Search Results for author: Pan Zhang

Found 32 papers, 14 papers with code

Real-Time Neural Character Rendering with Pose-Guided Multiplane Images

no code implementations25 Apr 2022 Hao Ouyang, Bo Zhang, Pan Zhang, Hao Yang, Jiaolong Yang, Dong Chen, Qifeng Chen, Fang Wen

We propose pose-guided multiplane image (MPI) synthesis which can render an animatable character in real scenes with photorealistic quality.

Image-to-Image Translation Novel View Synthesis

Semi-Supervised Image-to-Image Translation using Latent Space Mapping

no code implementations29 Mar 2022 Pan Zhang, Jianmin Bao, Ting Zhang, Dong Chen, Fang Wen

Thanks to the low dimensional feature space, it is easier to find the desired mapping function, resulting in improved quality of translation results as well as the stability of the translation model.

Image-to-Image Translation Translation

Tensor networks for unsupervised machine learning

1 code implementation24 Jun 2021 Jing Liu, Sujie Li, Jiang Zhang, Pan Zhang

Modeling the joint distribution of high-dimensional data is a central task in unsupervised machine learning.

Tensor Networks

Robust Mutual Learning for Semi-supervised Semantic Segmentation

no code implementations1 Jun 2021 Pan Zhang, Bo Zhang, Ting Zhang, Dong Chen, Fang Wen

The proposed robust mutual learning demonstrates state-of-the-art performance on semantic segmentation in low-data regime.

Semi-Supervised Semantic Segmentation

Boltzmann machines as two-dimensional tensor networks

no code implementations10 May 2021 Sujie Li, Feng Pan, Pengfei Zhou, Pan Zhang

Using numerical experiments, we demonstrate that the proposed algorithm is much more accurate than the state-of-the-art machine learning methods in estimating the partition function of restricted Boltzmann machines and deep Boltzmann machines, and have potential applications in training deep Boltzmann machines for general machine learning tasks.

Tensor Networks

Old Photo Restoration via Deep Latent Space Translation

6 code implementations14 Sep 2020 Zi-Yu Wan, Bo Zhang, Dong-Dong Chen, Pan Zhang, Dong Chen, Jing Liao, Fang Wen

Unlike conventional restoration tasks that can be solved through supervised learning, the degradation in real photos is complex and the domain gap between synthetic images and real old photos makes the network fail to generalize.

Image Restoration Translation

Supervised Learning with Projected Entangled Pair States

no code implementations12 Sep 2020 Song Cheng, Lei Wang, Pan Zhang

Tensor networks, a model that originated from quantum physics, has been gradually generalized as efficient models in machine learning in recent years.

Tensor Networks

Contact Area Detector using Cross View Projection Consistency for COVID-19 Projects

no code implementations18 Aug 2020 Pan Zhang, Wilfredo Torres Calderon, Bokyung Lee, Alex Tessier, Jacky Bibliowicz, Liviu Calin, Michael Lee

Instead of doing 3D scene reconstruction or transfer learning from deep networks, a mapping from the surface in the two camera views to the surface space is the only requirement.

3D Reconstruction 3D Scene Reconstruction +1

Tropical Tensor Network for Ground States of Spin Glasses

1 code implementation16 Aug 2020 Jin-Guo Liu, Lei Wang, Pan Zhang

We present a unified exact tensor network approach to compute the ground state energy, identify the optimal configuration, and count the number of solutions for spin glasses.

Statistical Mechanics Quantum Physics Computation

Bringing Old Photos Back to Life

6 code implementations CVPR 2020 Zi-Yu Wan, Bo Zhang, Dong-Dong Chen, Pan Zhang, Dong Chen, Jing Liao, Fang Wen

Unlike conventional restoration tasks that can be solved through supervised learning, the degradation in real photos is complex and the domain gap between synthetic images and real old photos makes the network fail to generalize.

Image Restoration Translation

Solving Quantum Statistical Mechanics with Variational Autoregressive Networks and Quantum Circuits

1 code implementation24 Dec 2019 Jin-Guo Liu, Liang Mao, Pan Zhang, Lei Wang

We extend the ability of unitary quantum circuits by interfacing it with classical autoregressive neural networks.

Quantum Physics

Yao.jl: Extensible, Efficient Framework for Quantum Algorithm Design

1 code implementation23 Dec 2019 Xiu-Zhe Luo, Jin-Guo Liu, Pan Zhang, Lei Wang

We introduce Yao, an extensible, efficient open-source framework for quantum algorithm design.

