13 citations · 23 across the 12 of their papers we have counts for
5 papers · 1 filter
UniTable: Towards a Unified Framework for Table Recognition via Self-Supervised Pretraining
ShengYun Peng, Aishwarya Chakravarthy, Seongmin Lee +3
Tables convey factual and quantitative data with implicit conventions created by humans that are often challenging for machines to parse. Prior work on table recognition (TR) has m…
Self-Supervised Pre-Training for Table Structure Recognition Transformer
ShengYun Peng, Seongmin Lee, Xiaojing Wang +2
Table structure recognition (TSR) aims to convert tabular images into a machine-readable format. Although hybrid convolutional neural network (CNN)-transformer architecture is wide…
High-Performance Transformers for Table Structure Recognition Need Early Convolutions
ShengYun Peng, Seongmin Lee, Xiaojing Wang +2
Table structure recognition (TSR) aims to convert tabular images into a machine-readable format, where a visual encoder extracts image features and a textual decoder generates tabl…
Robust Principles: Architectural Design Principles for Adversarially Robust CNNs
ShengYun Peng, Weilin Xu, Cory Cornelius +6
Our research aims to unify existing works' diverging opinions on how architectural components affect the adversarial robustness of CNNs. To accomplish our goal, we synthesize a sui…
RobArch: Designing Robust Architectures against Adversarial Attacks
ShengYun Peng, Weilin Xu, Cory Cornelius +4
Adversarial Training is the most effective approach for improving the robustness of Deep Neural Networks (DNNs). However, compared to the large body of research in optimizing the a…