Disentangling Factors of Variation via Generative Entangling

Abstract

Here we propose a novel model family with the objective of learning to disentangle the factors of variation in data. Our approach is based on the spike-and-slab restricted Boltzmann machine which we generalize to include higher-order interactions among multiple latent variables. Seen from a generative perspective, the multiplicative interactions emulates the entangling of factors of variation. Inference in the model can be seen as disentangling these generative factors. Unlike previous attempts at disentangling latent factors, the proposed model is trained using no supervised information regarding the latent factors. We apply our model to the task of facial expression classification.

Cited by in corpus (12)

• Deep Convolutional Inverse Graphics Network
• A Survey of Inductive Biases for Factorial Representation-Learning
• Learning Disentangled Representations with Reference-Based Variational Autoencoders
• Understanding Instance-based Interpretability of Variational Auto-Encoders
• "Mental Rotation" by Optimizing Transforming Distance
• Unsupervised Landmark Learning from Unpaired Data
• Independence Promoted Graph Disentangled Networks
• Adversarial Disentanglement with Grouped Observations
• WeLa-VAE: Learning Alternative Disentangled Representations Using Weak Labels
• Unsupervised Disentanglement of Linear-Encoded Facial Semantics
• Set-Based Face Recognition Beyond Disentanglement: Burstiness Suppression With Variance Vocabulary
• Disentanglement Learning via Topology