CrossMark is a multi-publisher initiative to provide a standard way for readers to locate the current version of a piece of content.
By applying the CrossMark logo, The International Journal of Fuzzy Logic and Intelligent Systems is committing to maintaining the content it publishes and to alerting readers to changes if and when they occur.
Clicking on the CrossMark logo will tell you the current status of a document and may also give you additional publication record information about the document (e.g. information on content type, peer review, publication history, availability of supplementary materials, and copyright and licencing).
Sangyun Lee and Sungjun Hong
International Journal of Fuzzy Logic and Intelligent Systems 2022;22: 339-349 https://doi.org/10.5391/IJFIS.2022.22.4.339Hamzeh Zureigat, Abd Ulazeez Alkouri, Areen Al-khateeb, Eman Abuteen, and Sana Abu-Ghurra
International Journal of Fuzzy Logic and Intelligent Systems 2023;23: 11-19 https://doi.org/10.5391/IJFIS.2023.23.1.11Hamzeh Zureigat, Abd Ulazeez Alkouri, Areen Al-khateeb, Eman Abuteen, and Sana Abu-Ghurra
International Journal of Fuzzy Logic and Intelligent Systems 2023;23: 11-19Sangyun Lee and Sungjun Hong
International Journal of Fuzzy Logic and Intelligent Systems 2022;22: 339-349Architecture of a conventional SCNN. The network is trained by contrastive loss in the training stage, whereas a distance function is used to compute the similarity metric in the testing stage.
|@|~(^,^)~|@|The proposed ESCNN architecture, which consists of three parts: (a) Siamese, (b) extension, and (c) decision parts. The feature dimensions are denoted as
Visualization of the features learned by the ESCNN: (a) positive and (b) negative samples.
|@|~(^,^)~|@|Training strategy of the proposed network. The network is optimized by a combination of two loss functions: 1) contrastive loss for the Siamese part and 2) cross-entropy loss for all parts, including the extension and decision parts.
|@|~(^,^)~|@|Examples from the iLIDS–VID dataset.
|@|~(^,^)~|@|Some example results: (a) positive and (b) negative samples.
|@|~(^,^)~|@|ROC curves for the methods under consideration.