Jun Zhu

is this you? claim profile

∙ 0 followers
Nanjing University of Aeronautics and Astronautics ∙ Qualcomm ∙ University of Wisconsin-Madison ∙ Carnegie Mellon University

Associate Professor, Computer Science Department at Tsinghua University. Adjunct Faculty, Machine Learning Department at Carnegie Mellon University.

Multi-label classification: do Hamming loss and subset accuracy really conflict with each other?

Various evaluation measures have been developed for multi-label classifi...
11/16/2020 ∙ by Guoqiang Wu, et al. ∙ 0 ∙ share

read it
Further Analysis of Outlier Detection with Deep Generative Models

The recent, counter-intuitive discovery that deep generative models (DGM...
10/25/2020 ∙ by Ziyu Wang, et al. ∙ 6 ∙ share

read it
Variational (Gradient) Estimate of the Score Function in Energy-based Latent Variable Models

The learning and evaluation of energy-based latent variable models (EBLV...
10/16/2020 ∙ by Fan Bao, et al. ∙ 0 ∙ share

read it
Bi-level Score Matching for Learning Energy-based Latent Variable Models

Score matching (SM) provides a compelling approach to learn energy-based...
10/15/2020 ∙ by Fan Bao, et al. ∙ 0 ∙ share

read it
Bag of Tricks for Adversarial Training

Adversarial training (AT) is one of the most effective strategies for pr...
10/01/2020 ∙ by Tianyu Pang, et al. ∙ 0 ∙ share

read it
Deep Active Learning by Model Interpretability

Recent successes of Deep Neural Networks (DNNs) in a variety of research...
07/23/2020 ∙ by Qiang Liu, et al. ∙ 0 ∙ share

read it
Training Interpretable Convolutional Neural Networks by Differentiating Class-specific Filters

Convolutional neural networks (CNNs) have been successfully used in a ra...
07/16/2020 ∙ by Haoyu Liang, et al. ∙ 0 ∙ share

read it
A quasi-conservative discontinuous Galerkin method for multi-component flows using the non-oscillatory kinetic flux

In this paper, a high order quasi-conservative discontinuous Galerkin (D...
07/12/2020 ∙ by Dongmi Luo, et al. ∙ 0 ∙ share

read it
Delving into the Adversarial Robustness on Face Recognition

Face recognition has recently made substantial progress and achieved hig...
07/08/2020 ∙ by Xiao Yang, et al. ∙ 10 ∙ share

read it
Efficient Inference of Nonparametric Interaction in Spiking-neuron Networks

Hawkes process provides an effective statistical framework for analyzing...
06/23/2020 ∙ by Feng Zhou, et al. ∙ 6 ∙ share

read it
Absolutely convergent fixed-point fast sweeping WENO methods for steady state of hyperbolic conservation laws

Fixed-point iterative sweeping methods were developed in the literature ...
06/21/2020 ∙ by Liang Li, et al. ∙ 0 ∙ share

read it
Calibrated Reliable Regression using Maximum Mean Discrepancy

Accurate quantification of uncertainty is crucial for real-world applica...
06/18/2020 ∙ by Peng Cui, et al. ∙ 0 ∙ share

read it
Dynamic Window-level Granger Causality of Multi-channel Time Series

Granger causality method analyzes the time series causalities without bu...
06/14/2020 ∙ by Zhiheng Zhang, et al. ∙ 0 ∙ share

read it
Brain-inspired global-local hybrid learning towards human-like intelligence

The combination of neuroscience-oriented and computer-science-oriented a...
06/05/2020 ∙ by Yujie Wu, et al. ∙ 0 ∙ share

read it
Nonparametric Score Estimators

Estimating the score, i.e., the gradient of log density function, from a...
05/20/2020 ∙ by Yuhao Zhou, et al. ∙ 0 ∙ share

read it
SUMO: Unbiased Estimation of Log Marginal Probability for Latent Variable Models

