EUVIMEDEUVIMED entdecken
Crossref

Bilinear Models of Parts and Appearances in Generative Adversarial Networks

James Oldfield, Christos Tzelepis, Yannis Panagakis, Mihalis A Nicolaou, Ioannis Patras

IEEE Transactions on Pattern Analysis and Machine Intelligence · 2024-12 · 46 (12) · 8568-8579

DOI: 10.1109/tpami.2024.3415506 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2024-12. Verfasst von James Oldfield und 4 weiteren Autor:innen. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 69 Literaturangaben. Gefördert von: EU H2020 AI4Media.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Recent advances in the understanding of Generative Adversarial Networks (GANs) have led to remarkable progress in visual editing and synthesis tasks, capitalizing on the rich semantics that are embedded in the latent spaces of pre-trained GANs. However, existing methods are often tailored to specific GAN architectures and are limited to either discovering global semantic directions that do not facilitate localized control, or require some form of supervision through manually provided regions or segmentation masks. In this light, we present an architecture-agnostic approach that jointly discovers factors representing spatial parts and their appearances in an entirely unsupervised fashion. These factors are obtained by applying a semi-nonnegative tensor factorization on the feature maps, which in turn enables context-aware local image editing with pixel-level control. In addition, we show that the discovered appearance factors correspond to saliency maps that localize concepts of interest, without using any labels. Experiments on a wide range of GAN architectures and datasets show that, in comparison to the state of the art, our method is far more efficient in terms of training time and, most importantly, provides much more accurate localized control.

Förderung

  • EU H2020 AI4Media

Zitieren

APA

Oldfield, J., Tzelepis, C., Panagakis, Y., Nicolaou, M. A., & Patras, I. (2024). Bilinear Models of Parts and Appearances in Generative Adversarial Networks. IEEE Transactions on Pattern Analysis and Machine Intelligence, 46(12), 8568-8579. https://doi.org/10.1109/tpami.2024.3415506

Vancouver

Oldfield J, Tzelepis C, Panagakis Y, Nicolaou MA, Patras I. Bilinear Models of Parts and Appearances in Generative Adversarial Networks. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2024;46(12):8568-8579. doi:10.1109/tpami.2024.3415506

BibTeX
@article{Oldfield2024,
  author = {Oldfield, James and Tzelepis, Christos and Panagakis, Yannis and Nicolaou, Mihalis A and Patras, Ioannis},
  title = {Bilinear Models of Parts and Appearances in Generative Adversarial Networks},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year = {2024},
  volume = {46},
  number = {12},
  pages = {8568--8579},
  doi = {10.1109/tpami.2024.3415506}
}
Kostenlos starten →