A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
Multi-StyleGAN simulates live cell microscopy imagery.
StylEx trains a GAN to explain classifier decisions in StyleSpace.
The style-based GAN architecture (StyleGAN) yields state-of-the-art results in data-driven unconditional generative image modeling. We expose and analyze several of its characteristic artifacts, and propose changes in both model architecture and training methods to address them. In particular, we redesign the generator…
The ability to automatically estimate the quality and coverage of the samples produced by a generative model is a vital requirement for driving algorithm research. We present an evaluation metric that can separately and reliably measure both of these aspects in image generation tasks by forming explicit, non-parametric…
New method compresses facial videos using GANs and latent space optimization.
Recent research has made the surprising finding that state-of-the-art deep learning models sometimes fail to generalize to small variations of the input. Adversarial training has been shown to be an effective approach to overcome this problem. However, its application has been limited to enforcing invariance to analyti…
Optimizes master faces for 2D and 3D face verification using evolutionary algorithms and neural networks.
A new method combines energy-based models and entropy-regularized optimal transport.
Simple fine-tuning of GANs with frozen discriminator outperforms existing methods.
Adversarial attacks have long been developed for revealing the vulnerability of Deep Neural Networks (DNNs) by adding imperceptible perturbations to the input. Most methods generate perturbations like normal noise, which is not interpretable and without semantic meaning. In this paper, we propose High-Resolution Featur…
Training generative adversarial networks (GANs) on high quality (HQ) images involves important computing resources. This requirement represents a bottleneck for the development of applications of GANs. We propose a transfer learning technique for GANs that significantly reduces training time. Our approach consists of f…
Feature Quantization improves GAN training stability.
Proposes -Nets, polynomial neural networks, for improved representation power.
InvGAN combines generative and inference models for photo-realistic image manipulation.
Despite remarkable recent progress on both unconditional and conditional image synthesis, it remains a long-standing problem to learn generative models that are capable of synthesizing realistic and sharp images from reconfigurable spatial layout (i.e., bounding boxes + class labels in an image lattice) and style (i.e.…
New GAN loss functions improve image generation quality and stability.