Variation Network: Learning High-level Attributes for Controlled Input Manipulation

Abstract

This paper presents the Variation Network (VarNet), a generative model providing means to manipulate the high-level attributes of a given input. The originality of our approach is that VarNet is not only capable of handling pre-defined attributes but can also learn the relevant attributes of the dataset by itself. These two settings can also be easily considered at the same time, which makes this model applicable to a wide variety of tasks. Further, VarNet has a sound information-theoretic interpretation which grants us with interpretable means to control how these high-level attributes are learned. We demonstrate experimentally that this model is capable of performing interesting input manipulation and that the learned attributes are relevant and meaningful.

15 pages, 7 figures

References in corpus (14)

• Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
• Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations
• Adversarially Learned Inference
• Style Tokens: Unsupervised Style Modeling, Control and Transfer in End-to-End Speech Synthesis
• Understanding disentangling in $\beta$-VAE
• Variational Lossy Autoencoder
• The Variational Fair Autoencoder
• RedNet: Residual Encoder-Decoder Network for indoor RGB-D Semantic Segmentation
• Invariant Representations without Adversarial Training
• Diagnosing and Enhancing VAE Models
• Lipschitz Generative Adversarial Nets
• On the Latent Space of Wasserstein Auto-Encoders
• Learning Discrete and Continuous Factors of Data via Alternating Disentanglement
• Deep Learning-Based Decoding of Constrained Sequence Codes

Cited by in corpus (1)

• Neural Drum Machine : An Interactive System for Real-time Synthesis of Drum Sounds