Scene Detection in De Boer Historical Photo Collection
Melvin Wevers · 2021
This paper demonstrates how transfer learning can be used to improve scene detection applied to a historical press photo collection. After applying transfer learning to a pre-trained Places-365 ResNet-50 model, we achieve a Top-1 accuracy of .68 and a Top-5 accuracy of .89 on our data set, which consists of 132 categories. In addition to describing our annotation and training strategy, we also reflect on the use of transfer learning and the evaluation of computer vision models for heritage institutes.