Standard variational lower bounds used to train latent variable models p...
04/01/2020 ∙ by Yucen Luo, et al. ∙ 8 ∙ share

read it
Towards Privacy Protection by Generating Adversarial Identity Masks

As billions of personal data such as photos are shared through social me...
03/15/2020 ∙ by Xiao Yang, et al. ∙ 5 ∙ share

read it
Triple Memory Networks: a Brain-Inspired Method for Continual Learning

Continual acquisition of novel experience without interfering previously...
03/06/2020 ∙ by Liyuan Wang, et al. ∙ 0 ∙ share

read it
VFlow: More Expressive Generative Flows with Variational Data Augmentation

Generative flows are promising tractable models for density modeling tha...
02/22/2020 ∙ by Jianfei Chen, et al. ∙ 0 ∙ share

read it
Boosting Adversarial Training with Hypersphere Embedding

Adversarial training (AT) is one of the most effective defenses to impro...
02/20/2020 ∙ by Tianyu Pang, et al. ∙ 13 ∙ share

read it
A Wasserstein Minimum Velocity Approach to Learning Unnormalized Models

Score matching provides an effective approach to learning flexible unnor...
02/18/2020 ∙ by Ziyu Wang, et al. ∙ 9 ∙ share

read it
Adversarial Distributional Training for Robust Deep Learning

Adversarial training (AT) is among the most effective techniques to impr...
02/14/2020 ∙ by Zhijie Deng, et al. ∙ 0 ∙ share

read it
Benchmarking Adversarial Robustness

Deep neural networks are vulnerable to adversarial examples, which becom...
12/26/2019 ∙ by Yinpeng Dong, et al. ∙ 0 ∙ share

read it
Triple Generative Adversarial Networks

Generative adversarial networks (GANs) have shown promise in image gener...
12/20/2019 ∙ by Chongxuan Li, et al. ∙ 28 ∙ share

read it
Control variates and Rao-Blackwellization for deterministic sweep Markov chains

We study control variate methods for Markov chain Monte Carlo (MCMC) in ...
12/14/2019 ∙ by Stephen Berg, et al. ∙ 0 ∙ share

read it
The Search for Sparse, Robust Neural Networks

Recent work on deep neural network pruning has shown there exist sparse ...
12/05/2019 ∙ by Justin Cosentino, et al. ∙ 0 ∙ share

read it
Design and Interpretation of Universal Adversarial Patches in Face Detection

We consider universal adversarial patches for faces - small visual eleme...
11/30/2019 ∙ by Xiao Yang, et al. ∙ 0 ∙ share

read it
DBSN: Measuring Uncertainty through Bayesian Learning of Deep Neural Network Structures

Bayesian neural networks (BNNs) introduce uncertainty estimation to deep...
11/22/2019 ∙ by Zhijie Deng, et al. ∙ 13 ∙ share

read it
Generative Well-intentioned Networks

We propose Generative Well-intentioned Networks (GWINs), a novel framewo...
10/28/2019 ∙ by Justin Cosentino, et al. ∙ 0 ∙ share

read it
Understanding and Stabilizing GANs' Training Dynamics with Control Theory

Generative adversarial networks (GANs) have made significant progress on...
09/29/2019 ∙ by Kun Xu, et al. ∙ 0 ∙ share

read it
Mixup Inference: Better Exploiting Mixup to Defend Adversarial Attacks

It has been widely recognized that adversarial examples can be easily cr...
09/25/2019 ∙ by Tianyu Pang, et al. ∙ 0 ∙ share

read it
A Simple yet Effective Baseline for Robust Deep Learning with Noisy Labels

Recently deep neural networks have shown their capacity to memorize trai...
09/20/2019 ∙ by Yucen Luo, et al. ∙ 0 ∙ share

read it
Cross-Lingual Contextual Word Embeddings Mapping With Multi-Sense Words In Mind

Recent work in cross-lingual contextual word embedding learning cannot h...
09/18/2019 ∙ by Zheng Zhang, et al. ∙ 0 ∙ share

read it
Spatial Process Decomposition for Quantitative Imaging Biomarkers Using Multiple Images of Varying Shapes

