Reflections on Disentanglement and the Latent Space

TL;DR

This paper explores the latent space of image generative models as both a cultural archive and a space of potentiality, emphasizing disentanglement as a key to understanding and exploiting its organization.

Contribution

It offers a double perspective on latent space, linking disentanglement to cultural interpretation and potentiality, and compares traditional and recent generative architectures.

Findings

Disentanglement clarifies the dual nature of latent space.

Latent space encodes rich cultural representations.

Recent architectures differ significantly from traditional models.

Abstract

The latent space of image generative models is a multi-dimensional space of compressed hidden visual knowledge. Its entity captivates computer scientists, digital artists, and media scholars alike. Latent space has become an aesthetic category in AI art, inspiring artistic techniques such as the latent space walk, exemplified by the works of Mario Klingemann and others. It is also viewed as cultural snapshots, encoding rich representations of our visual world. This paper proposes a double view of the latent space, as a multi-dimensional archive of culture and as a multi-dimensional space of potentiality. The paper discusses disentanglement as a method to elucidate the double nature of the space and as an interpretative direction to exploit its organization in human terms. The paper compares the role of disentanglement as potentiality to that of conditioning, as imagination, and confronts this interpretation with the philosophy of Deleuzian potentiality and Hume's imagination. Lastly, this paper notes the difference between traditional generative models and recent architectures.