arXiv subjects

Xiaofeng Zhu

Publications and source records attributed to Xiaofeng Zhu.

78 records · Page 5Linked to original sources

arXiv2020

Frosting Weights for Better Continual Training

Training a neural network model can be a lifelong learning process and is a computationally intensive one. A severe adverse effect that may occur in deep neural network models is that they can suffer from catastrophic forgetting during retraining on new data. To avoid such disruptions in the continuous learning, one appealing property is the additive nature of ensemble models. In this paper, we propose two generic ensemble approaches, gradient boosting and meta-learning, to solve the catastrophic forgetting problem in tuning pre-trained neural network models.

cs.LG↗

arXiv2019

High dynamic range image forensics using cnn

High dynamic range (HDR) imaging has recently drawn much attention in multimedia community. In this paper, we proposed a HDR image forensics method based on convolutional neural network (CNN).To our best knowledge, this is the first time to apply deep learning method on HDR image forensics. The proposed algorithm uses CNN to distinguish HDR images generated by multiple low dynamic range (LDR) images from that expanded by single LDR image using inverse tone mapping (iTM). To do this, we learn the change of statistical characteristics extracted by the proposed CNN architectures and classify two kinds of HDR images. Comparision results with some traditional statistical characteristics shows efficiency of the proposed method in HDR image source identification.

cs.CV↗

arXiv2018

Identification of multi-scale hierarchical brain functional networks using deep matrix factorization

We present a deep semi-nonnegative matrix factorization method for identifying subject-specific functional networks (FNs) at multiple spatial scales with a hierarchical organization from resting state fMRI data. Our method is built upon a deep semi-nonnegative matrix factorization framework to jointly detect the FNs at multiple scales with a hierarchical organization, enhanced by group sparsity regularization that helps identify subject-specific FNs without loss of inter-subject comparability. The proposed method has been validated for predicting subject-specific functional activations based on functional connectivity measures of the hierarchical multi-scale FNs of the same subjects. Experimental results have demonstrated that our method could obtain subject-specific multi-scale hierarchical FNs and their functional connectivity measures across different scales could better predict subject-specific functional activations than those obtained by alternative techniques.

cs.CV↗

arXiv2017

Semantic Document Distance Measures and Unsupervised Document Revision Detection

In this paper, we model the document revision detection problem as a minimum cost branching problem that relies on computing document distances. Furthermore, we propose two new document distance measures, word vector-based Dynamic Time Warping (wDTW) and word vector-based Tree Edit Distance (wTED). Our revision detection system is designed for a large scale corpus and implemented in Apache Spark. We demonstrate that our system can more precisely detect revisions than state-of-the-art methods by utilizing the Wikipedia revision dumps https://snap.stanford.edu/data/wiki-meta.html and simulated data sets.

cs.IR↗

arXiv2017

Unsupervised Terminological Ontology Learning based on Hierarchical Topic Modeling

In this paper, we present hierarchical relationbased latent Dirichlet allocation (hrLDA), a data-driven hierarchical topic model for extracting terminological ontologies from a large number of heterogeneous documents. In contrast to traditional topic models, hrLDA relies on noun phrases instead of unigrams, considers syntax and document structures, and enriches topic hierarchies with topic relations. Through a series of experiments, we demonstrate the superiority of hrLDA over existing topic models, especially for building hierarchies. Furthermore, we illustrate the robustness of hrLDA in the settings of noisy data sets, which are likely to occur in many practical scenarios. Our ontology evaluation results show that ontologies extracted from hrLDA are very competitive with the ontologies created by domain experts.

cs.CL↗

arXiv2013

Exchange-dominated Standing Spin Wave Excitations under microwave irradiation in Ni80Fe20 Thin Films

We investigated the microwave-assisted DC voltages of ferromagnetic resonances and exchangedominated standing spin wave excitations in two different in-plane magnetized permalloy thin films via homodyne detection. The line shapes of ferromagnetic resonance spectra and the dispersion curves of ferromagnetic resonance and standing spin wave are in agreement of previous studies, while further investigations of DC voltage spectra for these two excitations reveal that 1. unlike ferromagnetic resonance signals, the anti-symmetrical line shapes of standing spin wave excitations are not depend on the electromagnetic relative phase of assisted microwave, and 2. linewidths of their DC voltage spectra are distinct. The complicated spin dynamics of standing spin wave is consequently discussed by applying Landau-Lifshitz-Gilbert equation in term of exchange interaction.

cond-mat.mtrl-sci↗