FIANCEE: Faster Inference of Adversarial Networks via Conditional Early Exits
This addresses the problem of high computational load in real-time image synthesis applications, such as face generation, by allowing dynamic complexity reduction for less demanding inputs.
The paper tackles the computational inefficiency of generative DNNs by proposing a method to reduce computations while maintaining image quality, achieving up to a 50% reduction in computations for a quality threshold of LPIPS <=0.1.
Generative DNNs are a powerful tool for image synthesis, but they are limited by their computational load. On the other hand, given a trained model and a task, e.g. faces generation within a range of characteristics, the output image quality will be unevenly distributed among images with different characteristics. It follows, that we might restrain the models complexity on some instances, maintaining a high quality. We propose a method for diminishing computations by adding so-called early exit branches to the original architecture, and dynamically switching the computational path depending on how difficult it will be to render the output. We apply our method on two different SOTA models performing generative tasks: generation from a semantic map, and cross-reenactment of face expressions; showing it is able to output images with custom lower-quality thresholds. For a threshold of LPIPS <=0.1, we diminish their computations by up to a half. This is especially relevant for real-time applications such as synthesis of faces, when quality loss needs to be contained, but most of the inputs need fewer computations than the complex instances.