b'Ngai Wong'

research

∙ 06/25/2023

A Spectral Perspective towards Understanding and Improving Adversarial Robustness

Deep neural networks (DNNs) are incredibly vulnerable to crafted, imperc...

0 Binxiao Huang, et al. ∙

research

∙ 06/19/2023

To Fold or Not to Fold: Graph Regularized Tensor Train for Visual Data Completion

Tensor train (TT) representation has achieved tremendous success in visu...

0 Le Xu, et al. ∙

research

∙ 03/27/2023

Context-Aware Transformer for 3D Point Cloud Automatic Annotation

3D automatic annotation has received increased attention since manually ...

0 Xiaoyan Qian, et al. ∙

research

∙ 12/24/2022

Frequency Regularization for Improving Adversarial Robustness

Deep neural networks are incredibly vulnerable to crafted, human-imperce...

0 Binxiao Huang, et al. ∙

research

∙ 10/17/2022

ODG-Q: Robust Quantization via Online Domain Generalization

Quantizing neural networks to low-bitwidth is important for model deploy...

0 Chaofan Tao, et al. ∙

research

∙ 07/20/2022

Multimodal Transformer for Automatic 3D Annotation and Object Detection

Despite a growing number of datasets being collected for training 3D obj...

0 Chang Liu, et al. ∙

research

∙ 05/17/2022

Multilayer Perceptron Based Stress Evolution Analysis under DC Current Stressing for Multi-segment Wires

Electromigration (EM) is one of the major concerns in the reliability an...

7 Tianshu Hou, et al. ∙

research

∙ 03/29/2022

MAP-Gen: An Automated 3D-Box Annotation Flow with Multimodal Attention Point Generator

Manually annotating 3D point clouds is laborious and costly, limiting th...

13 Chang Liu, et al. ∙

research

∙ 03/29/2022

Coarse to Fine: Image Restoration Boosted by Multi-Scale Low-Rank Tensor Completion

Existing low-rank tensor completion (LRTC) approaches aim at restoring a...

0 Rui Lin, et al. ∙

research

∙ 03/25/2022

Deformable Butterfly: A Highly Structured and Sparse Linear Transform

We introduce a new kind of linear transform named Deformable Butterfly (...

0 Rui Lin, et al. ∙

research

∙ 03/16/2022

What Do Adversarially trained Neural Networks Focus: A Fourier Domain-based Study

Although many fields have witnessed the superior performance brought abo...

0 Binxiao Huang, et al. ∙

research

∙ 05/10/2021

Exploiting Elasticity in Tensor Ranks for Compressing Neural Networks

Elasticities in depth, width, kernel size and resolution have been explo...

0 Jie Ran, et al. ∙

research

∙ 05/08/2021

EZCrop: Energy-Zoned Channels for Robust Output Pruning

Recent results have revealed an interesting observation in a trained con...

0 Rui Lin, et al. ∙

research

∙ 03/22/2021

AET-EFN: A Versatile Design for Static and Dynamic Event-Based Vision

The neuromorphic event cameras, which capture the optical changes of a s...

0 Chang Liu, et al. ∙

research

∙ 02/15/2021

FAT: Learning Low-Bitwidth Parametric Representation via Frequency-Aware Transformation

Learning convolutional neural networks (CNNs) with low bitwidth is chall...

0 Chaofan Tao, et al. ∙

research

∙ 11/04/2020

S3-Net: A Fast and Lightweight Video Scene Understanding Network by Single-shot Segmentation

Real-time understanding in video is crucial in various AI applications s...

18 Yuan Cheng, et al. ∙

research

∙ 02/28/2020

HOTCAKE: Higher Order Tucker Articulated Kernels for Deeper CNN Compression

The emerging edge computing has promoted immense interests in compacting...

5 Rui Lin, et al. ∙

research

∙ 01/02/2020

Kernelized Support Tensor Train Machines

Tensor, a multi-dimensional data structure, has been exploited recently ...

15 Cong Chen, et al. ∙

research

∙ 12/20/2019

MERACLE: Constructive layer-wise conversion of a Tensor Train into a MERA

In this article two new algorithms are presented that convert a given da...

0 Kim Batselier, et al. ∙

research

∙ 12/02/2019

Fastened CROWN: Tightened Neural Network Robustness Certificates

The rapid growth of deep learning applications in real life is accompani...

0 Zhaoyang Lyu, et al. ∙

research

∙ 05/17/2019

MiSC: Mixed Strategies Crowdsourcing

Popular crowdsourcing techniques mostly focus on evaluating workers' lab...

0 Ching-Yun Ko, et al. ∙

research

∙ 05/17/2019

POPQORN: Quantifying Robustness of Recurrent Neural Networks

The vulnerability to adversarial attacks has been a critical issue for d...

0 Ching-Yun Ko, et al. ∙

research

∙ 11/12/2018

Matrix Product Operator Restricted Boltzmann Machines

A restricted Boltzmann machine (RBM) learns a probability distribution o...

22 Cong Chen, et al. ∙

research

∙ 11/09/2018

Deep Compression of Sum-Product Networks on Tensor Networks

Sum-product networks (SPNs) represent an emerging class of neural networ...

0 Ching-Yun Ko, et al. ∙

research

∙ 04/17/2018

Fast and Accurate Tensor Completion with Total Variation Regularized Tensor Trains

We propose a new tensor completion method based on tensor trains. The to...

0 Ching-Yun Ko, et al. ∙

research

∙ 04/17/2018

Fast and Accurate Tensor Completion with Tensor Trains: A System Identification Approach

We propose a novel tensor completion approach by equating it to a system...

0 Ching-Yun Ko, et al. ∙

research

∙ 04/17/2018

A Support Tensor Train Machine

There has been growing interest in extending traditional vector-based ma...

0 Cong Chen, et al. ∙

research

∙ 07/25/2017

Computing low-rank approximations of large-scale matrices with the Tensor Network randomized SVD

We propose a new algorithm for the computation of a singular value decom...

0 Kim Batselier, et al. ∙

research

∙ 12/20/2016

Parallelized Tensor Train Learning of Polynomial Classifiers

In pattern classification, polynomial classifiers are well-studied metho...

0 Zhongming Chen, et al. ∙

Ngai Wong

Featured Co-authors