Conditional Generative Modeling via Learning the Latent Space

Sameera Ramasinghe, Kanchana Nisal Ranasinghe, Salman Khan, Nick Barnes, Stephen Gould

Keywords: Multimodal Spaces, Conditional Generation, Generative Modeling

Abstract: Although deep learning has achieved appealing results on several machine learning tasks, most of the models are deterministic at inference, limiting their application to single-modal settings. We propose a novel general-purpose framework for conditional generation in multimodal spaces, that uses latent variables to model generalizable learning patterns while minimizing a family of regression cost functions. At inference, the latent variables are optimized to find solutions corresponding to multiple output modes. Compared to existing generative solutions, our approach demonstrates faster and more stable convergence, and can learn better representations for downstream tasks. Importantly, it provides a simple generic model that can perform better than highly engineered pipelines tailored using domain expertise on a variety of tasks, while generating diverse outputs. Code available at https://github.com/samgregoost/cGML.

One-sentence Summary: Conditional generation in continuous multimodal spaces by learning the behavior of latent variables.

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