Quantum Physics Strongly Correlated Electrons Computational Physics

Contracting Arbitrary Tensor Networks: general approximate algorithm and applications in graphical models and quantum circuit simulations

1 code implementation6 Dec 2019 Feng Pan, Pengfei Zhou, Sujie Li, Pan Zhang

We present a general method for approximately contracting tensor networks with an arbitrary connectivity.

Computational Physics Statistical Mechanics Strongly Correlated Electrons Quantum Physics

Phase transitions and optimal algorithms for semi-supervised classifications on graphs: from belief propagation to graph convolution network

no code implementations1 Nov 2019 Pengfei Zhou, Tianyi Li, Pan Zhang

For the first time, well-controlled benchmark datasets with asymptotially exact properties and optimal solutions could be produced for the evaluation of graph convolution neural networks, and for the theoretical understanding of their strengths and weaknesses.

Bayesian Inference General Classification +1

A streaming feature-based compression method for data from instrumented infrastructure

no code implementations12 Apr 2019 Alastair Gregory, Din-Houn Lau, Alex Tessier, Pan Zhang

An increasing amount of civil engineering applications are utilising data acquired from infrastructure instrumented with sensing devices.

Tree Tensor Networks for Generative Modeling

no code implementations8 Jan 2019 Song Cheng, Lei Wang, Tao Xiang, Pan Zhang

Matrix product states (MPS), a tensor network designed for one-dimensional quantum systems, has been recently proposed for generative modeling of natural data (such as images) in terms of `Born machine'.

Tensor Networks

Shortcut Matrix Product States and its applications

no code implementations13 Dec 2018 Zhuan Li, Pan Zhang

Matrix Product States (MPS), also known as Tensor Train (TT) decomposition in mathematics, has been proposed originally for describing an (especially one-dimensional) quantum system, and recently has found applications in various applications such as compressing high-dimensional data, supervised kernel linear classifier, and unsupervised generative modeling.

Solving Statistical Mechanics Using Variational Autoregressive Networks

2 code implementations27 Sep 2018 Dian Wu, Lei Wang, Pan Zhang

We propose a general framework for solving statistical mechanics of systems with finite size.


Weighted Community Detection and Data Clustering Using Message Passing

no code implementations30 Jan 2018 Cheng Shi, Yanchen Liu, Pan Zhang

In the community detection problem in weighted and directed networks, we show that our algorithm significantly outperforms existing algorithms.

Bayesian Inference Community Detection

Spectral estimation of the percolation transition in clustered networks

no code implementations4 Oct 2017 Pan Zhang

There have been several spectral bounds for the percolation transition in networks, using spectrum of matrices associated with the network such as the adjacency matrix and the non-backtracking matrix.

Unsupervised Generative Modeling Using Matrix Product States

1 code implementation6 Sep 2017 Zhao-Yu Han, Jun Wang, Heng Fan, Lei Wang, Pan Zhang

Generative modeling, which learns joint probability distribution from data and generates samples according to it, is an important task in machine learning and artificial intelligence.

Evaluating accuracy of community detection using the relative normalized mutual information

no code implementations15 Jan 2015 Pan Zhang

The Normalized Mutual Information (NMI) has been widely used to evaluate the accuracy of community detection algorithms.

Community Detection

Phase transitions in semisupervised clustering of sparse networks

no code implementations30 Apr 2014 Pan Zhang, Cristopher Moore, Lenka Zdeborová

For larger $k$ where a hard but detectable regime exists, we find that the easy/hard transition (the point at which efficient algorithms can do better than chance) becomes a line of transitions where the accuracy jumps discontinuously at a critical value of $\alpha$.

Stochastic Block Model

Scalable detection of statistically significant communities and hierarchies, using message-passing for modularity

1 code implementation23 Mar 2014 Pan Zhang, Cristopher Moore

We address this problem by using the modularity as a Hamiltonian at finite temperature, and using an efficient Belief Propagation algorithm to obtain the consensus of many partitions with high modularity, rather than looking for a single partition that maximizes it.

Stochastic Block Model

Model Selection for Degree-corrected Block Models

no code implementations17 Jul 2012 Xiaoran Yan, Cosma Rohilla Shalizi, Jacob E. Jensen, Florent Krzakala, Cristopher Moore, Lenka Zdeborova, Pan Zhang, Yaojia Zhu

We present the first principled and tractable approach to model selection between standard and degree-corrected block models, based on new large-graph asymptotics for the distribution of log-likelihood ratios under the stochastic block model, finding substantial departures from classical results for sparse graphs.

Model Selection Stochastic Block Model

Cannot find the paper you are looking for? You can Submit a new open access paper.