Discovering Hidden Factors of Variation in Deep Networks
arXiv:1412.6583
Abstract
Deep learning has enjoyed a great deal of success because of its ability to learn useful features for tasks such as classification. But there has been less exploration in learning the factors of variation apart from the classification signal. By augmenting autoencoders with simple regularization terms during training, we demonstrate that standard deep architectures can discover and explicitly represent factors of variation beyond those relevant for categorization. We introduce a cross-covariance penalty (XCov) as a method to disentangle factors like handwriting style for digits and subject identity in faces. We demonstrate this on the MNIST handwritten digit database, the Toronto Faces Database (TFD) and the Multi-PIE dataset by generating manipulated instances of the data. Furthermore, we demonstrate these deep networks can extrapolate `hidden' variation in the supervised signal.
Presented at International Conference on Learning Representations 2015 Workshop
References in corpus (3)
Cited by in corpus (12)
- Disentangling factors of variation in deep representations using adversarial training
- GeneGAN: Learning Object Transfiguration and Attribute Subspace from Unpaired Data
- A Survey of Inductive Biases for Factorial Representation-Learning
- Challenges in Disentangling Independent Factors of Variation
- Effect of The Latent Structure on Clustering with GANs
- Attribute Guided Unpaired Image-to-Image Translation with Semi-supervised Learning
- All-In-One: Facial Expression Transfer, Editing and Recognition Using A Single Network
- Conditional Adversarial Generative Flow for Controllable Image Synthesis
- Improving Content-Invariance in Gated Autoencoders for 2D and 3D Object Rotation
- Efficient decorrelation of features using Gramian in Reinforcement Learning
- Quantifying the Effects of Enforcing Disentanglement on Variational Autoencoders
- Attribute-controlled face photo synthesis from simple line drawing