activity
20172021
most citedAirCode: Unobtrusive Physical Tags for Digital Fabrication

62 citations · 62 across the 3 of their papers we have counts for

collaborators

11 papers

cs.CV2021

DeepCAD: A Deep Generative Network for Computer-Aided Design Models

Rundi Wu, Chang Xiao, Changxi Zheng

Deep generative models of 3D shapes have received a great deal of research interest. Yet, almost all of them generate discrete shape representations, such as voxels, point clouds,…

cs.CV2021

Linear Semantics in Generative Adversarial Networks

Jianjin Xu, Changxi Zheng

Generative Adversarial Networks (GANs) are able to generate high-quality images, but it remains difficult to explicitly specify the semantics of synthesized images. In this work, w…

cs.SD2020

Listening to Sounds of Silence for Speech Denoising

Ruilin Xu, Rundi Wu, Yuko Ishiwaka +2

We introduce a deep learning model for speech denoising, a long-standing challenge in audio analysis arising in numerous applications. Our approach is based on a key observation ab…

physics.optics2020

Differentiable Scattering Matrix for Optimization of Photonic Structures

Ziwei Zhu, Changxi Zheng

The scattering matrix, which quantifies the optical reflection and transmission of a photonic structure, is pivotal for understanding the performance of the structure. In many phot…

cs.LG2019

One Man's Trash is Another Man's Treasure: Resisting Adversarial Examples by Adversarial Examples

Chang Xiao, Changxi Zheng

Modern image classification systems are often built on deep neural networks, which suffer from adversarial examples--images with deliberately crafted, imperceptible noise to mislea…

cs.LG2019

Enhancing Adversarial Defense by k-Winners-Take-All

Chang Xiao, Peilin Zhong, Changxi Zheng

We propose a simple change to existing neural network structures for better defending against gradient-based adversarial attacks. Instead of using popular activation functions (suc…