Partial Hybrid Transfer Learning

While the typical approach to leverage transfer learning in image segmentation models involves replacing the entire encoder, this can restrict the customization and unique strengths of the main network. To address this limitation, we propose a hybrid transfer learning strategy that incorporates pre-trained convolutional layers from two distinct architectures (e.g., VGG16 and DenseNet201), allowing us to leverage the advantages of transfer learning while preserving the core features and characteristics of the base model's architecture.