Diverse Conditional Image Generation by Stochastic Regression with Latent Drop-Out Codes
This work addresses conditional image generation for computer vision applications, offering an incremental improvement by combining existing approaches.
The paper tackles the problem of generating diverse conditional images by addressing stability issues in GANs and mode-mixing in CVAEs, proposing a stochastic regression method with latent drop-out codes that improves accuracy and diversity over state-of-the-art methods.
Recent advances in Deep Learning and probabilistic modeling have led to strong improvements in generative models for images. On the one hand, Generative Adversarial Networks (GANs) have contributed a highly effective adversarial learning procedure, but still suffer from stability issues. On the other hand, Conditional Variational Auto-Encoders (CVAE) models provide a sound way of conditional modeling but suffer from mode-mixing issues. Therefore, recent work has turned back to simple and stable regression models that are effective at generation but give up on the sampling mechanism and the latent code representation. We propose a novel and efficient stochastic regression approach with latent drop-out codes that combines the merits of both lines of research. In addition, a new training objective increases coverage of the training distribution leading to improvements over the state of the art in terms of accuracy as well as diversity.