A Self-supervised Sub-style Separation Framework for Artistic Painting Classification

Key Points

• The aim is to develop a framework that can classify artistic paintings by separating sub-styles effectively.
• Developed a self-supervised learning framework for art classification.
• Implemented techniques to identify and separate sub-styles of paintings.
• Utilized various datasets of artistic paintings for training and testing.
• Achieved improved accuracy in classifying paintings based on sub-styles.
• Demonstrated robustness across different artistic genres and styles.

Abstract