Self-Supervised Variational Auto-Encoders

Ioannis Gatopoulos, Jakub Mikolaj Tomczak

Keywords: generative modeling, deep learning, deep autoencoders

Abstract: Density estimation, compression, and data generation are crucial tasks in artificial intelligence. Variational Auto-Encoders (VAEs) constitute a single framework to achieve these goals. Here, we present a novel class of generative models, called self-supervised Variational Auto-Encoder (selfVAE), that utilizes deterministic and discrete transformations of data. This class of models allows performing both conditional and unconditional sampling while simplifying the objective function. First, we use a single self-supervised transformation as a latent variable, where a transformation is either downscaling or edge detection. Next, we consider a hierarchical architecture, i.e., multiple transformations, and we show its benefits compared to the VAE. The flexibility of selfVAE in data reconstruction finds a particularly interesting use case in data compression tasks, where we can trade-off memory for better data quality, and vice-versa. We present the performance of our approach on three benchmark image data (Cifar10, Imagenette64, and CelebA).

One-sentence Summary: We present a novel class of generative models, called self-supervised Variational Auto-Encoder, where we improve VAEs by applying deterministic and discrete transformations of data.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Community Implementations: [ 1 code implementation](https://www.catalyzex.com/paper/arxiv:2010.02014/code)

Reviewed Version (pdf): https://openreview.net/references/pdf?id=dckNRnOqIj