ALADIN: All Layer Adaptive Instance Normalization for Fine-grained Style Similarity

We present ALADIN (All Layer AdaIN); a novel architecture for searching images based on the similarity of their artistic style. Representation learning is critical to visual search, where distance in the learned search embedding reflects image similarity. Learning an embedding that discriminates fine-grained variations in style is hard, due to the difficulty of defining and labelling style. ALADIN takes a weakly supervised approach to learning a representation for fine-grained style similarity of digital artworks, leveraging BAM-FG, a novel large-scale dataset of user generated content groupings gathered from the web. ALADIN sets a new state of the art accuracy for style-based visual search over both coarse labelled style data (BAM) and BAM-FG; a new 2.62 million image dataset of 310,000 fine-grained style groupings also contributed by this work.

1. Introduction

Digital artwork spans a broad range of content depicted in diverse visual styles. Learning a representation suitable for searching artwork based on visual style is an open challenge, particularly when discriminating between subtle, fine-grained [39], [37], [25] variations in style. This is due to the difficulties of both (i) defining a suitable fine-grained ontology to label styles and (ii) the expert annotation task. Research to date has therefore focused upon coarse-grain discrimination of a limited number of styles [17], [6].