paper-with-me

Papers

Multi-level Latent Space Structuring for Generative Control

2022-02-11 · Oren Katzir, Vicky Perepelook, Dani Lischinski, Daniel Cohen-Or

Truncation is widely used in generative models for improving the quality of the generated samples, at the expense of reducing their diversity. We propose to leverage the StyleGAN generative architecture to devise a new truncation technique, based on a decomposition of the latent space into clusters, enabling customized truncation to be performed at multiple semantic levels. We do so by learning to re-generate W-space, the extended intermediate latent space of StyleGAN, using a learnable mixture of Gaussians, while simultaneously training a classifier to identify, for each latent vector, the cluster that it belongs to. The resulting truncation scheme is more faithful to the original untruncated samples and allows a better trade-off between quality and diversity. We compare our method to other truncation approaches for StyleGAN, both qualitatively and quantitatively.

📄 PDF Abstract BibTeX arXiv:2202.05910

Code (0)

등록된 구현이 없습니다.

Tasks

Diversity

Methods 이 논문이 사용한 방법론

Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…
Adaptive Instance Normalization 설명 없음
R1 Regularization R_INLINE_MATH_1 Regularization is a regularization technique and gradient penalty for training [generative adversarial…
Feedforward Network A Feedforward Network, or a Multilayer Perceptron (MLP), is a neural network with solely densely connected layers. This is the classic neural network architecture of the…
HuMan(Expedia)||How do I get a human at Expedia? How do I get a human at Expedia? How Do I Get a Human at Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Real-Time Help & Exclusive…

Similar Papers 제목 키워드 기반

Learning Latent Subspaces in Variational Autoencoders

2018-12-14 · NeurIPS 2018 12 · Jack Klys, Jake Snell, Richard Zemel

Variational autoencoders (VAEs) are widely used deep generative models capable of learning unsupervised latent representations of data. Such representations are often difficult to interpret or control. We consider the pr…

Attribute

Integrating Predictive and Generative Capabilities by Latent Space Design via the DKL-VAE Model

2025-03-04 · Boris N. Slautin, Utkarsh Pratiush, Doru C. Lupascu, Maxim A. Ziatdinov 외

We introduce a Deep Kernel Learning Variational Autoencoder (VAE-DKL) framework that integrates the generative power of a Variational Autoencoder (VAE) with the predictive nature of Deep Kernel Learning (DKL). The VAE le…

Property Prediction

Disentangling Geometric Deformation Spaces in Generative Latent Shape Models

2021-02-27 · Tristan Aumentado-Armstrong, Stavros Tsogkas, Sven Dickinson, Allan Jepson

A complete representation of 3D objects requires characterizing the space of deformations in an interpretable manner, from articulations of a single instance to changes in shape across categories. In this work, we improv…

DisentanglementPose TransferRepresentation LearningRetrieval

A Sparsity-promoting Dictionary Model for Variational Autoencoders

2022-03-29 · Mostafa Sadeghi, Paul Magron

Structuring the latent space in probabilistic deep generative models, e.g., variational autoencoders (VAEs), is important to yield more expressive models and interpretable representations, and to avoid overfitting. One w…

modelVariational Inference

CTTVAE: Latent Space Structuring for Conditional Tabular Data Generation on Imbalanced Datasets

2026-02-03 · Milosh Devic, Jordan Gierschendorf, David Garson arxiv

Generating synthetic tabular data under severe class imbalance is essential for domains where rare but high-impact events drive decision-making. However, most generative models either overlook minority groups or fail to …

Tabular Data GenerationFraud Detection