
Query2Label: A Simple Transformer Way to MultiLabel Classification
This paper presents a simple and effective approach to solving the multi...
read it

On the Convergence of PriorGuided ZerothOrder Optimization Algorithms
Zerothorder (ZO) optimization is widely used to handle challenging task...
read it

Boosting Transferability of Targeted Adversarial Examples via Hierarchical Generative Networks
Transferbased adversarial attacks can effectively evaluate model robust...
read it

Understanding Adversarial Attacks on Observations in Deep Reinforcement Learning
Recent works demonstrate that deep reinforcement learning (DRL) models a...
read it

Regularized OFU: an Efficient UCB Estimator forNonlinear Contextual Bandit
Balancing exploration and exploitation (EE) is a fundamental problem in ...
read it

Improving Transferability of Adversarial Patches on Face Recognition with Generative Models
Face recognition is greatly improved by deep convolutional neural networ...
read it

Accumulative Poisoning Attacks on Realtime Data
Collecting training data from untrusted sources exposes machine learning...
read it

Scalable QuasiBayesian Inference for Instrumental Variable Regression
Recent years have witnessed an upsurge of interest in employing flexible...
read it

Understanding Softmax Confidence and Uncertainty
It is often remarked that neural networks fail to increase their uncerta...
read it

Nonlinear Hawkes Processes in TimeVarying System
Hawkes processes are a class of point processes that have the ability to...
read it

Stability and Generalization of Bilevel Programming in Hyperparameter Optimization
Recently, the (gradientbased) bilevel programming framework is widely u...
read it

Exploring Memorization in Adversarial Training
It is well known that deep learning models have a propensity for fitting...
read it

KOPDE: Kernel Optimized Discovery of Partial Differential Equations with Varying Coefficients
Partial differential equations (PDEs) fitting scientific data can repres...
read it

Adversarial Training with Rectified Rejection
Adversarial training (AT) is one of the most effective strategies for pr...
read it

Unsupervised Part Segmentation through Disentangling Appearance and Shape
We study the problem of unsupervised discovery and segmentation of objec...
read it

Rethinking and Reweighting the Univariate Losses for MultiLabel Ranking: Consistency and Generalization
(Partial) ranking loss is a commonly used evaluation measure for multil...
read it

Automated Decisionbased Adversarial Attacks
Deep learning models are vulnerable to adversarial examples, which can f...
read it

MiCE: Mixture of Contrastive Experts for Unsupervised Image Clustering
We present Mixture of Contrastive Experts (MiCE), a unified probabilisti...
read it

Fewshot Continual Learning: a Braininspired Approach
It is an important yet challenging setting to continually learn new task...
read it

CounterStrike Deathmatch with LargeScale Behavioural Cloning
This paper describes an AI agent that plays the popular firstpersonsho...
read it

Accurate and Reliable Forecasting using Stochastic Differential Equations
It is critical yet challenging for deep learning models to properly char...
read it

LiBRe: A Practical Bayesian Approach to Adversarial Detection
Despite their appealing flexibility, deep neural networks (DNNs) are vul...
read it

Blackbox Detection of Backdoor Attacks with Limited Information and Data
Although deep neural networks (DNNs) have made rapid progress in recent ...
read it

Implicit Normalizing Flows
Normalizing flows define a probability distribution by an explicit inver...
read it

DNN2LR: Automatic Feature Crossing for Credit Scoring
Credit scoring is a major application of machine learning for financial ...
read it

Rethinking Natural Adversarial Examples for Classification Models
Recently, it was found that many realworld examples without intentional...
read it

Deep LearningBased Autoencoder for DataDriven Modeling of an RF Photoinjector
We adopt a datadriven approach to model the longitudinal phasespace di...
read it

Cognitive Visual Inspection Service for LCD Manufacturing Industry
With the rapid growth of display devices, quality inspection via machine...
read it

Relaxed Conditional Image Transfer for Semisupervised Domain Adaptation
Semisupervised domain adaptation (SSDA), which aims to learn models in ...
read it

ORDisCo: Effective and Efficient Usage of Incremental Unlabeled Data for Semisupervised Continual Learning
Continual learning usually assumes the incoming data are fully labeled, ...
read it

Series Saliency: Temporal Interpretation for Multivariate Time Series Forecasting
Time series forecasting is an important yet challenging task. Though dee...
read it

Fork or Fail: CycleConsistent Training with ManytoOne Mappings
Cycleconsistent training is widely used for jointly learning a forward ...
read it

Multilabel classification: do Hamming loss and subset accuracy really conflict with each other?
Various evaluation measures have been developed for multilabel classifi...
read it

Further Analysis of Outlier Detection with Deep Generative Models
The recent, counterintuitive discovery that deep generative models (DGM...
read it

Variational (Gradient) Estimate of the Score Function in Energybased Latent Variable Models
The learning and evaluation of energybased latent variable models (EBLV...
read it

Bilevel Score Matching for Learning Energybased Latent Variable Models
Score matching (SM) provides a compelling approach to learn energybased...
read it

Bag of Tricks for Adversarial Training
Adversarial training (AT) is one of the most effective strategies for pr...
read it

Deep Active Learning by Model Interpretability
Recent successes of Deep Neural Networks (DNNs) in a variety of research...
read it

Training Interpretable Convolutional Neural Networks by Differentiating Classspecific Filters
Convolutional neural networks (CNNs) have been successfully used in a ra...
read it

A quasiconservative discontinuous Galerkin method for multicomponent flows using the nonoscillatory kinetic flux
In this paper, a high order quasiconservative discontinuous Galerkin (D...
read it

Delving into the Adversarial Robustness on Face Recognition
Face recognition has recently made substantial progress and achieved hig...
read it

Efficient Inference of Nonparametric Interaction in Spikingneuron Networks
Hawkes process provides an effective statistical framework for analyzing...
read it

Absolutely convergent fixedpoint fast sweeping WENO methods for steady state of hyperbolic conservation laws
Fixedpoint iterative sweeping methods were developed in the literature ...
read it

Calibrated Reliable Regression using Maximum Mean Discrepancy
Accurate quantification of uncertainty is crucial for realworld applica...
read it

Dynamic Windowlevel Granger Causality of Multichannel Time Series
Granger causality method analyzes the time series causalities without bu...
read it

Braininspired globallocal hybrid learning towards humanlike intelligence
The combination of neuroscienceoriented and computerscienceoriented a...
read it

Nonparametric Score Estimators
Estimating the score, i.e., the gradient of log density function, from a...
read it

SUMO: Unbiased Estimation of Log Marginal Probability for Latent Variable Models
Standard variational lower bounds used to train latent variable models p...
read it

Towards Privacy Protection by Generating Adversarial Identity Masks
As billions of personal data such as photos are shared through social me...
read it

Triple Memory Networks: a BrainInspired Method for Continual Learning
Continual acquisition of novel experience without interfering previously...
read it
Jun Zhu
is this you? claim profile
Associate Professor, Computer Science Department at Tsinghua University. Adjunct Faculty, Machine Learning Department at Carnegie Mellon University.