Zhangyang Wang

research

∙ 05/24/2022

Quarantine: Sparsity Can Uncover the Trojan Attack Trigger for Free

Trojan attacks threaten deep neural networks (DNNs) by poisoning them to...

Tianlong Chen, et al. ∙

research

∙ 05/11/2022

Deep Architecture Connectivity Matters for Its Convergence: A Fine-Grained Analysis

Advanced deep neural networks (DNNs), designed by either human or AutoML...

Wuyang Chen, et al. ∙

research

∙ 04/09/2022

E^2TAD: An Energy-Efficient Tracking-based Action Detector

Video action detection (spatio-temporal action localization) is usually ...

Xin Hu, et al. ∙

research

∙ 04/05/2022

Unified Implicit Neural Stylization

Representing visual signals by implicit representation (e.g., a coordina...

Zhiwen Fan, et al. ∙

research

∙ 04/04/2022

APP: Anytime Progressive Pruning

With the latest advances in deep learning, there has been a lot of focus...

Diganta Misra, et al. ∙

research

∙ 04/02/2022

SinNeRF: Training Neural Radiance Fields on Complex Scenes from a Single Image

Despite the rapid development of Neural Radiance Field (NeRF), the neces...

Dejia Xu, et al. ∙

research

∙ 03/31/2022

VFDS: Variational Foresight Dynamic Selection in Bayesian Neural Networks for Efficient Human Activity Recognition

In many machine learning tasks, input features with varying degrees of p...

Randy Ardywibowo, et al. ∙

research

∙ 03/27/2022

On the Neural Tangent Kernel Analysis of Randomly Pruned Wide Neural Networks

We study the behavior of ultra-wide neural networks when their weights a...

Hongru Yang, et al. ∙

research

∙ 03/18/2022

Efficient Split-Mix Federated Learning for On-Demand and In-Situ Customization

Federated learning (FL) provides a distributed learning framework for mu...

Junyuan Hong, et al. ∙

research

∙ 03/13/2022

Symbolic Learning to Optimize: Towards Interpretability and Scalability

Recent studies on Learning to Optimize (L2O) suggest a promising path to...

Wenqing Zheng, et al. ∙

research

∙ 03/12/2022

Optimizer Amalgamation

Selecting an appropriate optimizer for a given problem is of major inter...

Tianshu Huang, et al. ∙

research

∙ 03/12/2022

The Principle of Diversity: Training Stronger Vision Transformers Calls for Reducing All Levels of Redundancy

Vision transformers (ViTs) have gained increasing popularity as they are...

Tianlong Chen, et al. ∙

research

∙ 03/09/2022

Anti-Oversmoothing in Deep Vision Transformers via the Fourier Domain Analysis: From Theory to Practice

Vision Transformer (ViT) has recently demonstrated promise in computer v...

Peihao Wang, et al. ∙

research

∙ 02/24/2022

Auto-scaling Vision Transformers without Training

This work targets automated designing and scaling of Vision Transformers...

Wuyang Chen, et al. ∙

research

∙ 02/09/2022

Coarsening the Granularity: Towards Structurally Sparse Lottery Tickets

The lottery ticket hypothesis (LTH) has shown that dense models contain ...

Tianlong Chen, et al. ∙

research

∙ 02/05/2022

The Unreasonable Effectiveness of Random Pruning: Return of the Most Naive Baseline for Sparse Training

Random pruning is arguably the most naive way to attain sparsity in neur...

Shiwei Liu, et al. ∙

research

∙ 01/04/2022

Bringing Your Own View: Graph Contrastive Learning without Prefabricated Data Augmentations

Self-supervision is recently surging at its new frontier of graph learni...

Yuning You, et al. ∙

research

∙ 01/02/2022

Fast and High-Quality Image Denoising via Malleable Convolutions

Many image processing networks apply a single set of static convolutiona...

Yifan Jiang, et al. ∙

research

∙ 12/18/2021

Federated Dynamic Sparse Training: Computing Less, Communicating Less, Yet Learning Better

Federated learning (FL) enables distribution of machine learning workloa...

Sameer Bibikar, et al. ∙

research

∙ 12/17/2021

A Simple Single-Scale Vision Transformer for Object Localization and Instance Segmentation

This work presents a simple vision transformer design as a strong baseli...

Wuyang Chen, et al. ∙

research

∙ 12/09/2021

Auto-X3D: Ultra-Efficient Video Understanding via Finer-Grained Neural Architecture Search

Efficient video architecture is the key to deploying video recognition s...

Yifan Jiang, et al. ∙

research

∙ 11/08/2021

Cold Brew: Distilling Graph Node Representations with Incomplete or Missing Neighborhoods

Graph Neural Networks (GNNs) have achieved state of the art performance ...

Wenqing Zheng, et al. ∙

research

∙ 11/01/2021

Improving Contrastive Learning on Imbalanced Seed Data via Open-World Sampling

Contrastive learning approaches have achieved great success in learning ...

Ziyu Jiang, et al. ∙

research

∙ 10/30/2021

You are caught stealing my winning lottery ticket! Making a lottery ticket claim its ownership

Despite tremendous success in many application scenarios, the training a...

Xuxi Chen, et al. ∙

research

∙ 10/30/2021

DSEE: Dually Sparsity-embedded Efficient Tuning of Pre-trained Language Models

Gigantic pre-trained models have become central to natural language proc...

