NewEvery arXiv paper, its researchers & institutions — mapped.
the archive

#generative modeling

6 results
cs.CV2019

Image Synthesis with a Single (Robust) Classifier

Shibani Santurkar, Dimitris Tsipras, Brandon Tran +3

The paper demonstrates that a single off‑the‑shelf classifier, when trained to be adversarially robust, can be used for various image synthesis tasks by directly manipulating salie…

#image synthesis#adversarial robustness#robust classifiers#feature manipulation
cs.SD2019

Audio Source Separation Using Variational Autoencoders and Weak Class Supervision

Ertuğ Karamatlı, Ali Taylan Cemgil, Serap Kırbız

The paper introduces a method for separating audio sources in mixtures using class‑level labels only, by attaching a variational autoencoder to each source class within a non‑negat…

#source separation#variational autoencoders#weak supervision#generative modeling
cs.LG2019

Noise Contrastive Variational Autoencoders

Octavian-Eugen Ganea, Yashas Annadani, Gary Bécigneul

The paper studies why variational autoencoders often suffer from posterior collapse and proposes a new model, NC‑VAE, that uses noise contrastive estimation to prevent this collaps…

#variational autoencoders#posterior collapse#noise contrastive estimation#latent representations
cs.NE2019

Training capsules as a routing-weighted product of expert neurons

Michael Hauser

The paper models capsule networks as a product of expert neurons, using routing‑by‑agreement coefficients as weights in an energy‑based formulation, and introduces an unsupervised…

#capsule networks#dynamic routing#unsupervised learning#energy-based models
cs.LG2019

Training products of expert capsules with mixing by dynamic routing

Michael Hauser

The paper proposes an unsupervised learning algorithm for capsule networks that uses an energy function and dynamic routing to train products of expert capsules, enabling realistic…

#unsupervised learning#capsule networks#dynamic routing#energy-based models
econ.EM2019

Information processing constraints in travel behaviour modelling: A generative learning approach

Melvin Wong, Bilal Farooq

The paper introduces a data‑driven generative model based on rational inattention theory to capture how travelers process limited information and uncertainty when making travel cho…

#travel behavior#rational inattention#generative modeling#information processing