Richard Zhang

Richard Zhang

Auto-generated profile, based on publicly available information

Richard Zhang

Adobe Research

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
23 July 2023
Verified
Conference Paper
Open access
GPGaurav Parmar
Gaurav Parmar
KSKrishna Kumar Singh
Krishna Kumar Singh
RZRichard Zhang
Richard Zhang
YLYijun Li
Yijun Li
JLJingwan Lu
Jingwan Lu
JZJun-Yan Zhu
Jun-Yan Zhu

26 October 2024
Verified
Book Chapter
Closed access
PDF file
ZWZongze Wu
Zongze Wu
NKNicholas Kolkin
Nicholas Kolkin
JBJonathan Brandt
Jonathan Brandt
RZRichard Zhang
Richard Zhang
ESEli Shechtman
Eli Shechtman

3 December 2024
Verified
Conference Paper
Open access
NKNupur Kumari
Nupur Kumari
GSGrace Su
Grace Su
RZRichard Zhang
Richard Zhang
TPTaesung Park
Taesung Park
ESEli Shechtman
Eli Shechtman
JZJun-Yan Zhu
Jun-Yan Zhu

31 October 2022
Verified
Book Chapter
Closed access
PDF file
YLYuchen Liu
Yuchen Liu
ZSZhixin Shu
Zhixin Shu
YLYijun Li
Yijun Li
ZLZhe Lin
Zhe Lin
RZRichard Zhang
Richard Zhang
SKS. Y. Kung
S. Y. Kung

3 November 2024
Verified
Book Chapter
Closed access
PDF file
YNYotam Nitzan
Yotam Nitzan
ZWZongze Wu
Zongze Wu
RZRichard Zhang
Richard Zhang
ESEli Shechtman
Eli Shechtman
DCDaniel Cohen-Or
Daniel Cohen-Or
MGMichaël Gharbi
Michaël Gharbi

9 June 2019 in arXiv
Verified
Preprint
Open access
PDF file
RZRichard Zhang
Richard Zhang
Modern convolutional networks are not shift-invariant, as small input shifts or translations can cause drastic changes in the output. Commonly used downsampling methods, such as max-pooling, strided-convolution, and average-pooling, ignore the sampling theorem. The well-known signal processing fix is anti-aliasing by low-pass filtering before downsampling. However, simply inserting this module into deep networks degrades performance; as a result, it is seldomly used today. We show that when integrated correctly, it is compatible with existing architectural components, such as max-pooling and strided-convolution. We observe \textit{increased accuracy} in ImageNet classification, across several commonly-used architectures, such as ResNet, DenseNet, and MobileNet, indicating effective regularization. Furthermore, we observe \textit{better generalization}, in terms of stability and robustness to input corruptions. Our results demonstrate that this classical signal processing technique has been undeservingly overlooked in modern deep networks. Code and anti-aliased versions of popular networks are available at https://richzhang.github.io/antialiased-cnns/ .