AIConfPaper
← Search

Christos Tzelepis

6 accepted papers

2024

Multilinear Mixture of Experts: Scalable Expert Specialization through Factorization

James Oldfield, Markos Georgopoulos, Grigorios Chrysos, Christos Tzelepis, Yannis Panagakis, Mihalis Nicolaou +2
NeurIPS 2024poster

The Mixture of Experts (MoE) paradigm provides a powerful way to decompose dense layers into smaller, modular computations often more amenable to human interpretation, debugging, and editability. However, a major challenge lies in the computational cost of scaling the number of experts high enough t…

Cited by 9Source ↗PDF ↗code ↗Scholar ↗
2023

Attribute-Preserving Face Dataset Anonymization via Latent Code Optimization

Simone Barattin, Christos Tzelepis, Ioannis Patras, Nicu Sebe
CVPR 2023highlight

This work addresses the problem of anonymizing the identity of faces in a dataset of images, such that the privacy of those depicted is not violated, while at the same time the dataset is useful for downstream task such as for training machine learning models. To the best of our knowledge, we are th…

Cited by 55Source ↗PDF ↗code ↗Scholar ↗
2023

HyperReenact: One-Shot Reenactment via Jointly Learning to Refine and Retarget Faces

Stella Bounareli, Christos Tzelepis, Vasileios Argyriou, Ioannis Patras, Georgios Tzimiropoulos
ICCV 2023poster

In this paper, we present our method for neural face reenactment, called HyperReenact, that aims to generate realistic talking head images of a source identity, driven by a target facial pose. Existing state-of-the-art face reenactment methods train controllable generative models that learn to synth…

Cited by 43PDF ↗code ↗Scholar ↗
2023

PandA: Unsupervised Learning of Parts and Appearances in the Feature Maps of GANs

James Oldfield, Christos Tzelepis, Yannis Panagakis, Mihalis Nicolaou, Ioannis Patras
ICLR 2023poster

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 specifi…

Cited by 22Source ↗PDF ↗code ↗Scholar ↗
2023

Parts of Speech–Grounded Subspaces in Vision-Language Models

James Oldfield, Christos Tzelepis, Yannis Panagakis, Mihalis Nicolaou, Ioannis Patras
NeurIPS 2023poster

Latent image representations arising from vision-language models have proved immensely useful for a variety of downstream tasks. However, their utility is limited by their entanglement with respect to different visual attributes. For instance, recent work has shown that CLIP image representations ar…

Cited by 8Source ↗PDF ↗code ↗Scholar ↗
2021

WarpedGANSpace: Finding Non-Linear RBF Paths in GAN Latent Space

Christos Tzelepis, Georgios Tzimiropoulos, Ioannis Patras
ICCV 2021poster

This work addresses the problem of discovering, in an unsupervised manner, interpretable paths in the latent space of pretrained GANs, so as to provide an intuitive and easy way of controlling the underlying generative factors. In doing so, it addresses some of the limitations of the state-of-the-ar…

Cited by 66PDF ↗code ↗Scholar ↗