Xuxi Chen, et al. ∙

research

∙ 10/29/2021

Delayed Propagation Transformer: A Universal Computation Engine towards Practical Control in Cyber-Physical Systems

Multi-agent control is a central theme in the Cyber-Physical Systems (CP...

Wenqing Zheng, et al. ∙

research

∙ 10/29/2021

Hyperparameter Tuning is All You Need for LISTA

Learned Iterative Shrinkage-Thresholding Algorithm (LISTA) introduces th...

Xiaohan Chen, et al. ∙

research

∙ 10/26/2021

AugMax: Adversarial Composition of Random Augmentations for Robust Training

Data augmentation is a simple yet effective way to improve the robustnes...

Haotao Wang, et al. ∙

research

∙ 10/09/2021

Towards Lifelong Learning of Multilingual Text-To-Speech Synthesis

This work presents a lifelong learning approach to train a multilingual ...

Mu Yang, et al. ∙

research

∙ 10/07/2021

Universality of Deep Neural Network Lottery Tickets: A Renormalization Group Perspective

Foundational work on the Lottery Ticket Hypothesis has suggested an exci...

William T Redman, et al. ∙

research

∙ 09/21/2021

Skeleton-Graph: Long-Term 3D Motion Prediction From 2D Observations Using Deep Spatio-Temporal Graph CNNs

Several applications such as autonomous driving, augmented reality and v...

Abduallah Mohamed, et al. ∙

research

∙ 08/30/2021

Searching for Two-Stream Models in Multivariate Space for Video Recognition

Conventional video models rely on a single stream to capture the complex...

Xinyu Gong, et al. ∙

research

∙ 08/26/2021

Understanding and Accelerating Neural Architecture Search with Training-Free and Theory-Grounded Metrics

This work targets designing a principled and unified training-free frame...

Wuyang Chen, et al. ∙

research

∙ 08/24/2021

Bag of Tricks for Training Deeper Graph Neural Networks: A Comprehensive Benchmark Study

Training deep graph neural networks (GNNs) is notoriously hard. Besides ...

Tianlong Chen, et al. ∙

research

∙ 08/15/2021

SSH: A Self-Supervised Framework for Image Harmonization

Image harmonization aims to improve the quality of image compositing by ...

Yifan Jiang, et al. ∙

research

∙ 08/01/2021

CERL: A Unified Optimization Framework for Light Enhancement with Realistic Noise

Low-light images captured in the real world are inevitably corrupted by ...

Zeyuan Chen, et al. ∙

research

∙ 07/16/2021

DANCE: DAta-Network Co-optimization for Efficient Segmentation Model Training and Inference

Semantic segmentation for scene understanding is nowadays widely demande...

Chaojian Li, et al. ∙

research

∙ 07/01/2021

Sanity Checks for Lottery Tickets: Does Your Winning Ticket Really Win the Jackpot?

There have been long-standing controversies and inconsistencies over the...

Xiaolong Ma, et al. ∙

research

∙ 06/28/2021

FreeTickets: Accurate, Robust and Efficient Deep Ensemble by Training with Dynamic Sparsity

Recent works on sparse neural networks have demonstrated that it is poss...

Shiwei Liu, et al. ∙

research

∙ 06/24/2021

Scalable Perception-Action-Communication Loops with Convolutional and Graph Neural Networks

In this paper, we present a perception-action-communication loop design ...

Ting-Kuei Hu, et al. ∙

research

∙ 06/23/2021

IA-RED^2: Interpretability-Aware Redundancy Reduction for Vision Transformers

The self-attention-based model, transformer, is recently becoming the le...

Bowen Pan, et al. ∙

research

∙ 06/19/2021

Sparse Training via Boosting Pruning Plasticity with Neuroregeneration

Works on lottery ticket hypothesis (LTH) and single-shot network pruning...

Shiwei Liu, et al. ∙

research

∙ 06/18/2021

Federated Robustness Propagation: Sharing Adversarial Robustness in Federated Learning

Federated learning (FL) emerges as a popular distributed learning schema...

Junyuan Hong, et al. ∙

research

∙ 06/10/2021

Sparse and Imperceptible Adversarial Attack via a Homotopy Algorithm

Sparse adversarial attacks can fool deep neural networks (DNNs) by only ...

Mingkang Zhu, et al. ∙

research

∙ 06/09/2021

Practical Machine Learning Safety: A Survey and Primer

The open-world deployment of Machine Learning (ML) algorithms in safety-...

Sina Mohseni, et al. ∙

research

∙ 06/08/2021

Chasing Sparsity in Vision Transformers: An End-to-End Exploration

Vision transformers (ViTs) have recently received explosive popularity, ...

Tianlong Chen, et al. ∙

research

∙ 06/06/2021

Efficient Lottery Ticket Finding: Less Data is More

The lottery ticket hypothesis (LTH) reveals the existence of winning tic...

Zhenyu Zhang, et al. ∙

research

∙ 06/06/2021

Self-Damaging Contrastive Learning

The recent breakthrough achieved by contrastive learning accelerates the...

Ziyu Jiang, et al. ∙

research

∙ 05/16/2021

Undistillable: Making A Nasty Teacher That CANNOT teach students

Knowledge Distillation (KD) is a widely used technique to transfer knowl...

Haoyu Ma, et al. ∙

research

∙ 05/14/2021

Troubleshooting Blind Image Quality Models in the Wild

Recently, the group maximum differentiation competition (gMAD) has been ...

Zhihua Wang, et al. ∙

Zhangyang Wang

Featured Co-authors