Chun-Liang Li

On Concept-Based Explanations in Deep Neural Networks

Deep neural networks (DNNs) build high-level intelligence on low-level r...
10/17/2019 ∙ by Chih-Kuan Yeh, et al. ∙ 21 ∙ share

read it
Unsupervised Program Synthesis for Images using Tree-Structured LSTM

Program synthesis has recently emerged as a promising approach to the im...
01/27/2020 ∙ by Chenghui Zhou, et al. ∙ 12 ∙ share

read it
Developing Creative AI to Generate Sculptural Objects

We explore the intersection of human and machine creativity by generatin...
08/20/2019 ∙ by Songwei Ge, et al. ∙ 8 ∙ share

read it
FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence

Semi-supervised learning (SSL) provides an effective means of leveraging...
01/21/2020 ∙ by Kihyuk Sohn, et al. ∙ 7 ∙ share

read it
A Simple Semi-Supervised Learning Framework for Object Detection

Semi-supervised learning (SSL) has promising potential for improving the...
05/10/2020 ∙ by Kihyuk Sohn, et al. ∙ 3 ∙ share

read it
Adversarial Geometry and Lighting using a Differentiable Renderer

Many machine learning classifiers are vulnerable to adversarial attacks,...
08/08/2018 ∙ by Hsueh-Ti Derek Liu, et al. ∙ 2 ∙ share

read it
Sobolev GAN

We propose a new Integral Probability Metric (IPM) between distributions...
11/14/2017 ∙ by Youssef Mroueh, et al. ∙ 0 ∙ share

read it
MMD GAN: Towards Deeper Understanding of Moment Matching Network

Generative moment matching network (GMMN) is a deep generative model tha...
05/24/2017 ∙ by Chun-Liang Li, et al. ∙ 0 ∙ share

read it
Data-driven Random Fourier Features using Stein Effect

Large-scale kernel approximation is an important problem in machine lear...
05/23/2017 ∙ by Wei-Cheng Chang, et al. ∙ 0 ∙ share

read it
Annealing Gaussian into ReLU: a New Sampling Strategy for Leaky-ReLU RBM

Restricted Boltzmann Machine (RBM) is a bipartite graphical model that i...
11/11/2016 ∙ by Chun-Liang Li, et al. ∙ 0 ∙ share

read it
One Network to Solve Them All --- Solving Linear Inverse Problems using Deep Projection Models

While deep learning methods have achieved state-of-the-art performance i...
03/29/2017 ∙ by J. H. Rick Chang, et al. ∙ 0 ∙ share

read it
Rivalry of Two Families of Algorithms for Memory-Restricted Streaming PCA

We study the problem of recovering the subspace spanned by the first k p...
06/04/2015 ∙ by Chun-Liang Li, et al. ∙ 0 ∙ share

read it
Pedestrian-Synthesis-GAN: Generating Pedestrian Data in Real Scene and Beyond

State-of-the-art pedestrian detection models have achieved great success...
04/05/2018 ∙ by Xi Ouyang, et al. ∙ 0 ∙ share

read it
Nonparametric Density Estimation under Adversarial Losses

We study minimax convergence rates of nonparametric density estimation u...
05/22/2018 ∙ by Shashank Singh, et al. ∙ 0 ∙ share

read it
Point Cloud GAN

Generative Adversarial Networks (GAN) can achieve promising performance ...
10/13/2018 ∙ by Chun-Liang Li, et al. ∙ 0 ∙ share

read it
Hallucinating Point Cloud into 3D Sculptural Object

Our team of artists and machine learning researchers designed a creative...
11/13/2018 ∙ by Chun-Liang Li, et al. ∙ 0 ∙ share

read it
Kernel Change-point Detection with Auxiliary Deep Generative Models

Detecting the emergence of abrupt property changes in time series is a c...
01/18/2019 ∙ by Wei-Cheng Chang, et al. ∙ 0 ∙ share

read it
Implicit Kernel Learning

Kernels are powerful and versatile tools in machine learning and statist...
02/26/2019 ∙ by Chun-Liang Li, et al. ∙ 0 ∙ share

read it
Beyond Pixel Norm-Balls: Parametric Adversaries using an Analytically Differentiable Renderer

Many machine learning image classifiers are vulnerable to adversarial at...
08/08/2018 ∙ by Hsueh-Ti Derek Liu, et al. ∙ 0 ∙ share

read it
LBS Autoencoder: Self-supervised Fitting of Articulated Meshes to Point Clouds

We present LBS-AE; a self-supervised autoencoding algorithm for fitting ...
04/22/2019 ∙ by Chun-Liang Li, et al. ∙ 0 ∙ share

read it
Getting Topology and Point Cloud Generation to Mesh

In this work, we explore the idea that effective generative models for p...
12/08/2019 ∙ by Austin Dill, et al. ∙ 0 ∙ share

read it
Learned Interpolation for 3D Generation

In order to generate novel 3D shapes with machine learning, one must all...
12/08/2019 ∙ by Austin Dill, et al. ∙ 0 ∙ share

read it

Chun-Liang Li

Featured Co-authors

Ruslan Salakhutdinov

Barnabas Poczos

Yu Cheng

Yang Zhang

Pradeep Ravikumar

Yiming Yang

Pan Zhou

Han Zhang

Nicholas Carlini

Been Kim

Manzil Zaheer

On Concept-Based Explanations in Deep Neural Networks

Unsupervised Program Synthesis for Images using Tree-Structured LSTM

Developing Creative AI to Generate Sculptural Objects

FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence

A Simple Semi-Supervised Learning Framework for Object Detection

Adversarial Geometry and Lighting using a Differentiable Renderer

Sobolev GAN

MMD GAN: Towards Deeper Understanding of Moment Matching Network

Data-driven Random Fourier Features using Stein Effect

Annealing Gaussian into ReLU: a New Sampling Strategy for Leaky-ReLU RBM

One Network to Solve Them All --- Solving Linear Inverse Problems using Deep Projection Models

Rivalry of Two Families of Algorithms for Memory-Restricted Streaming PCA

Pedestrian-Synthesis-GAN: Generating Pedestrian Data in Real Scene and Beyond

Nonparametric Density Estimation under Adversarial Losses

Point Cloud GAN

Hallucinating Point Cloud into 3D Sculptural Object

Kernel Change-point Detection with Auxiliary Deep Generative Models

Implicit Kernel Learning

Beyond Pixel Norm-Balls: Parametric Adversaries using an Analytically Differentiable Renderer

LBS Autoencoder: Self-supervised Fitting of Articulated Meshes to Point Clouds

Getting Topology and Point Cloud Generation to Mesh

Learned Interpolation for 3D Generation