FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3216289989> ?p ?o ?g. }

• W3216289989 abstract "Weakly-supervised learning has become a popular technology in recent years. In this paper, we propose a novel medical image classification algorithm, called Weakly-Supervised Generative Adversarial Networks (WSGAN), which only uses a small number of real images without labels to generate fake images or mask images to enlarge the sample size of the training set. First, we combine with MixMatch to generate pseudo labels for the fake images and unlabeled images to do the classification. Second, contrastive learning and self-attention mechanism are introduced into the proposed problem to enhance the classification accuracy. Third, the problem of mode collapse is well addressed by cyclic consistency loss. Finally, we design global and local classifiers to complement each other with the key information needed for classification. The experimental results on four medical image datasets show that WSGAN can obtain relatively high learning performance by using few labeled and unlabeled data. For example, the classification accuracy of WSGAN is 11% higher than that of the second-ranked MIXMATCH with 100 labeled images and 1000 unlabeled images on the OCT dataset. In addition, we also conduct ablation experiments to verify the effectiveness of our algorithm." @default.
• W3216289989 created "2021-12-06" @default.
• W3216289989 creator A5029462500 @default.
• W3216289989 creator A5036051515 @default.
• W3216289989 creator A5084922351 @default.
• W3216289989 creator A5087677226 @default.
• W3216289989 date "2021-11-29" @default.
• W3216289989 modified "2023-09-25" @default.
• W3216289989 title "Weakly-supervised Generative Adversarial Networks for medical image classification" @default.
• W3216289989 cites W1971840768 @default.
• W3216289989 cites W1973598714 @default.
• W3216289989 cites W2099471712 @default.
• W3216289989 cites W2125389028 @default.
• W3216289989 cites W2163605009 @default.
• W3216289989 cites W2178768799 @default.
• W3216289989 cites W2194775991 @default.
• W3216289989 cites W2412510955 @default.
• W3216289989 cites W2531409750 @default.
• W3216289989 cites W2546066744 @default.
• W3216289989 cites W2548275288 @default.
• W3216289989 cites W2554423077 @default.
• W3216289989 cites W2559597482 @default.
• W3216289989 cites W2593414223 @default.
• W3216289989 cites W2598991778 @default.
• W3216289989 cites W2610935556 @default.
• W3216289989 cites W2746791238 @default.
• W3216289989 cites W2798729263 @default.
• W3216289989 cites W2804078698 @default.
• W3216289989 cites W2889582485 @default.
• W3216289989 cites W2891158090 @default.
• W3216289989 cites W2893749619 @default.
• W3216289989 cites W2962770929 @default.
• W3216289989 cites W2962793481 @default.
• W3216289989 cites W2963073614 @default.
• W3216289989 cites W2963091558 @default.
• W3216289989 cites W2963170156 @default.
• W3216289989 cites W2963373786 @default.
• W3216289989 cites W2963403868 @default.
• W3216289989 cites W2963981733 @default.
• W3216289989 cites W2964159205 @default.
• W3216289989 cites W2978426779 @default.
• W3216289989 cites W2979798680 @default.
• W3216289989 cites W2982041717 @default.
• W3216289989 cites W3021553033 @default.
• W3216289989 cites W3028070348 @default.
• W3216289989 cites W3031064055 @default.
• W3216289989 cites W3034491749 @default.
• W3216289989 cites W3034978746 @default.
• W3216289989 cites W3035574324 @default.
• W3216289989 cites W3091449858 @default.
• W3216289989 cites W3108164655 @default.
• W3216289989 cites W3126089204 @default.
• W3216289989 cites W3138848412 @default.
• W3216289989 cites W3171007011 @default.
• W3216289989 cites W3176671950 @default.
• W3216289989 cites W3180562345 @default.
• W3216289989 doi "https://doi.org/10.48550/arxiv.2111.14605" @default.
• W3216289989 hasPublicationYear "2021" @default.
• W3216289989 type Work @default.
• W3216289989 sameAs 3216289989 @default.
• W3216289989 citedByCount "0" @default.
• W3216289989 crossrefType "posted-content" @default.
• W3216289989 hasAuthorship W3216289989A5029462500 @default.
• W3216289989 hasAuthorship W3216289989A5036051515 @default.
• W3216289989 hasAuthorship W3216289989A5084922351 @default.
• W3216289989 hasAuthorship W3216289989A5087677226 @default.
• W3216289989 hasBestOaLocation W32162899891 @default.
• W3216289989 hasConcept C104317684 @default.
• W3216289989 hasConcept C112313634 @default.
• W3216289989 hasConcept C115961682 @default.
• W3216289989 hasConcept C119857082 @default.
• W3216289989 hasConcept C127716648 @default.
• W3216289989 hasConcept C153180895 @default.
• W3216289989 hasConcept C154945302 @default.
• W3216289989 hasConcept C177264268 @default.
• W3216289989 hasConcept C185592680 @default.
• W3216289989 hasConcept C188082640 @default.
• W3216289989 hasConcept C199360897 @default.
• W3216289989 hasConcept C26517878 @default.
• W3216289989 hasConcept C2776436953 @default.
• W3216289989 hasConcept C38652104 @default.
• W3216289989 hasConcept C39890363 @default.
• W3216289989 hasConcept C41008148 @default.
• W3216289989 hasConcept C55493867 @default.
• W3216289989 hasConcept C58973888 @default.
• W3216289989 hasConcept C75294576 @default.
• W3216289989 hasConceptScore W3216289989C104317684 @default.
• W3216289989 hasConceptScore W3216289989C112313634 @default.
• W3216289989 hasConceptScore W3216289989C115961682 @default.
• W3216289989 hasConceptScore W3216289989C119857082 @default.
• W3216289989 hasConceptScore W3216289989C127716648 @default.
• W3216289989 hasConceptScore W3216289989C153180895 @default.
• W3216289989 hasConceptScore W3216289989C154945302 @default.
• W3216289989 hasConceptScore W3216289989C177264268 @default.
• W3216289989 hasConceptScore W3216289989C185592680 @default.
• W3216289989 hasConceptScore W3216289989C188082640 @default.
• W3216289989 hasConceptScore W3216289989C199360897 @default.
• W3216289989 hasConceptScore W3216289989C26517878 @default.
• W3216289989 hasConceptScore W3216289989C2776436953 @default.
• W3216289989 hasConceptScore W3216289989C38652104 @default.

• next