A Comparative Transfer-Learning Study of CNN Backbones for Partial Face Recognition on the SoF Dataset
Three pretrained convolutional backbones, ResNet-50, VGG-16, and FaceNet, fine-tuned for PFR by transfer learning under identical preprocessing, splitting, and optimization protocols on the Specs-on-Faces (SoF) dataset are compared.
A. Kubba, Ali Alsalama, A. Abd Alla et al.
· 0 citations