Explainable Ai for Style Interpretation in Contemporary Art Using Vision Transformers
Year: 2025
Type: article
Abstract: This study looks into how Explainable AI (XAI) can be used to figure out style in modern art by using Vision Transformers (ViTs). As the need for interpretability in AI-driven art research has grown, models have had to be made that not only work well but also give clear, understandable reasons for the choices they make. We use ViTs, a cutting-edge deep learning system that is known for being very good at classifying images, to look at and figure out what the style aspects of modern art mean. The study aims to find a balance between the need for high-performance AI models and the need for openness in the art world. It will do this by showing how certain aspects of artworks, like colour schemes, structural structures, and brushstroke patterns, affect the overall style. We present a mixed framework that blends the power of Vision Transformers with techniques for explaining things like Grad-CAM and focus maps. This framework helps you see and understand how the model's predictions work. The results show that the model can correctly spot important creative traits and give visual descriptions, which helps people understand different types of art. Additionally, the suggested method is tried on a wide range of modern artworks, showing that it can be used with various types of art. This work has effects beyond just analysing art; it gives managers, artists, and students a useful tool for working with AI systems in a more open way. It also adds to the field of explainable AI by using these methods to study art analysis, which is very biassed and hard to explain.
Authors: Nikil Tiwari, Naman Soni, Rahul Anantrao Padgilwar, Preeti Pandurang Kale, Mandeep Kaur, Vinay Nagalkar
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: diamond
OpenAlex ID: W7118008024