Quantitative imaging biomarkers (QIB) are extracted from medical images ...
07/26/2019 ∙ by ShengLi Tzeng, et al. ∙ 0 ∙ share

read it
Improving Black-box Adversarial Attacks with a Transfer-based Prior

We consider the black-box adversarial setting, where the adversary has t...
06/17/2019 ∙ by Shuyu Cheng, et al. ∙ 0 ∙ share

read it
Multi-objects Generation with Amortized Structural Regularization

Deep generative models (DGMs) have shown promise in image generation. Ho...
06/10/2019 ∙ by Kun Xu, et al. ∙ 0 ∙ share

read it
Automatic Realistic Music Video Generation from Segments of Youtube Videos

A Music Video (MV) is a video aiming at visually illustrating or extendi...
05/29/2019 ∙ by Sarah Gross, et al. ∙ 0 ∙ share

read it
Scalable Training of Inference Networks for Gaussian-Process Models

Inference in Gaussian process (GP) models is computationally challenging...
05/27/2019 ∙ by Jiaxin Shi, et al. ∙ 0 ∙ share

read it
Rethinking Softmax Cross-Entropy Loss for Adversarial Robustness

Previous work shows that adversarially robust generalization requires la...
05/25/2019 ∙ by Tianyu Pang, et al. ∙ 0 ∙ share

read it
Boosting Generative Models by Leveraging Cascaded Meta-Models

Deep generative models are effective methods of modeling data. However, ...
05/11/2019 ∙ by Fan Bao, et al. ∙ 0 ∙ share

read it
Efficient Decision-based Black-box Adversarial Attacks on Face Recognition

Face recognition has obtained remarkable progress in recent years due to...
04/09/2019 ∙ by Yinpeng Dong, et al. ∙ 0 ∙ share

read it
Evading Defenses to Transferable Adversarial Examples by Translation-Invariant Attacks

Deep neural networks are vulnerable to adversarial examples, which can m...
04/05/2019 ∙ by Yinpeng Dong, et al. ∙ 0 ∙ share

read it
Cluster Alignment with a Teacher for Unsupervised Domain Adaptation

Deep learning methods have shown promise in unsupervised domain adaptati...
03/24/2019 ∙ by Zhijie Deng, et al. ∙ 0 ∙ share

read it
Function Space Particle Optimization for Bayesian Neural Networks

While Bayesian neural networks (BNNs) have drawn increasing attention, t...
02/26/2019 ∙ by Ziyu Wang, et al. ∙ 24 ∙ share

read it
Batch Virtual Adversarial Training for Graph Convolutional Networks

We present batch virtual adversarial training (BVAT), a novel regulariza...
02/25/2019 ∙ by Zhijie Deng, et al. ∙ 0 ∙ share

read it
Understanding MCMC Dynamics as Flows on the Wasserstein Space

It is known that the Langevin dynamics used in MCMC is the gradient flow...
02/01/2019 ∙ by Chang Liu, et al. ∙ 0 ∙ share

read it
Secure Massive MIMO Communication with Low-resolution DACs

In this paper, we investigate secure transmission in a massive multiple-...
01/28/2019 ∙ by Jindan Xu, et al. ∙ 0 ∙ share

read it
Reward Shaping via Meta-Learning

Reward shaping is one of the most effective methods to tackle the crucia...
01/27/2019 ∙ by Haosheng Zou, et al. ∙ 0 ∙ share

read it
Improving Adversarial Robustness via Promoting Ensemble Diversity

Though deep neural networks have achieved significant progress on variou...
01/25/2019 ∙ by Tianyu Pang, et al. ∙ 0 ∙ share

read it
Towards Interpretable Deep Neural Networks by Leveraging Adversarial Examples

Sometimes it is not enough for a DNN to produce an outcome. For example,...
01/25/2019 ∙ by Yinpeng Dong, et al. ∙ 0 ∙ share

read it

Jun Zhu

Featured Co-authors