Enhanced Scene Recognition via Multi-Model Transfer Learning with Limited Labeled Data

Scene recognition is a critical component of computer vision, powering applications from autonomous vehicles to surveillance systems. However, its development is often constrained by a heavy reliance on large, expensively annotated datasets. This research presents a novel, efficient approach that leverages multi-model transfer learning from pre-trained deep neural networks—specifically DenseNet201 and Visual Geometry Group (VGG)—to overcome this limitation. Our method significantly reduces dependency on vast labeled data while achieving high accuracy. Evaluated on the Aerial Image Dataset (AID) dataset, the model attained a validation accuracy of 93.6% with a loss of 0.35, demonstrating robust performance with minimal training data. These results underscore the viability of our approach for real-time, data-efficient scene recognition, offering a practical and cost-effective advancement for the field.