AI Art Neural Constellation: Revealing the Collective and Contrastive State of AI-Generated and Human Art

Faizan Farooq Khan, Diana Kim, Divyansh Jha, Youssef Mohamed, Hanna H Chang, Ahmed Elgammal, Luba Elliott, Mohamed Elhoseiny; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2024, pp. 7470-7478

Discovering the creative potentials of a random signal to various artistic expressions in aesthetic and conceptual richness is a ground for the recent success of generative machine learning as a way of art creation. To understand the new artistic medium better in this work we comprehensively analyze AI-generated art within the context of human art heritage using our dataset "ArtConstellation" comprising annotations for 6000 WikiArt and 3200 AI-generated artworks. After training various generative models we compare the produced art samples with WikiArt data using the last hidden layer of a deep-CNN trained for style classification. By interpreting neural representations with important artistic concepts like Wolfflin's principles we find that AI-generated artworks align with modern period art concepts (1800 - 2000). Out-Of-Distribution (OOD) and In-Distribution (ID) detection in CLIP space reveal that AI-generated art is ID to human art with landscapes and geometric abstract figures but OOD with deformed and twisted figures showcasing unique characteristics. A human survey on emotional experience indicates color composition and familiar subjects as key factors in likability and emotions. We introduce our methodologies and dataset "ArtNeuralConstellation" as a framework for contrasting human and AI-generated art. Code and data are available \href https://github.com/faixan-khan/ArtNeuralConstellation here .