Art Style Classification with Self-Trained Ensemble of AutoEncoding Transformations

TL;DR

This paper introduces a self-supervised ensemble learning approach for art style classification, significantly improving accuracy on imbalanced datasets by leveraging limited annotations and diverse transformations.

Contribution

It proposes a novel semi-supervised ensemble autoencoding method that enhances artistic style recognition with minimal labeled data.

Findings

Almost 20% accuracy improvement over existing methods

Effective recognition of complex artistic styles with high intra-class variation

Robust performance on a highly imbalanced WikiArt dataset

Abstract

The artistic style of a painting is a rich descriptor that reveals both visual and deep intrinsic knowledge about how an artist uniquely portrays and expresses their creative vision. Accurate categorization of paintings across different artistic movements and styles is critical for large-scale indexing of art databases. However, the automatic extraction and recognition of these highly dense artistic features has received little to no attention in the field of computer vision research. In this paper, we investigate the use of deep self-supervised learning methods to solve the problem of recognizing complex artistic styles with high intra-class and low inter-class variation. Further, we outperform existing approaches by almost 20% on a highly class imbalanced WikiArt dataset with 27 art categories. To achieve this, we train the EnAET semi-supervised learning model (Wang et al., 2019) with limited annotated data samples and supplement it with self-supervised representations learned from an ensemble of spatial and non-spatial transformations.