325 Hits in 0.79 sec

Surface Reconstruction with Data-driven Exemplar Priors [article]

Oussama Remil, Qian Xie, Xingyu Xie, Kai Xu, Jun Wang
2017 arXiv   pre-print
In this paper, we propose a framework to reconstruct 3D models from raw scanned points by learning the prior knowledge of a specific class of objects. Unlike previous work that heuristically specifies particular regularities and defines parametric models, our shape priors are learned directly from existing 3D models under a framework based on affinity propagation. Given a database of 3D models within the same class of objects, we build a comprehensive library of 3D local shape priors. We then
more » ... rmulate the problem to select as-few-as-possible priors from the library, referred to as exemplar priors. These priors are sufficient to represent the 3D shapes of the whole class of objects from where they are generated. By manipulating these priors, we are able to reconstruct geometrically faithful models with the same class of objects from raw point clouds. Our framework can be easily generalized to reconstruct various categories of 3D objects that have more geometrically or topologically complex structures. Comprehensive experiments exhibit the power of our exemplar priors for gracefully solving several problems in 3D shape reconstruction such as preserving sharp features, recovering fine details and so on.
arXiv:1701.03230v1 fatcat:qv23qbb46vchvnpp6uqaqw4smm

Differentiable Linearized ADMM [article]

Xingyu Xie, Jianlong Wu, Zhisheng Zhong, Guangcan Liu, Zhouchen Lin
2019 arXiv   pre-print
In Proceedings of the AAAI Conference on Artificial Intelligence, 2018.Xingyu Xie * 1 Jianlong Wu * 1 Zhisheng Zhong 1 Guangcan Liu 2 Zhouchen Lin 1 Differentiable Linearized ADMM (Supplementary Material  ... 
arXiv:1905.06179v1 fatcat:upuwu2zsijam3ic3lti6qdhfmq

Maximum-and-Concatenation Networks [article]

Xingyu Xie, Hao Kong, Jianlong Wu, Wayne Zhang, Guangcan Liu, Zhouchen Lin
2020 arXiv   pre-print
This is not in conflict with the learning-based optimization theories(Xie et al., 2019; Liu et al., 2019), which show that their networks can converge fast and need only a smaller number of layers to solve  ... 
arXiv:2007.04630v1 fatcat:3yitm2jlenddxmwvuaquvexrle

Matrix Recovery with Implicitly Low-Rank Data [article]

Xingyu Xie, Jianlong Wu, Guangcan Liu, Jun Wang
2018 arXiv   pre-print
In this paper, we study the problem of matrix recovery, which aims to restore a target matrix of authentic samples from grossly corrupted observations. Most of the existing methods, such as the well-known Robust Principal Component Analysis (RPCA), assume that the target matrix we wish to recover is low-rank. However, the underlying data structure is often non-linear in practice, therefore the low-rankness assumption could be violated. To tackle this issue, we propose a novel method for matrix
more » ... ecovery in this paper, which could well handle the case where the target matrix is low-rank in an implicit feature space but high-rank or even full-rank in its original form. Namely, our method pursues the low-rank structure of the target matrix in an implicit feature space. By making use of the specifics of an accelerated proximal gradient based optimization algorithm, the proposed method could recover the target matrix with non-linear structures from its corrupted version. Comprehensive experiments on both synthetic and real datasets demonstrate the superiority of our method.
arXiv:1811.03945v1 fatcat:unxcilrdfna4ng6o6oz2dr3ssy

AlphaGomoku: An AlphaGo-based Gomoku Artificial Intelligence using Curriculum Learning [article]

Zheng Xie, XingYu Fu, JinYuan Yu
2018 arXiv   pre-print
In this project, we combine AlphaGo algorithm with Curriculum Learning to crack the game of Gomoku. Modifications like Double Networks Mechanism and Winning Value Decay are implemented to solve the intrinsic asymmetry and short-sight of Gomoku. Our final AI AlphaGomoku, through two days' training on a single GPU, has reached humans' playing level.
arXiv:1809.10595v1 fatcat:xgewq2oh6jhk5ftfvjh2kz4phu

Global Convergence of Over-parameterized Deep Equilibrium Models [article]

Zenan Ling, Xingyu Xie, Qiuhao Wang, Zongpeng Zhang, Zhouchen Lin
2022 arXiv   pre-print
A deep equilibrium model (DEQ) is implicitly defined through an equilibrium point of an infinite-depth weight-tied model with an input-injection. Instead of infinite computations, it solves an equilibrium point directly with root-finding and computes gradients with implicit differentiation. The training dynamics of over-parameterized DEQs are investigated in this study. By supposing a condition on the initial equilibrium point, we show that the unique equilibrium point always exists during the
more » ... raining process, and the gradient descent is proved to converge to a globally optimal solution at a linear convergence rate for the quadratic loss function. In order to show that the required initial condition is satisfied via mild over-parameterization, we perform a fine-grained analysis on random DEQs. We propose a novel probabilistic framework to overcome the technical difficulty in the non-asymptotic analysis of infinite-depth weight-tied models.
arXiv:2205.13814v1 fatcat:yvqtrkdplbg4pcrq6yrvi4yaby

