Object Detection in Historical Images: Transfer Learning and Pseudo Labelling

Abstract

The automatic analysis of images in the historical sciences often requires the identification of objects. Object identification is a well-researched problem for modern photographs; however, for historical material, annotations are often necessary. We present a solution for finding objects without manual work. The method consists of a style transfer of images from the COCO dataset into the domain using CycleGAN and training with items obtained through pseudo-labelling on the original and the additional transferred COCO images. Different strategies to assemble the dataset are compared. The best method obtains an F1 score of 0.58 for 15 object types without any labelling.