ProtoVAE: Prototypical Networks for Unsupervised Disentanglement

by   Vaishnavi Patil, et al.

Generative modeling and self-supervised learning have in recent years made great strides towards learning from data in a completely unsupervised way. There is still however an open area of investigation into guiding a neural network to encode the data into representations that are interpretable or explainable. The problem of unsupervised disentanglement is of particular importance as it proposes to discover the different latent factors of variation or semantic concepts from the data alone, without labeled examples, and encode them into structurally disjoint latent representations. Without additional constraints or inductive biases placed in the network, a generative model may learn the data distribution and encode the factors, but not necessarily in a disentangled way. Here, we introduce a novel deep generative VAE-based model, ProtoVAE, that leverages a deep metric learning Prototypical network trained using self-supervision to impose these constraints. The prototypical network constrains the mapping of the representation space to data space to ensure that controlled changes in the representation space are mapped to changes in the factors of variations in the data space. Our model is completely unsupervised and requires no a priori knowledge of the dataset, including the number of factors. We evaluate our proposed model on the benchmark dSprites, 3DShapes, and MPI3D disentanglement datasets, showing state of the art results against previous methods via qualitative traversals in the latent space, as well as quantitative disentanglement metrics. We further qualitatively demonstrate the effectiveness of our model on the real-world CelebA dataset.


page 6

page 7

page 8


DOT-VAE: Disentangling One Factor at a Time

As we enter the era of machine learning characterized by an overabundanc...

Leveraging Relational Information for Learning Weakly Disentangled Representations

Disentanglement is a difficult property to enforce in neural representat...

TC-VAE: Uncovering Out-of-Distribution Data Generative Factors

Uncovering data generative factors is the ultimate goal of disentangleme...

Is Disentanglement enough? On Latent Representations for Controllable Music Generation

Improving controllability or the ability to manipulate one or more attri...

A Survey of Inductive Biases for Factorial Representation-Learning

With the resurgence of interest in neural networks, representation learn...

Unsupervised Semantic Attribute Discovery and Control in Generative Models

This work focuses on the ability to control via latent space factors sem...

Unsupervised learning of disentangled representations in deep restricted kernel machines with orthogonality constraints

We introduce Constr-DRKM, a deep kernel method for the unsupervised lear...

Please sign up or login with your details

Forgot password? Click here to reset