paper-with-me

Papers

Sampling Generative Networks

2016-09-14 · Tom White

We introduce several techniques for sampling and visualizing the latent spaces of generative models. Replacing linear interpolation with spherical linear interpolation prevents diverging from a model's prior distribution and produces sharper samples. J-Diagrams and MINE grids are introduced as visualizations of manifolds created by analogies and nearest neighbors. We demonstrate two new techniques for deriving attribute vectors: bias-corrected vectors with data replication and synthetic vectors with data augmentation. Binary classification using attribute vectors is presented as a technique supporting quantitative analysis of the latent space. Most techniques are intended to be independent of model type and examples are shown on both Variational Autoencoders and Generative Adversarial Networks.

📄 PDF Abstract BibTeX arXiv:1609.04468

Code (13)

dribnet/plat 공식 구현
AntreasAntoniou/DAGAN tf
BilcSergiu/DAGAN tf
MindSpore-scientific-2/code-3/tree/main/stable-sam mindspore
amurthy1/dagan tf
gitaar9/MLDAGAN tf
hy-zpg/DAGAN tf
jaingaurav3/GAN-Hacks
kingcheng2000/GAN
linxi159/GAN-training-tricks
linxi159/Tips-and-tricks-to-train-GANs
michael13162/DoodleGAN
ptrblck/prog_gans_pytorch_inference pytorch

Tasks

AttributeBinary ClassificationData AugmentationGeneral ClassificationSuper-Resolution

Similar Papers 제목 키워드 기반

Approximating Constraint Manifolds Using Generative Models for Sampling-Based Constrained Motion Planning

2022-04-14 · Cihan Acar, Keng Peng Tee

Sampling-based motion planning under task constraints is challenging because the null-measure constraint manifold in the configuration space makes rejection sampling extremely inefficient, if not impossible. This paper p…

Motion Planning

SOS: Score-based Oversampling for Tabular Data

2022-06-17 · Jayoung Kim, Chaejeong Lee, Yehjin Shin, Sewon Park 외

Score-based generative models (SGMs) are a recent breakthrough in generating fake images. SGMs are known to surpass other generative models, e.g., generative adversarial networks (GANs) and variational autoencoders (VAEs…

Style Transfer

Sketch-based Normal Map Generation with Geometric Sampling

2021-04-23 · Yi He, Haoran Xie, Chao Zhang, Xi Yang 외

Normal map is an important and efficient way to represent complex 3D models. A designer may benefit from the auto-generation of high quality and accurate normal maps from freehand sketches in 3D content creation. This pa…

Generative Adversarial Network

Adaptive sampling using variational autoencoder and reinforcement learning

2025-12-03 · Adil Rasheed, Mikael Aleksander Jansen Shahly, Muhammad Faisal Aftab arxiv

Compressed sensing enables sparse sampling but relies on generic bases and random measurements, limiting efficiency and reconstruction quality. Optimal sensor placement uses historcal data to design tailored sampling pat…

Reinforcement Learning

Improving Sampling from Generative Autoencoders with Markov Chains

2016-10-28 · Antonia Creswell, Kai Arulkumaran, Anil Anthony Bharath

We focus on generative autoencoders, such as variational or adversarial autoencoders, which jointly learn a generative model alongside an inference model. Generative autoencoders are those which are trained to softly enf…