Z
Zhuo Su
Researcher at University of Oulu
Publications - 19
Citations - 337
Zhuo Su is an academic researcher from University of Oulu. The author has contributed to research in topics: Computer science & Convolutional neural network. The author has an hindex of 4, co-authored 13 publications receiving 98 citations.
Papers
More filters
Proceedings ArticleDOI
Searching Central Difference Convolutional Networks for Face Anti-Spoofing
TL;DR: Yu et al. as discussed by the authors proposed a frame level FAS method based on Central Difference Convolution (CDC), which is able to capture intrinsic detailed patterns via aggregating both intensity and gradient information.
Book ChapterDOI
Dynamic Group Convolution for Accelerating Convolutional Neural Networks.
TL;DR: Zhuo et al. as mentioned in this paper proposed dynamic group convolution (DGC) that adaptively selects which part of input channels to be connected within each group for individual samples on the fly.
Posted Content
Dynamic Group Convolution for Accelerating Convolutional Neural Networks
TL;DR: This paper proposes dynamic group convolution (DGC) that adaptively selects which part of input channels to be connected within each group for individual samples on the fly, and has similar computational efficiency as the conventional group Convolution simultaneously.
Proceedings Article
BIRD: Learning Binary and Illumination Robust Descriptor for Face Recognition.
Zhuo Su,Matti Pietikäinen,Li Liu +2 more
TL;DR: The proposed BIRD is shown to be highly robust to illumination changes, and produces 89.5% on the CAS_PEAL_R1 illumination subset, which, it is believed, is so far the best reported results on this dataset.
Journal ArticleDOI
Deep Ladder Reconstruction-Classification Network for Unsupervised Domain Adaptation
Wanxia Deng,Zhuo Su,Qiang Qiu,Lingjun Zhao,Gangyao Kuang,Matti Pietikäinen,Huaxin Xiao,Li Liu,Li Liu +8 more
TL;DR: Deep Ladder Reconstruction-Classification Network (DLaReC) as mentioned in this paper adopts an encoder with cross-domain sharing and a target-domain reconstruction decoder, which is designed to learn crossdomain shared contents by suppressing domain-specific variations.