UGC: Unified GAN Compression for Efficient Image-to-Image Translation
This addresses efficiency issues in GAN-based image translation, but it appears incremental as it builds on existing model slimming and data-efficient techniques.
The paper tackles the high computational cost and data requirements of GANs for image-to-image translation by proposing Unified GAN Compression (UGC), a new paradigm that combines model-efficient and label-efficient learning, resulting in an architecture-flexible and performance-excellent model.
Recent years have witnessed the prevailing progress of Generative Adversarial Networks (GANs) in image-to-image translation. However, the success of these GAN models hinges on ponderous computational costs and labor-expensive training data. Current efficient GAN learning techniques often fall into two orthogonal aspects: i) model slimming via reduced calculation costs; ii)data/label-efficient learning with fewer training data/labels. To combine the best of both worlds, we propose a new learning paradigm, Unified GAN Compression (UGC), with a unified optimization objective to seamlessly prompt the synergy of model-efficient and label-efficient learning. UGC sets up semi-supervised-driven network architecture search and adaptive online semi-supervised distillation stages sequentially, which formulates a heterogeneous mutual learning scheme to obtain an architecture-flexible, label-efficient, and performance-excellent model.