1 citations · 1 across the 3 of their papers we have counts for
3 papers
Heavy-Tailed Class-Conditional Priors for Long-Tailed Generative Modeling
Aymene Mohammed Bouayed, Samuel Deslauriers-Gauthier, Adrian Iaccovelli +1
Variational Autoencoders (VAEs) with global priors trained under an imbalanced empirical class distribution can lead to underrepresentation of tail classes in the latent space. Whi…
CNN Explainability with Multivector Tucker Saliency Maps for Self-Supervised Models
Aymene Mohammed Bouayed, Samuel Deslauriers-Gauthier, Adrian Iaccovelli +1
Interpreting the decisions of Convolutional Neural Networks (CNNs) is essential for understanding their behavior, yet explainability remains a significant challenge, particularly f…
Sampling From Autoencoders' Latent Space via Quantization And Probability Mass Function Concepts
Aymene Mohammed Bouayed, Adrian Iaccovelli, David Naccache
In this study, we focus on sampling from the latent space of generative models built upon autoencoders so as the reconstructed samples are lifelike images. To do to, we introduce a…