Unconditional Image Generation
12 papers with code • 3 benchmarks • 1 datasets
Combined with multiple architectural improvements, we achieve record-breaking performance for unconditional image generation on CIFAR-10 with an Inception score of 9. 89 and FID of 2. 20, a competitive likelihood of 2. 99 bits/dim, and demonstrate high fidelity generation of 1024 x 1024 images for the first time from a score-based generative model.
Ranked #3 on Image Generation on CIFAR-10
In this paper, we propose an AdversarialNAS method specially tailored for Generative Adversarial Networks (GANs) to search for a superior generative model on the task of unconditional image generation.
Such a model disentangles latent factors according to the semantic of feature channels by channel-/group- wise fusion of latent codes and feature channels.
We extensively evaluate the representation learning and generation capabilities of these BigBiGAN models, demonstrating that these generation-based models achieve the state of the art in unsupervised representation learning on ImageNet, as well as in unconditional image generation.
Ranked #25 on Semi-Supervised Image Classification on ImageNet - 1% labeled data (Top 5 Accuracy metric)
While Generative Adversarial Networks (GANs) show increasing performance and the level of realism is becoming indistinguishable from natural images, this also comes with high demands on data and computation.
GLANN combines the strengths of IMLE and GLO in a way that overcomes the main drawbacks of each method.