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.