996 citations · 1.7k across the 31 of their papers we have counts for
31 papers
Immune Defense: A Novel Adversarial Defense Mechanism for Preventing the Generation of Adversarial Examples
Jinwei Wang, Hao Wu, Haihua Wang +3
The vulnerability of Deep Neural Networks (DNNs) to adversarial examples has been confirmed. Existing adversarial defenses primarily aim at preventing adversarial examples from att…
The Quadratic Wasserstein Metric With Squaring Scaling For Seismic Velocity Inversion
Zhengyang Li, Yijia Tang, Jing Chen +1
The quadratic Wasserstein metric has shown its power in measuring the difference between probability densities, which benefits optimization objective function with better convexity…
Cooperative Learning for Noisy Supervision
Hao Wu, Jiangchao Yao, Ya Zhang +1
Learning with noisy labels has gained the enormous interest in the robust deep learning area. Recent studies have empirically disclosed that utilizing dual networks can enhance the…
Conjugate Energy-Based Models
Hao Wu, Babak Esmaeili, Michael Wick +2
In this paper, we propose conjugate energy-based models (CEBMs), a new class of energy-based models that define a joint density over data and latent variables. The joint density of…
Boosting Offline Reinforcement Learning with Residual Generative Modeling
Hua Wei, Deheng Ye, Zhao Liu +5
Offline reinforcement learning (RL) tries to learn the near-optimal policy with recorded offline experience without online exploration. Current offline RL research includes: 1) gen…
Nested Variational Inference
Heiko Zimmermann, Hao Wu, Babak Esmaeili +1
We develop nested variational inference (NVI), a family of methods that learn proposals for nested importance samplers by minimizing an forward or reverse KL divergence at each lev…
XRJL-HKUST at SemEval-2021 Task 4: WordNet-Enhanced Dual Multi-head Co-Attention for Reading Comprehension of Abstract Meaning
Yuxin Jiang, Ziyi Shou, Qijun Wang +2
This paper presents our submitted system to SemEval 2021 Task 4: Reading Comprehension of Abstract Meaning. Our system uses a large pre-trained language model as the encoder and an…
Learning Proposals for Probabilistic Programs with Inference Combinators
Sam Stites, Heiko Zimmermann, Hao Wu +2
We develop operators for construction of proposals in probabilistic programs, which we refer to as inference combinators. Inference combinators define a grammar over importance sam…
Memory Group Sampling Based Online Action Recognition Using Kinetic Skeleton Features
Guoliang Liu, Qinghui Zhang, Yichao Cao +3
Online action recognition is an important task for human centered intelligent services, which is still difficult to achieve due to the varieties and uncertainties of spatial and te…
Learning the Best Pooling Strategy for Visual Semantic Embedding
Jiacheng Chen, Hexiang Hu, Hao Wu +2
Visual Semantic Embedding (VSE) is a dominant approach for vision-language retrieval, which aims at learning a deep embedding space such that visual data are embedded close to thei…
Real-time Human Activity Recognition Using Conditionally Parametrized Convolutions on Mobile and Wearable Devices
Xin Cheng, Lei Zhang, Yin Tang +3
Recently, deep learning has represented an important research trend in human activity recognition (HAR). In particular, deep convolutional neural networks (CNNs) have achieved stat…
DanHAR: Dual Attention Network For Multimodal Human Activity Recognition Using Wearable Sensors
Wenbin Gao, Lei Zhang, Qi Teng +2
Human activity recognition (HAR) in ubiquitous computing has been beginning to incorporate attention into the context of deep neural networks (DNNs), in which the rich sensing data…
Integer Quantization for Deep Learning Inference: Principles and Empirical Evaluation
Hao Wu, Patrick Judd, Xiaojie Zhang +2
Quantization techniques can reduce the size of Deep Neural Networks and improve inference latency and throughput by taking advantage of high throughput integer instructions. In thi…
Masked Face Recognition Dataset and Application
Zhongyuan Wang, Guangcheng Wang, Baojin Huang +11
In order to effectively prevent the spread of COVID-19 virus, almost everyone wears a mask during coronavirus epidemic. This almost makes conventional facial recognition technology…
DeepDualMapper: A Gated Fusion Network for Automatic Map Extraction using Aerial Images and Trajectories
Hao Wu, Hanyuan Zhang, Xinyu Zhang +3
Automatic map extraction is of great importance to urban computing and location-based services. Aerial image and GPS trajectory data refer to two different data sources that could…
Mastering Complex Control in MOBA Games with Deep Reinforcement Learning
Deheng Ye, Zhao Liu, Mingfei Sun +15
We study the reinforcement learning problem of complex action control in the Multi-player Online Battle Arena (MOBA) 1v1 games. This problem involves far more complicated state and…
Large Scale Open-Set Deep Logo Detection
Muhammet Bastan, Hao-Yu Wu, Tian Cao +2
We present an open-set logo detection (OSLD) system, which can detect (localize and recognize) any number of unseen logo classes without re-training; it only requires a small set o…
Amortized Population Gibbs Samplers with Neural Sufficient Statistics
Hao Wu, Heiko Zimmermann, Eli Sennesh +2
We develop amortized population Gibbs (APG) samplers, a class of scalable methods that frames structured variational inference as adaptive importance sampling. APG samplers constru…
A Variational Approach for Learning from Positive and Unlabeled Data
Hui Chen, Fangqing Liu, Yin Wang +2
Learning binary classifiers only from positive and unlabeled (PU) data is an important and challenging task in many real-world applications, including web text classification, dise…
Adaptive Learning Material Recommendation in Online Language Education
Shuhan Wang, Hao Wu, Ji Hun Kim +1
Recommending personalized learning materials for online language learning is challenging because we typically lack data about the student's ability and the relative difficulty of l…
UniVSE: Robust Visual Semantic Embeddings via Structured Semantic Representations
Hao Wu, Jiayuan Mao, Yufeng Zhang +4
We propose Unified Visual-Semantic Embeddings (UniVSE) for learning a joint space of visual and textual concepts. The space unifies the concepts at different levels, including obje…
Composing Modeling and Inference Operations with Probabilistic Program Combinators
Eli Sennesh, Adam Ścibior, Hao Wu +1
Probabilistic programs with dynamic computation graphs can define measures over sample spaces with unbounded dimensionality, which constitute programmatic analogues to Bayesian non…
Classification is a Strong Baseline for Deep Metric Learning
Andrew Zhai, Hao-Yu Wu
Deep metric learning aims to learn a function mapping image pixels to embedding feature vectors that model the similarity between images. Two major applications of metric learning…
Structured Disentangled Representations
Babak Esmaeili, Hao Wu, Sarthak Jain +6
Deep latent-variable models learn representations of high-dimensional data in an unsupervised manner. A number of recent efforts have focused on learning representations that disen…