Demystifying Inter-Class Disentanglement

Abstract

Learning to disentangle the hidden factors of variations within a set of observations is a key task for artificial intelligence. We present a unified formulation for class and content disentanglement and use it to illustrate the limitations of current methods. We therefore introduce LORD, a novel method based on Latent Optimization for Representation Disentanglement. We find that latent optimization, along with an asymmetric noise regularization, is superior to amortized inference for achieving disentangled representations. In extensive experiments, our method is shown to achieve better disentanglement performance than both adversarial and non-adversarial methods that use the same level of supervision. We further introduce a clustering-based approach for extending our method for settings that exhibit in-class variation with promising results on the task of domain translation.

arXiv commentICLR 2020. Project page: http://www.vision.huji.ac.il/lord

References in corpus (10)

• Auto-Encoding Variational Bayes
• Large Scale GAN Training for High Fidelity Natural Image Synthesis
• The Unreasonable Effectiveness of Deep Features as a Perceptual Metric
• Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations
• A Learned Representation For Artistic Style
• Disentangling by Factorising
• Multi-Level Variational Autoencoder: Learning Disentangled Representations from Grouped Observations
• Learning Deep Disentangled Embeddings with the F-Statistic Loss
• Generating Diverse High-Fidelity Images with VQ-VAE-2
• Demystifying Neural Style Transfer

Cited by in corpus (5)

• Weakly Supervised Disentanglement with Guarantees
• Structural-analogy from a Single Image Pair
• Weakly-Supervised Reinforcement Learning for Controllable Behavior
• Controllable Gradient Item Retrieval
• Training End-to-end Single Image Generators without GANs