Weakly Supervised Object Detection in Artworks
This method benefits art historians by enabling weakly supervised object detection in large digital art databases, though it is incremental as it applies existing weakly supervised techniques to a new domain.
The paper tackles the problem of detecting objects in paintings using only image-level annotations, showing that dropping instance-level annotations yields only mild performance losses on several databases. It introduces a new database, IconArt, enabling detection of iconographic elements like Jesus Child or Saint Sebastian, which could not be learned from photographs.
We propose a method for the weakly supervised detection of objects in paintings. At training time, only image-level annotations are needed. This, combined with the efficiency of our multiple-instance learning method, enables one to learn new classes on-the-fly from globally annotated databases, avoiding the tedious task of manually marking objects. We show on several databases that dropping the instance-level annotations only yields mild performance losses. We also introduce a new database, IconArt, on which we perform detection experiments on classes that could not be learned on photographs, such as Jesus Child or Saint Sebastian. To the best of our knowledge, these are the first experiments dealing with the automatic (and in our case weakly supervised) detection of iconographic elements in paintings. We believe that such a method is of great benefit for helping art historians to explore large digital databases.