Search Results for author: Zhisheng Xiao

Found 11 papers, 5 papers with code

Adaptive Multi-stage Density Ratio Estimation for Learning Latent Space Energy-based Model

no code implementations19 Sep 2022 Zhisheng Xiao, Tian Han

Instead, we propose to use noise contrastive estimation (NCE) to discriminatively learn the EBM through density ratio estimation between the latent prior density and latent posterior density.

Anomaly Detection Density Ratio Estimation +1

Tackling the Generative Learning Trilemma with Denoising Diffusion GANs

5 code implementations ICLR 2022 Zhisheng Xiao, Karsten Kreis, Arash Vahdat

To the best of our knowledge, denoising diffusion GAN is the first model that reduces sampling cost in diffusion models to an extent that allows them to be applied to real-world applications inexpensively.

Image Generation

Do We Really Need to Learn Representations from In-domain Data for Outlier Detection?

no code implementations19 May 2021 Zhisheng Xiao, Qing Yan, Yali Amit

Unsupervised outlier detection, which predicts if a test sample is an outlier or not using only the information from unlabelled inlier data, is an important but challenging task.

Outlier Detection Representation Learning

EBMs Trained with Maximum Likelihood are Generator Models Trained with a Self-adverserial Loss

no code implementations ICLR Workshop EBM 2021 Zhisheng Xiao, Qing Yan, Yali Amit

Doing so allows us to study the density induced by the dynamics (if the dynamics are invertible), and connect with GANs by treating the dynamics as generator models, the initial values as latent variables and the loss as optimizing a critic defined by the very same energy that determines the generator through its gradient.

ControlVAE: Tuning, Analytical Properties, and Performance Analysis

4 code implementations31 Oct 2020 Huajie Shao, Zhisheng Xiao, Shuochao Yao, Aston Zhang, Shengzhong Liu, Tarek Abdelzaher

ControlVAE is a new variational autoencoder (VAE) framework that combines the automatic control theory with the basic VAE to stabilize the KL-divergence of VAE models to a specified value.

Disentanglement Image Generation +1

VAEBM: A Symbiosis between Variational Autoencoders and Energy-based Models

1 code implementation ICLR 2021 Zhisheng Xiao, Karsten Kreis, Jan Kautz, Arash Vahdat

VAEBM captures the overall mode structure of the data distribution using a state-of-the-art VAE and it relies on its EBM component to explicitly exclude non-data-like regions from the model and refine the image samples.

Image Generation Out-of-Distribution Detection

Exponential Tilting of Generative Models: Improving Sample Quality by Training and Sampling from Latent Energy

no code implementations15 Jun 2020 Zhisheng Xiao, Qing Yan, Yali Amit

In this paper, we present a general method that can improve the sample quality of pre-trained likelihood based generative models.

Likelihood Regret: An Out-of-Distribution Detection Score For Variational Auto-encoder

3 code implementations NeurIPS 2020 Zhisheng Xiao, Qing Yan, Yali Amit

An important application of generative modeling should be the ability to detect out-of-distribution (OOD) samples by setting a threshold on the likelihood.

Out-of-Distribution Detection Out of Distribution (OOD) Detection

A Method to Model Conditional Distributions with Normalizing Flows

no code implementations5 Nov 2019 Zhisheng Xiao, Qing Yan, Yali Amit

In particular, we use our proposed method to analyze inverse problems with invertible neural networks by maximizing the posterior likelihood.

Understanding Limitation of Two Symmetrized Orders by Worst-case Complexity

no code implementations10 Oct 2019 Peijun Xiao, Zhisheng Xiao, Ruoyu Sun

Recently, Coordinate Descent (CD) with cyclic order was shown to be $O(n^2)$ times slower than randomized versions in the worst-case.

Vocal Bursts Valence Prediction

Generative Latent Flow

1 code implementation24 May 2019 Zhisheng Xiao, Qing Yan, Yali Amit

In this work, we propose the Generative Latent Flow (GLF), an algorithm for generative modeling of the data distribution.

Image Generation

Cannot find the paper you are looking for? You can Submit a new open access paper.