Portrait of Ibtihel Amara is unavailable

Ibtihel Amara

PhD - McGill University
Supervisor
Research Topics
Computer Vision
Deep Learning
Natural Language Processing
Representation Learning

Publications

What Secrets Do Your Manifolds Hold? Understanding the Local Geometry of Generative Models
Ahmed Imtiaz Humayun
Cristina Nader Vasconcelos
Deepak Ramachandran
Candice Schumann
Junfeng He
Katherine A Heller
Mohammad Havaei
Deep Generative Models are frequently used to learn continuous representations of complex data distributions using a finite number of sample… (see more)s. For any generative model, including pre-trained foundation models with GAN, Transformer or Diffusion architectures, generation performance can vary significantly based on which part of the learned data manifold is sampled. In this paper we study the post-training local geometry of the learned manifold and its relationship to generation outcomes for models ranging from toy settings to the latent decoder of the near state-of-the-art Stable Diffusion 1.4 Text-to-Image model. Building on the theory of continuous piecewise-linear (CPWL) generators, we characterize the local geometry in terms of three geometric descriptors - scaling (
What Secrets Do Your Manifolds Hold? Understanding the Local Geometry of Generative Models
Ahmed Imtiaz Humayun
Candice Schumann
Cristina Nader Vasconcelos
Deepak Ramachandran
Junfeng He
Mohammad Havaei
Katherine Heller