Semi-supervised learning using BiGAN with triplet loss.
problem Training GANs with limited labeled data.
method BiGAN with triplet loss for semi-supervised learning.
result BiGAN latent space features improve classification and retrieval.
On-device research index
arXiv research
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.
169,051 papers · 148 categories
Trend · papers per month
15 results for “BiGANs”
We improve GANs by enforcing reproducibility and using non-uniform sampling.
problem Overrepresentation of certain samples in GANs' marginal log-likelihood.
method Enforce reproducibility through matching empirical distribution to prior, use non-uniform sampling for mini-batch selection.
result Improved quality and variety in generated samples, validated on CIFAR10, Fashion MNIST, and CelebA.
A new method uses BiGANs to assess operational risks in distribution networks.
problem Operational risk assessment in distribution networks using online monitoring data.
method Unsupervised approach based on BiGANs with adversarial feature learning and operational risk assessment.
result The approach provides more accurate risk assessment and discovers latent data structures.
This study improves GANs with encoders for better image generation and reconstruction.
problem GANs lack encoders that map images back to latent space.
method Consider adversarially learned generative models with autoencoders, and compare simple encoder training to BiGAN.
result Simple encoder training can achieve comparable performance to BiGAN.
CBiGAN combines GANs and AutoEncoders for efficient anomaly detection in images.
problem Efficient anomaly detection in images, especially texture-type anomalies.
method CBiGAN integrates a consistency constraint in both encoder and decoder of a BiGAN model.
result CBiGAN outperforms standard baselines and state-of-the-art approaches on MVTec AD benchmark.
We reinterpreting the variational inference in a new perspective. Via this way, we can easily prove that EM algorithm, VAE, GAN, AAE, ALI(BiGAN) are all special cases of variational inference. The proof also reveals the loss of standard GAN is incomplete and it explains why we need to train GAN cautiously. From that, w…
New method for bidirectional generative modeling using adversarial gradient estimation.
problem Bidirectional generative modeling with various -divergences.
method Adversarial gradient estimation for -divergence optimization.
result Similar algorithms for different -divergences with varying scaling.
On the Statistical Properties of Generative Adversarial Models for Low Intrinsic Data Dimensionstat.ML
The paper improves GANs' theoretical guarantees for low-dimensional data.
problem Theoretical guarantees for GANs' statistical accuracy remain pessimistic.
method Analytical derivation of statistical guarantees on estimated densities.
result Theoretical rates of convergence for GANs and BiGANs are derived.
The ability of the Generative Adversarial Networks (GANs) framework to learn generative models mapping from simple latent distributions to arbitrarily complex data distributions has been demonstrated empirically, with compelling results showing that the latent space of such generators captures semantic variation in the…
The Information Autoencoding Family: A Lagrangian Perspective on Latent Variable Generative Modelsstat.ML
A large number of objectives have been proposed to train latent variable generative models. We show that many of them are Lagrangian dual functions of the same primal optimization problem. The primal problem optimizes the mutual information between latent and visible variables, subject to the constraints of accurately …
Encoder-decoder GANs architectures (e.g., BiGAN and ALI) seek to add an inference mechanism to the GANs setup, consisting of a small encoder deep net that maps data-points to their succinct encodings. The intuition is that being forced to train an encoder alongside the usual generator forces the system to learn meaning…
Proposes GM Score to evaluate GANs considering diversity, disentanglement, and discriminability.
problem Evaluation of GANs for sample quality and diversity.
method Integrates various factors including intra-class and inter-class diversity, disentanglement, and discriminability metrics.
result Demonstrates improved evaluation of GANs on MNIST dataset.
Survey of GANs and autoencoders, addressing mode collapse and likelihood issues.
problem Addressing mode collapse and likelihood issues in GANs and autoencoders.
method Explains various GAN and autoencoder variants, their applications, and methods to resolve issues.
result Various methods to resolve mode collapse and improve likelihood in GANs and autoencoders.
Sharp error bounds derived for bidirectional GANs without restrictive assumptions.
problem Estimating the error of bidirectional GANs under various conditions.
method Dudley distance, neural network functions, decomposition of IPM.
result Nearly sharp bounds for bidirectional GAN estimation error.
Generalizes adversarial learning for better latent variable inference in GANs.
problem Improving latent variable inference in GANs for diverse applications.
method Adversarial learning with multiple feedback layers, self-supervision, and auxiliary tasks.
result Achieves global optimum matching multiple joint distributions.