Disentangling Factors of Variation via Generative Entangling
This addresses the challenge of unsupervised disentanglement for tasks like facial analysis, but appears incremental as it builds on existing models.
The authors tackled the problem of learning to disentangle factors of variation in data without supervised information, achieving application to facial expression classification.
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.