A Deep Learning Approach to Clustering Visual Arts

Abstract Clustering artworks is difficult for several reasons. On the one hand, recognizing meaningful patterns based on domain knowledge and visual perception extremely hard. other applying traditional clustering feature reduction techniques to highly dimensional pixel space can be ineffective. To address these issues, in this paper we propose : a DEep learning approach cLustering vIsUal artS. The method uses pre-trained convolutional network extract features then feeds into deep embedded model, where task of mapping input data latent jointly optimized with finding set cluster centroids space. Quantitative qualitative experimental results show effectiveness proposed method. useful tasks related art analysis, particular link retrieval historical discovery painting datasets.