Questions tagged [disentangled-representation]

For questions related to Disentangled representation, an unsupervised learning technique

Disentangled representation is an unsupervised learning technique that breaks down, or disentangles, each feature into narrowly defined variables and encodes them as separate dimensions. The goal is to mimic the quick intuition process of a human, using both “high” and “low” dimension reasoning.

2 questions

votes

1 answer

Why different images of the same person, under some restrictions, are in a 50 dimension manifold?

In this lecture (starting from 1:31:00) the professor says that the set of all images of a person lives in a low dimensional surface (compared the the set of all possible images). And he says that the dimension of that surface is 50 and that they…

datasets representation-learning disentangled-representation

asked Mar 03 '21 at 10:19

Daviiid

vote

1 answer

What is the main contribution of the paper Disentangling by Factorising?

Considering the paper Disentangling by Factorising, in addition to introducing a new model for Disentangled Representation Learning, FactorVAE (see figure), what is the main theoretical contribution provided by the paper?

neural-networks deep-learning papers variational-autoencoder disentangled-representation

asked May 31 '20 at 23:01

Nicola Bernini