Skip to yearly menu bar Skip to main content


Conditional Generative Modeling via Learning the Latent Space

Sameera Ramasinghe · Kanchana Ranasinghe · Salman Khan · Nick Barnes · Stephen Gould

Keywords: [ generative modeling ] [ conditional generation ] [ Multimodal Spaces ]


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

Chat is not available.