Content-Based Image Retrieval from Weakly-Supervised Disentangled Representations

In content-based image retrieval (CBIR), a database of images is ordered basedon the similarity to a query image. Similarity criterion is usually determinedwith respect to a shared category e.g. whether the database images contain anobject of the same type as depicted in the query. Depending on the situation,multiple similarity criteria can be relevant such as the type of object, its color,or the depicted background. Ideally, a dataset labeled with all possible criteriainformation is available for training a model for computing the similarity. Typically,this is not the case. In this paper, we explore the use of disentangled representationsfor CBIR with respect to multiple criteria. To alleviate the need for labels, themodels used to create the representations are learned via weak supervision by usingdata organized into groups with shared information. We show that such modelscan attain better retrieval performances compared to unsupervised baselines.