Semi-Supervised Disentanglement of Class-Related and Class-Independent Factors in VAE

02/01/2021
by   Sina Hajimiri, et al.
12

In recent years, extending variational autoencoder's framework to learn disentangled representations has received much attention. We address this problem by proposing a framework capable of disentangling class-related and class-independent factors of variation in data. Our framework employs an attention mechanism in its latent space in order to improve the process of extracting class-related factors from data. We also deal with the multimodality of data distribution by utilizing mixture models as learnable prior distributions, as well as incorporating the Bhattacharyya coefficient in the objective function to prevent highly overlapping mixtures. Our model's encoder is further trained in a semi-supervised manner, with a small fraction of labeled data, to improve representations' interpretability. Experiments show that our framework disentangles class-related and class-independent factors of variation and learns interpretable features. Moreover, we demonstrate our model's performance with quantitative and qualitative results on various datasets.

READ FULL TEXT

page 7

page 8

page 14

page 16

research
10/19/2022

DOT-VAE: Disentangling One Factor at a Time

As we enter the era of machine learning characterized by an overabundanc...
research
05/24/2021

Semi-supervised learning of images with strong rotational disorder: assembling nanoparticle libraries

The proliferation of optical, electron, and scanning probe microscopies ...
research
06/02/2023

Learning Causally Disentangled Representations via the Principle of Independent Causal Mechanisms

Learning disentangled causal representations is a challenging problem th...
research
03/14/2020

Semi-supervised Disentanglement with Independent Vector Variational Autoencoders

We aim to separate the generative factors of data into two latent vector...
research
06/12/2020

LaRVAE: Label Replacement VAE for Semi-Supervised Disentanglement Learning

Learning interpretable and disentangled representations is a crucial yet...
research
04/06/2018

Hierarchical Disentangled Representations

Deep latent-variable models learn representations of high-dimensional da...
research
03/07/2019

Adversarial Mixup Resynthesizers

In this paper, we explore new approaches to combining information encode...

Please sign up or login with your details

Forgot password? Click here to reset