# Unsupervised Learning of Artistic Styles with Archetypal Style Analysis

arXiv: https://arxiv.org/abs/1805.11155 · HTML: https://mlsanity.com/paper/1805.11155/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 May 2018.

## Built on by (most cited first, 10 of 10)

- [Measuring Style Similarity in Diffusion Models](https://mlsanity.com/paper/2404.01292/) (2024)
- [Archetypal SAE: Adaptive and Stable Dictionary Learning for Concept Extraction in Large Vision Models](https://mlsanity.com/paper/2502.12892/) (2025)
- [Explain Me the Painting: Multi-Topic Knowledgeable Art Description Generation](https://mlsanity.com/paper/2109.05743/) (2021)
- [A Survey on Archetypal Analysis](https://mlsanity.com/paper/2504.12392/) (2025)
- [KALE: An Artwork Image Captioning System Augmented with Heterogeneous Graph](https://mlsanity.com/paper/2409.10921/) (2024)
- [StyleProtect: Safeguarding Artistic Identity in Fine-tuned Diffusion Models](https://mlsanity.com/paper/2509.13711/) (2025)
- [A Geometric Unification of Concept Learning with Concept Cones](https://mlsanity.com/paper/2512.07355/) (2025)
- [Emotion Transfer Using Vector-Valued Infinite Task Learning](https://mlsanity.com/paper/2102.05075/) (2021)
- [The Deleuzian Representation Hypothesis](https://mlsanity.com/paper/2512.19734/) (2025)
- [Efficient and Generalizable Archetypal Analysis for Discrete Data](https://mlsanity.com/paper/2610.12035/) (2026)

## Abstract (arXiv)

In this paper, we introduce an unsupervised learning approach to automatically discover, summarize, and manipulate artistic styles from large collections of paintings. Our method is based on archetypal analysis, which is an unsupervised learning technique akin to sparse coding with a geometric interpretation. When applied to deep image representations from a collection of artworks, it learns a dictionary of archetypal styles, which can be easily visualized. After training the model, the style of a new image, which is characterized by local statistics of deep visual features, is approximated by a sparse convex combination of archetypes. This enables us to interpret which archetypal styles are present in the input image, and in which proportion. Finally, our approach allows us to manipulate the coefficients of the latent archetypal decomposition, and achieve various special effects such as style enhancement, transfer, and interpolation between multiple archetypes.