R
Rentuo Tao
Researcher at University of Science and Technology of China
Publications - 22
Citations - 56
Rentuo Tao is an academic researcher from University of Science and Technology of China. The author has contributed to research in topics: Normalization (statistics) & Segmentation. The author has an hindex of 2, co-authored 16 publications receiving 29 citations.
Papers
More filters
Journal ArticleDOI
ResAttr-GAN: Unpaired Deep Residual Attributes Learning for Multi-Domain Face Image Translation
TL;DR: A Siamese-Network based residual attributes learning model to learn the attributes difference in the high-level latent space and can improve data utilization efficiency and thus can boost the editing performance when the train data was limited.
Journal ArticleDOI
Interpreting the Latent Space of GANs via Measuring Decoupling
TL;DR: Two methods to measure the sensitivity of latent dimensions are proposed: one is a sequential intervention method, and the other is an optimization-based method that measures the sensitivity in both the value and the direction.
Posted Content
DA-RefineNet:A Dual Input Whole Slide Image Segmentation Algorithm Based on Attention.
TL;DR: A dual input semantic segmentation network based on attention is proposed, in which, one input provides small-scale fine information, the other input provides large-scale coarse information, and exhibits a dramatic performance improvement on ICIAR2018 breast cancer segmentation task.
Posted Content
Regularization And Normalization For Generative Adversarial Networks: A Review
Ziqiang Li,Rentuo Tao,Bin Li +2 more
TL;DR: This paper reviews and summarizes the research in the regularization and normalization for GAN, and classifies the methods into six groups: Gradient penalty, Norm normalization and regularization, Jacobian regularized, Layer normalization, Consistency regularizations, and Self-supervision.
Proceedings ArticleDOI
SAR image retrieval based-on fly algorithm
Kai Zhang,Bin Li,Rentuo Tao +2 more
TL;DR: Three computational strategies extracted from the logic of an important sensory function are used in the fly algorithm to improve the performance of computational similarity searches and another effective binary quantization method is adopted to generate binary hash code in SAR image retrieval system.