Versatile Auxiliary Regressor with Generative Adversarial network (VAR+GAN)
This work addresses a domain-specific need for controllable sample generation in regression problems, representing an incremental advancement over existing conditional GANs.
The paper tackles the problem of generating constrained samples for regression tasks by extending conditional generative adversarial networks (GANs) to continuous data aspects, presenting a new loss function and demonstrating its application in generating faces with specific landmarks.
Being able to generate constrained samples is one of the most appealing applications of the deep generators. Conditional generators are one of the successful implementations of such models wherein the created samples are constrained to a specific class. In this work, the application of these networks is extended to regression problems wherein the conditional generator is restrained to any continuous aspect of the data. A new loss function is presented for the regression network and also implementations for generating faces with any particular set of landmarks is provided.