Education during the Enlightenment: Public Education and Social Reform

Xingyu Chen, Junyan Xia, Yimeng Xie
2021 BCP Education & Psychology  
The Enlightenment shaped and transformed European society in many ways. This paper illustrates how thinkers like Martin Luther and Jean Jacques Rousseau proposed their thoughts on education, which then played an important role in the educational reform of Prussia and France respectively. It further analyzes how geographical and cultural differences led to distinctively different education systems and goals.
doi:10.54691/bcpep.v3i.14 fatcat:twbmoutjhneubgtgreguqzmluu

Design of Painting Art Style Rendering System Based on Convolutional Neural Network

Xingyu Xie, Bin Lv
2021 Scientific Programming  
Convolutional Neural Network- (CNN-) based GAN models mainly suffer from problems such as data set limitation and rendering efficiency in the segmentation and rendering of painting art. In order to solve these problems, this paper uses the improved cycle generative adversarial network (CycleGAN) to render the current image style. This method replaces the deep residual network (ResNet) of the original network generator with a dense connected convolutional network (DenseNet) and uses the
more » ... l loss function for adversarial training. The painting art style rendering system built in this paper is based on perceptual adversarial network (PAN) for the improved CycleGAN that suppresses the limitation of the network model on paired samples. The proposed method also improves the quality of the image generated by the artistic style of painting and further improves the stability and speeds up the network convergence speed. Experiments were conducted on the painting art style rendering system based on the proposed model. Experimental results have shown that the image style rendering method based on the perceptual adversarial error to improve the CycleGAN + PAN model can achieve better results. The PSNR value of the generated image is increased by 6.27% on average, and the SSIM values are all increased by about 10%. Therefore, the improved CycleGAN + PAN image painting art style rendering method produces better painting art style images, which has strong application value.
doi:10.1155/2021/4708758 doaj:869e936a8b08472d9aef0b6f40ba7e76 fatcat:qixnntb53nhmfeamqx4xafpcpy

Optimization Induced Equilibrium Networks [article]

Xingyu Xie, Qiuhao Wang, Zenan Ling, Xia Li, Yisen Wang, Guangcan Liu, Zhouchen Lin
2021 arXiv   pre-print
Implicit equilibrium models, i.e., deep neural networks (DNNs) defined by implicit equations, have been becoming more and more attractive recently. In this paper, we investigate an emerging question: can an implicit equilibrium model's equilibrium point be regarded as the solution of an optimization problem? To this end, we first decompose DNNs into a new class of unit layer that is the proximal operator of an implicit convex function while keeping its output unchanged. Then, the equilibrium
more » ... el of the unit layer can be derived, named Optimization Induced Equilibrium Networks (OptEq), which can be easily extended to deep layers. The equilibrium point of OptEq can be theoretically connected to the solution of its corresponding convex optimization problem with explicit objectives. Based on this, we can flexibly introduce prior properties to the equilibrium points: 1) modifying the underlying convex problems explicitly so as to change the architectures of OptEq; and 2) merging the information into the fixed point iteration, which guarantees to choose the desired equilibrium point when the fixed point set is non-singleton. We show that deep OptEq outperforms previous implicit models even with fewer parameters. This work establishes the first step towards the optimization-guided design of deep models.
arXiv:2105.13228v3 fatcat:m2whdgdhkndolgcfmriw4u7q3e

A studyforrest extension, MEG recordings while watching the audio-visual movie "Forrest Gump" [article]

Xingyu Liu, Yuxuan Dai, Hailun Xie, Zonglei Zhen
2021 bioRxiv   pre-print
Naturalistic stimuli, such as movies, are being increasingly used to map brain function because of their high ecological validity. The pioneering studyforrest and other naturalistic neuroimaging projects have provided free access to multiple movie-watching functional magnetic resonance imaging (fMRI) datasets to prompt the community for naturalistic experimental paradigms. However, sluggish blood-oxygenation-level-dependent fMRI signals are incapable of resolving neuronal activity with the
more » ... ral resolution at which it unfolds. Instead, magnetoencephalography (MEG) measures changes in the magnetic field produced by neuronal activity and is able to capture rich dynamics of the brain at the millisecond level while watching naturalistic movies. Herein, we present the first public prolonged MEG dataset collected from 11 participants while watching the 2 h long audio-visual movie "Forrest Gump". Minimally preprocessed data was also provided to facilitate the use. As a studyforrest extension, we envision that this dataset, together with fMRI data from the studyforrest project, will serve as a foundation for exploring the neural dynamics of various cognitive functions in real-world contexts.
doi:10.1101/2021.06.04.446837 fatcat:luj6ps77mff2je7644ejfyvbci

