Weakly Supervised Object Detection in Artworks

TL;DR

This paper introduces a weakly supervised object detection method for artworks that requires only image-level labels, enabling efficient learning of new classes and aiding art analysis without detailed annotations.

Contribution

It presents a novel weakly supervised detection approach tailored for paintings, including a new database and experiments on iconographic elements.

Findings

Mild performance loss compared to fully supervised methods

Successful detection of iconographic elements in paintings

Introduction of the IconArt database

Abstract

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.