Related papers: Unsupervised evaluation of GAN sample quality: Int…

Generative adversarial networks (GANs) are a recent approach to train generative models of data, which have been shown to work particularly well on image data. In the current paper we introduce a new model for texture synthesis based on GAN…

Generative models make huge progress to the photorealistic image synthesis in recent years. To enable human to steer the image generation process and customize the output, many works explore the interpretable dimensions of the latent space…

Recent advances in diffusion models bring state-of-the-art performance on image generation tasks. However, empirical results from previous research in diffusion models imply an inverse correlation between density estimation and sample…

Adversarial loss in a conditional generative adversarial network (GAN) is not designed to directly optimize evaluation metrics of a target task, and thus, may not always guide the generator in a GAN to generate data with improved metric…

Deep generative models have recently achieved significant success in modeling graph data, including dynamic graphs, where topology and features evolve over time. However, unlike in vision and natural language domains, evaluating generative…

Data synthesis is a privacy enhancing technology aiming to produce realistic and timely data when real data is hard to obtain. Utility of synthetic data generators (SDGs) has been investigated through different utility metrics. These…

One of the growing trends in machine learning is the use of data generation techniques, since the performance of machine learning models is dependent on the quantity of the training dataset. However, in many real-world applications,…

Requirements of large amounts of data is a difficulty in training many GANs. Data efficient GANs involve fitting a generators continuous target distribution with a limited discrete set of data samples, which is a difficult task. Single…

Unconditional video generation is a challenging task that involves synthesizing high-quality videos that are both coherent and of extended duration. To address this challenge, researchers have used pretrained StyleGAN image generators for…

In the last few years, we have witnessed the rise of a series of deep learning methods to generate synthetic images that look extremely realistic. These techniques prove useful in the movie industry and for artistic purposes. However, they…

We present a novel metric for generative modeling evaluation, focusing primarily on generative networks. The method uses dendrograms to represent real and fake data, allowing for the divergence between training and generated samples to be…

This paper observes that there is an issue of high frequencies missing in the discriminator of standard GAN, and we reveal it stems from downsampling layers employed in the network architecture. This issue makes the generator lack the…

We propose SADGE, a quantitative similarity metric that predicts the performance of synthetic image datasets for common computer vision tasks without downstream model training. Estimating whether a synthetic dataset will lead to a model…

Text-image generation has advanced rapidly, but assessing whether outputs truly capture the objects, attributes, and relations described in prompts remains a central challenge. Evaluation in this space relies heavily on automated metrics,…

Text-to-image (T2I) generation aims at producing realistic images corresponding to text descriptions. Generative Adversarial Network (GAN) has proven to be successful in this task. Typical T2I GANs are 2 phase methods that first pretrain an…

Noise synthesis is a challenging low-level vision task aiming to generate realistic noise given a clean image along with the camera settings. To this end, we propose an effective generative model which utilizes clean features as guidance…

The rapid advancement of generative AI has revolutionized image creation, enabling high-quality synthesis from text prompts while raising critical challenges for media authenticity. We present Ai-GenBench, a novel benchmark designed to…

The generation of high-quality synthetic data presents significant challenges in machine learning research, particularly regarding statistical fidelity and uncertainty quantification. Existing generative models produce compelling synthetic…

Recent advancements in Generative Adversarial Networks (GANs) enable the generation of highly realistic images, raising concerns about their misuse for malicious purposes. Detecting these GAN-generated images (GAN-images) becomes…

We propose two new techniques for training Generative Adversarial Networks (GANs). Our objectives are to alleviate mode collapse in GAN and improve the quality of the generated samples. First, we propose neighbor embedding, a manifold…