Deep generative modelling: A comparative review of vaes, gans, normalizing flows, energy-based and autoregressive models
Deep generative models are a class of techniques that train deep neural networks to model
the distribution of training samples. Research has fragmented into various interconnected …
the distribution of training samples. Research has fragmented into various interconnected …
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 …
Diffusion art or digital forgery? investigating data replication in diffusion models
Cutting-edge diffusion models produce images with high quality and customizability,
enabling them to be used for commercial art and graphic design purposes. But do diffusion …
enabling them to be used for commercial art and graphic design purposes. But do diffusion …
Deep learning for molecular design—a review of the state of the art
In the space of only a few years, deep generative modeling has revolutionized how we think
of artificial creativity, yielding autonomous systems which produce original images, music …
of artificial creativity, yielding autonomous systems which produce original images, music …
Regularizing generative adversarial networks under limited data
Recent years have witnessed the rapid progress of generative adversarial networks (GANs).
However, the success of the GAN models hinges on a large amount of training data. This …
However, the success of the GAN models hinges on a large amount of training data. This …
Can push-forward generative models fit multimodal distributions?
Many generative models synthesize data by transforming a standard Gaussian random
variable using a deterministic neural network. Among these models are the Variational …
variable using a deterministic neural network. Among these models are the Variational …
Membership inference attacks against synthetic data through overfitting detection
Data is the foundation of most science. Unfortunately, sharing data can be obstructed by the
risk of violating data privacy, impeding research in fields like healthcare. Synthetic data is a …
risk of violating data privacy, impeding research in fields like healthcare. Synthetic data is a …
KD-DLGAN: Data limited image generation via knowledge distillation
Abstract Generative Adversarial Networks (GANs) rely heavily on large-scale training data
for training high-quality image generation models. With limited training data, the GAN …
for training high-quality image generation models. With limited training data, the GAN …
Bias correction of learned generative models using likelihood-free importance weighting
A learned generative model often produces biased statistics relative to the underlying data
distribution. A standard technique to correct this bias is importance sampling, where …
distribution. A standard technique to correct this bias is importance sampling, where …
Compositional zero-shot learning via fine-grained dense feature composition
D Huynh, E Elhamifar - Advances in Neural Information …, 2020 - proceedings.neurips.cc
We develop a novel generative model for zero-shot learning to recognize fine-grained
unseen classes without training samples. Our observation is that generating holistic features …
unseen classes without training samples. Our observation is that generating holistic features …