Ensembling Off-the-shelf Models for GAN Training
video (3m) | website | paper
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 performance when used in an ensemble of discriminators. We propose an effective selection mechanism, by probing the linear separability between real and fake samples in pretrained model embeddings, choosing the most accurate model, and progressively adding it to the discriminator ensemble. Our method can improve GAN training in both limited