Pros and cons of GAN evaluation measures: New developments
A Borji - Computer Vision and Image Understanding, 2022 - Elsevier
This work is an update of my previous paper on the same topic published a few years ago
(Borji, 2019). With the dramatic progress in generative modeling, a suite of new quantitative …
(Borji, 2019). With the dramatic progress in generative modeling, a suite of new quantitative …
Generative adversarial networks for face generation: A survey
Recently, generative adversarial networks (GANs) have progressed enormously, which
makes them able to learn complex data distributions in particular faces. More and more …
makes them able to learn complex data distributions in particular faces. More and more …
Imagereward: Learning and evaluating human preferences for text-to-image generation
We present a comprehensive solution to learn and improve text-to-image models from
human preference feedback. To begin with, we build ImageReward---the first general …
human preference feedback. To begin with, we build ImageReward---the first general …
Make-a-scene: Scene-based text-to-image generation with human priors
Recent text-to-image generation methods provide a simple yet exciting conversion capability
between text and image domains. While these methods have incrementally improved the …
between text and image domains. While these methods have incrementally improved the …
Cold diffusion: Inverting arbitrary image transforms without noise
Standard diffusion models involve an image transform--adding Gaussian noise--and an
image restoration operator that inverts this degradation. We observe that the generative …
image restoration operator that inverts this degradation. We observe that the generative …
Diffusion models beat gans on image synthesis
P Dhariwal, A Nichol - Advances in neural information …, 2021 - proceedings.neurips.cc
We show that diffusion models can achieve image sample quality superior to the current
state-of-the-art generative models. We achieve this on unconditional image synthesis by …
state-of-the-art generative models. We achieve this on unconditional image synthesis by …
Cross-modal contrastive learning for text-to-image generation
The output of text-to-image synthesis systems should be coherent, clear, photo-realistic
scenes with high semantic fidelity to their conditioned text descriptions. Our Cross-Modal …
scenes with high semantic fidelity to their conditioned text descriptions. Our Cross-Modal …
Brain-inspired replay for continual learning with artificial neural networks
Artificial neural networks suffer from catastrophic forgetting. Unlike humans, when these
networks are trained on something new, they rapidly forget what was learned before. In the …
networks are trained on something new, they rapidly forget what was learned before. In the …
Improved techniques for training score-based generative models
Score-based generative models can produce high quality image samples comparable to
GANs, without requiring adversarial optimization. However, existing training procedures are …
GANs, without requiring adversarial optimization. However, existing training procedures are …
Generating diverse high-fidelity images with vq-vae-2
A Razavi, A Van den Oord… - Advances in neural …, 2019 - proceedings.neurips.cc
We explore the use of Vector Quantized Variational AutoEncoder (VQ-VAE) models for large
scale image generation. To this end, we scale and enhance the autoregressive priors used …
scale image generation. To this end, we scale and enhance the autoregressive priors used …