Reflections on Disentanglement and the Latent Space
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.
Code (0)
등록된 구현이 없습니다.
Tasks
DisentanglementPhilosophySimilar Papers 제목 키워드 기반
PRISM: Latent Composition Consistency for Single-Image Reflection Removal
Single-image reflection removal (SIRR) seeks to recover the transmission layer from a mixture corrupted by reflections -- a severely ill-posed problem. Existing methods operate in pixel space, where the nonlinear sRGB fo…
Contrastive LearningReflection RemovalA Unified Latent Space Disentanglement VAE Framework with Robust Disentanglement Effectiveness Evaluation
Evaluating and interpreting latent representations, such as variational autoencoders (VAEs), remains a significant challenge for diverse data types, especially when ground-truth generative factors are unknown. To address…
Variantional autoencoder with decremental information bottleneck for disentanglement
One major challenge of disentanglement learning with variational autoencoders is the trade-off between disentanglement and reconstruction fidelity. Previous studies, which increase the information bottleneck during train…
DisentanglementRepresentation LearningSemantic Unfolding of StyleGAN Latent Space
Generative adversarial networks (GANs) have proven to be surprisingly efficient for image editing by inverting and manipulating the latent code corresponding to an input real image. This editing property emerges from the…
AttributeDisentanglementFacial EditingUnsupervised Disentanglement with Tensor Product Representations on the Torus
The current methods for learning representations with auto-encoders almost exclusively employ vectors as the latent representations. In this work, we propose to employ a tensor product structure for this purpose. This wa…
DisentanglementInformativeness