activity
20172026
most citedRandom Matrix Theory Proves that Deep Learning Representations of GAN-data Behave as Gaussian Mixtures

20 citations · 33 across the 19 of their papers we have counts for

collaborators
Showing 2017Show all

1 paper · 1 filter

cs.CV2017

Learning More Universal Representations for Transfer-Learning

Youssef Tamaazousti, Hervé Le Borgne, Céline Hudelot +2

A representation is supposed universal if it encodes any element of the visual world (e.g., objects, scenes) in any configuration (e.g., scale, context). While not expecting pure u…