Ensembling Off-the-shelf Models for GAN Training. (arXiv:2112.09130v3 [cs.CV] UPDATED)

Web: http://arxiv.org/abs/2112.09130

The advent of large-scale training has produced a cornucopia of powerful
visual recognition models. However, generative models, such as GANs, have
traditionally been trained from scratch in an unsupervised manner. Can the
collective "knowledge" from a large bank of pretrained vision models be
leveraged to improve GAN training? If so, with so many models to choose from,
which one(s) should be selected, and in what manner are they most effective? We
find that pretrained computer vision models can significantly improve …

arxiv cv gan models training