5037162506 @default.
- W4328007082 hasAuthorship W4328007082A5044608144 @default.
- W4328007082 hasAuthorship W4328007082A5090268445 @default.
- W4328007082 hasConcept C104317684 @default.
- W4328007082 hasConcept C108583219 @default.
- W4328007082 hasConcept C111919701 @default.
- W4328007082 hasConcept C118505674 @default.
- W4328007082 hasConcept C124504099 @default.
- W4328007082 hasConcept C153180895 @default.
- W4328007082 hasConcept C154945302 @default.
- W4328007082 hasConcept C185592680 @default.
- W4328007082 hasConcept C41008148 @default.
- W4328007082 hasConcept C55493867 @default.
- W4328007082 hasConcept C63479239 @default.
- W4328007082 hasConcept C81363708 @default.
- W4328007082 hasConcept C89600930 @default.
- W4328007082 hasConceptScore W4328007082C104317684 @default.
- W4328007082 hasConceptScore W4328007082C108583219 @default.
- W4328007082 hasConceptScore W4328007082C111919701 @default.
- W4328007082 hasConceptScore W4328007082C118505674 @default.
- W4328007082 hasConceptScore W4328007082C124504099 @default.
- W4328007082 hasConceptScore W4328007082C153180895 @default.
- W4328007082 hasConceptScore W4328007082C154945302 @default.
- W4328007082 hasConceptScore W4328007082C185592680 @default.
- W4328007082 hasConceptScore W4328007082C41008148 @default.
- W4328007082 hasConceptScore W4328007082C55493867 @default.
- W4328007082 hasConceptScore W4328007082C63479239 @default.
- W4328007082 hasConceptScore W4328007082C81363708 @default.
- W4328007082 hasConceptScore W4328007082C89600930 @default.
- W4328007082 hasFunder F4320321001 @default.
- W4328007082 hasIssue "6" @default.
- W4328007082 hasLocation W43280070821 @default.
- W4328007082 hasLocation W43280070822 @default.
- W4328007082 hasOpenAccess W4328007082 @default.
- W4328007082 hasPrimaryLocation W43280070821 @default.
- W4328007082 hasRelatedWork W2731899572 @default.
- W4328007082 hasRelatedWork W2790662084 @default.
- W4328007082 hasRelatedWork W2960184797 @default.
- W4328007082 hasRelatedWork W2999805992 @default.
- W4328007082 hasRelatedWork W3116150086 @default.