1 code implementation • 9 Sep 2020 • Ke Zhang, Yukun Su, Xiwang Guo, Liang Qi, Zhenbing Zhao
Facial attribute editing has mainly two objectives: 1) translating image from a source domain to a target one, and 2) only changing the facial regions related to a target attribute and preserving the attribute-excluding details.
no code implementations • 17 Jan 2020 • Zhenbing Zhao, Hongyu Qi, Yincheng Qi, Ke Zhang, Yongjie Zhai, Wenqing Zhao
In this paper, an automatic detection model called Automatic Visual Shape Clustering Network (AVSCNet) for pin-missing defect is constructed.
1 code implementation • 25 Dec 2019 • Ke Zhang, Yurong Guo, Xinsheng Wang, Dongliang Chang, Zhenbing Zhao, Zhanyu Ma, Tony X. Han
However, during the training of the deep convolutional neural network, the value of NLLR is not always positive or negative, which severely affects the convergence of NLLR.
no code implementations • 31 Jul 2019 • Ke Zhang, Xinsheng Wang, Yurong Guo, Zhenbing Zhao, Zhanyu Ma, Tony X. Han
A lot of studies of image classification based on deep convolutional neural network focus on the network structure to improve the image classification performance.
no code implementations • 26 May 2018 • Ke Zhang, Na Liu, Xingfang Yuan, Xinyao Guo, Ce Gao, Zhenbing Zhao, Zhanyu Ma
Then, we fine-tune the ResNets or the RoR on the target age datasets to extract the global features of face images.
Ranked #4 on Age And Gender Classification on Adience Age (using extra training data)
no code implementations • 9 Oct 2017 • Ke Zhang, Ce Gao, Liru Guo, Miao Sun, Xingfang Yuan, Tony X. Han, Zhenbing Zhao, Baogang Li
In this paper, we propose a new CNN based method for age group and gender estimation leveraging Residual Networks of Residual Networks (RoR), which exhibits better optimization ability for age group and gender classification than other CNN architectures. Moreover, two modest mechanisms based on observation of the characteristics of age group are presented to further improve the performance of age estimation. In order to further improve the performance and alleviate over-fitting problem, RoR model is pre-trained on ImageNet firstly, and then it is fune-tuned on the IMDB-WIKI-101 data set for further learning the features of face images, finally, it is used to fine-tune on Adience data set.
Ranked #6 on Age And Gender Classification on Adience Age (using extra training data)
no code implementations • 1 Oct 2017 • Ke Zhang, Liru Guo, Ce Gao, Zhenbing Zhao
The Residual Networks of Residual Networks (RoR) exhibits excellent performance in the image classification task, but sharply increasing the number of feature map channels makes the characteristic information transmission incoherent, which losses a certain of information related to classification prediction, limiting the classification performance.