arXiv subjects

Hui Ding

Publications and source records attributed to Hui Ding.

23 records · Page 2Linked to original sources

arXiv2017

Semi-supervised Conditional GANs

We introduce a new model for building conditional generative models in a semi-supervised setting to conditionally generate data given attributes by adapting the GAN framework. The proposed semi-supervised GAN (SS-GAN) model uses a pair of stacked discriminators to learn the marginal distribution of the data, and the conditional distribution of the attributes given the data respectively. In the semi-supervised setting, the marginal distribution (which is often harder to learn) is learned from the labeled + unlabeled data, and the conditional distribution is learned purely from the labeled data. Our experimental results demonstrate that this model performs significantly better compared to existing semi-supervised conditional GAN models.

stat.ML↗

arXiv2016

FaceNet2ExpNet: Regularizing a Deep Face Recognition Net for Expression Recognition

Relatively small data sets available for expression recognition research make the training of deep networks for expression recognition very challenging. Although fine-tuning can partially alleviate the issue, the performance is still below acceptable levels as the deep features probably contain redun- dant information from the pre-trained domain. In this paper, we present FaceNet2ExpNet, a novel idea to train an expression recognition network based on static images. We first propose a new distribution function to model the high-level neurons of the expression network. Based on this, a two-stage training algorithm is carefully designed. In the pre-training stage, we train the convolutional layers of the expression net, regularized by the face net; In the refining stage, we append fully- connected layers to the pre-trained convolutional layers and train the whole network jointly. Visualization shows that the model trained with our method captures improved high-level expression semantics. Evaluations on four public expression databases, CK+, Oulu-CASIA, TFD, and SFEW demonstrate that our method achieves better results than state-of-the-art.

cs.CV↗

arXiv2012

Domain tuning in mixed-phase BiFeO3 thin films using vicinal substrates

The structural and ferroelectric domain variants of highly-strained BiFeO3 films grown on vicinal LaSrAlO4 substrates were studied by piezoelectric force microscopy and high-resolution X-ray reciprocal space mapping. Through symmetry breaking of the substrate surface, ferroelastic domain variants in the highly-strained MC phase BiFeO3 can be greatly reduced. Single-domain film can be obtained on substrates with large miscut angle, which is accompanied by the reduction of structural variants in the mixed-phase nanodomains. These findings lead to better understanding of the phase evolution and polarization rotation process in the strain-driven morphotropic phase system.

cond-mat.mtrl-sci↗

arXiv2012

Characterization and manipulation of mixed phase domains in highly-strained BiFeO3 thin films

The novel strain-driven morphotropic phase boundary (MPB) in highly-strained BiFeO3 thin film is featured by ordered mixed phase nanodomains (MPNs). Through scanning probe microscopy and synchrotron X-ray diffraction, eight structural variants of the MPNs are identified. Detailed polarization configurations within the MPNs are resolved using angular-dependent piezoelectric force microscopy. Guided by the obtained results, deterministic manipulation of the MPNs has been demonstrated by controlling the motion of the local probe. These findings are important for in-depth understanding of the ultrahigh electromechanical response arising from phase transformation between competing phases, enabling future explorations on the electronic structure, magnetoelectricity and other functionalities in this new MPB system.

cond-mat.mtrl-sci↗

arXiv2010

Experimental Comparison of Representation Methods and Distance Measures for Time Series Data

The previous decade has brought a remarkable increase of the interest in applications that deal with querying and mining of time series data. Many of the research efforts in this context have focused on introducing new representation methods for dimensionality reduction or novel similarity measures for the underlying data. In the vast majority of cases, each individual work introducing a particular method has made specific claims and, aside from the occasional theoretical justifications, provided quantitative experimental observations. However, for the most part, the comparative aspects of these experiments were too narrowly focused on demonstrating the benefits of the proposed methods over some of the previously introduced ones. In order to provide a comprehensive validation, we conducted an extensive experimental study re-implementing eight different time series representations and nine similarity measures and their variants, and testing their effectiveness on thirty-eight time series data sets from a wide variety of application domains. In this paper, we give an overview of these different techniques and present our comparative experimental findings regarding their effectiveness. In addition to providing a unified validation of some of the existing achievements, our experiments also indicate that, in some cases, certain claims in the literature may be unduly optimistic.

cs.AI↗