Disclosed is a feedback adversarial learning framework, a recurrent framework for generative adversarial networks that can be widely adapted to not only stabilize training but also generate higher quality images. In some aspects, a discriminator's spatial outputs are distilled to improve generation quality. The disclosed embodiments model the discriminator into the generator, and the generator learns from its mistakes over time. In some aspects, a discriminator architecture encourages the model to be locally and globally consistent.