A Two-Step Disentanglement Method

2017/09/01 by Naama Hadad, Hadad, Naama, Lior Wolf +3 · 2 citations
Computer Science · #Currency Recognition and Detection #Digital Media Forensic Detection #FOS: Computer and information sciences #Generative Adversarial Networks and Image Synthesis #Machine Learning (cs.LG) #Machine Learning (stat.ML)

paper · pdf · doi:10.48550/arxiv.1709.00199

openalex publication_date 2017/09/01 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/03

Abstract

We address the problem of disentanglement of factors that generate a given data into those that are correlated with the labeling and those that are not. Our solution is simpler than previous solutions and employs adversarial training. First, the part of the data that is correlated with the labels is extracted by training a classifier. Then, the other part is extracted such that it enables the reconstruction of the original data but does not contain label information. The utility of the new method is demonstrated on visual datasets as well as on financial data. Our code is available at https://github.com/naamahadad/A-Two-Step-Disentanglement-Method

Citations

• The Pricing of Options and Corporate Liabilities
• Semi-Supervised Learning with Deep Generative Models

Cited by

• Adversarial Disentanglement by Backpropagation with Physics-Informed Variational Autoencoder
• Self-supervised Latent Space Optimization with Nebula Variational Coding

Related

• DisUnknown: Distilling Unknown Factors for Disentanglement Learning
• Disentanglement of Correlated Factors via Hausdorff Factorized Support
• Disentangling by Factorising
• Disentanglement and Generalization Under Correlation Shifts
• NashAE: Disentangling Representations through Adversarial Covariance Minimization