Wei Zhu

Evaluation of nucleus segmentation in digital pathology images through large scale image synthesis

2017 · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE

Digital histopathology images with more than 1 Gigapixel are drawing more and more attention in clinical, biomedical research, and computer vision fields. Among the multiple observable features spanning multiple scales in the pathology images, the …

Adversarial Defense via Data Dependent Activation Function and Total Variation Minimization

2018 · arXiv (Cornell University)

We improve the robustness of Deep Neural Net (DNN) to adversarial attacks by using an interpolating function as the output activation. This data-dependent activation remarkably improves both the generalization and robustness of DNN. In the …

MVP-BERT: Redesigning Vocabularies for Chinese BERT and Multi-Vocab Pretraining

2020 · arXiv (Cornell University)

Despite the development of pre-trained language models (PLMs) significantly raise the performances of various Chinese natural language processing (NLP) tasks, the vocabulary for these Chinese PLMs remain to be the one provided by Google Chinese …

Parameter Inversion of High-Dimensional Chaotic Systems Using Neural Ordinary Differential Equations

2024

High-dimensional chaotic systems possess complex structural characteristics, which have potential research value in fields like encrypted communication and chaos control. The inverse problem of parameters in high-dimensional chaotic systems is of significant importance for a …

Improved RIME algorithm: CEC performance analysis and feature selection experiment of Sino foreign cooperative data sets

2025 · Journal Of Big Data

In recent years, with the rapid development of higher education, China has actively constructed an evaluation framework of education quality. As an important part of higher education, Sino foreign cooperation in running schools plays an …