2 papers
cs.CV2021
Visual Probing: Cognitive Framework for Explaining Self-Supervised Image Representations
Witold Oleszkiewicz, Dominika Basaj, Igor Sieradzki +5
Recently introduced self-supervised methods for image representation learning provide on par or superior results to their fully supervised competitors, yet the corresponding effort…
cs.LG2018
On Latent Distributions Without Finite Mean in Generative Models
Damian Leśniak, Igor Sieradzki, Igor Podolak
We investigate the properties of multidimensional probability distributions in the context of latent space prior distributions of implicit generative models. Our work revolves arou…