Affine Variational Autoencoders: An Efficient Approach for Improving Generalization and Robustness to Distribution Shift
arXiv:1905.05300
Abstract
In this study, we propose the Affine Variational Autoencoder (AVAE), a variant of Variational Autoencoder (VAE) designed to improve robustness by overcoming the inability of VAEs to generalize to distributional shifts in the form of affine perturbations. By optimizing an affine transform to maximize ELBO, the proposed AVAE transforms an input to the training distribution without the need to increase model complexity to model the full distribution of affine transforms. In addition, we introduce a training procedure to create an efficient model by learning a subset of the training distribution, and using the AVAE to improve generalization and robustness to distributional shift at test time. Experiments on affine perturbations demonstrate that the proposed AVAE significantly improves generalization and robustness to distributional shift in the form of affine perturbations without an increase in model complexity.
arXiv comment6 pages
References in corpus (6)
- Semi-Supervised Learning with Deep Generative Models
- Deep Convolutional Inverse Graphics Network
- Group Equivariant Convolutional Networks
- Towards the first adversarially robust neural network model on MNIST
- Deforming Autoencoders: Unsupervised Disentangling of Shape and Appearance
- A Survey of Inductive Biases for Factorial Representation-Learning