DG-Labeler and DGL-MOTS Dataset: Boost the Autonomous Driving Perception [article]

Yiming Cui, Zhiwen Cao, Yixin Xie, Xingyu Jiang, Feng Tao, Yingjie Chen, Lin Li, Dongfang Liu
2021 arXiv   pre-print
Multi-object tracking and segmentation (MOTS) is a critical task for autonomous driving applications. The existing MOTS studies face two critical challenges: 1) the published datasets inadequately capture the real-world complexity for network training to address various driving settings; 2) the working pipeline annotation tool is under-studied in the literature to improve the quality of MOTS learning examples. In this work, we introduce the DG-Labeler and DGL-MOTS dataset to facilitate the
more » ... ing data annotation for the MOTS task and accordingly improve network training accuracy and efficiency. DG-Labeler uses the novel Depth-Granularity Module to depict the instance spatial relations and produce fine-grained instance masks. Annotated by DG-Labeler, our DGL-MOTS dataset exceeds the prior effort (i.e., KITTI MOTS and BDD100K) in data diversity, annotation quality, and temporal representations. Results on extensive cross-dataset evaluations indicate significant performance improvements for several state-of-the-art methods trained on our DGL-MOTS dataset. We believe our DGL-MOTS Dataset and DG-Labeler hold the valuable potential to boost the visual perception of future transportation.
arXiv:2110.07790v1 fatcat:7ljzemgbmfdd3kvygrhczl6f6y

Digital Loop-Mediated Isothermal Amplification on a Commercial Membrane

Xingyu Lin, Xiao Huang, Katharina Urmann, Xing Xie, Michael R. Hoffmann
2019 ACS Sensors  
For example, water in oil droplets generated by T-junction, 6 flow focusing, 7−9 centrifugation, 10, 11 SAMFS 12, 13 and XiE 14, 15 have been applied to dPCR or digital LAMP (dLAMP) analysis.  ... 
doi:10.1021/acssensors.8b01419 pmid:30604619 pmcid:PMC6350201 fatcat:6ilvtykmtnas5mrs5iqdzfrj2m

Efficient Occluded Road Extraction from High-Resolution Remote Sensing Imagery

Dejun Feng, Xingyu Shen, Yakun Xie, Yangge Liu, Jian Wang
2021 Remote Sensing  
remote sensing Article Efficient Occluded Road Extraction from High-Resolution Remote Sensing Imagery Dejun Feng, Xingyu Shen, Yakun Xie *, Yangge Liu and Jian Wang  ...  Xu, Y.; Xie, Z.; Feng, Y.; Chen, Z. Road extraction from high-resolution remote sensing imagery using deep learning. Remote Sens. 2018, 10, 1461. [CrossRef] 10.  ... 
doi:10.3390/rs13244974 fatcat:rr6zwwswgrbvhlamwbhrjleehm

Correction of Field-Measured Wind Speed Affected by Deterministic Interference Factors

Jing Duan, Xingyu Chen, Zhuangning Xie, Lele Zhang
2022 Applied Sciences  
The observations of meteorological wind speed may be biased due to the influence of various distractions. Therefore, the original measured data should be corrected in a targeted manner. Wind tunnel tests (WTT) and computational fluid dynamics (CFD) numerical simulation methods are used to study the local wind environment characteristics of observation sites in Noi Ling Ding Island (NLDI) and Ping An International Financial Center (PAFC) in the Shenzhen area. The interference effects of NLDI and
more » ... the building components and instruments in the hollow-layer atop PAFC on their corresponding anemometer measurement results were analyzed, and a quantitative description was provided with the wind speed influence coefficient (CVI), which is the wind speed ratio in disturbed and undisturbed cases. Results show that the CVI of WTT at the NLDI site is slightly higher than that of CFD, and the wind speed in the wind-sensitive direction is accelerated by 12% due to the influence of NLDI. The large pillars at the corner of PAFC have a considerable occlusion effect on the wind speed under the wind direction of 45°. An acceleration effect with CVI of 1.163 is found in the dominant wind direction when instruments are absent atop the hollow-layer, whereas a sheltering effect is observed with the CVI of 0.593 when instruments are present. These results are used to correct the recorded wind speed at the NLDI and PAFC sites during Super Typhoon Manghut with No. 201822, and then converted into the 10 min mean wind pressure value at 10 m height under the standard landform. The reference wind pressure values obtained are 0.526 and 0.505 kPa. The analogous conversion values achieve the purpose of mutual verification, and the effectiveness and reliability of the methodologies are presented.
doi:10.3390/app12041868 fatcat:jnlya4ztpzdyrhcqsr6drqljri

Reliability Calculation of Mine Ventilation Network

Luo Wengui, Xie Xianping, Xiao Houzao, Cui Chao, Yin Xiaoyu, Su Meiwei, Wang Tinjun, Li Jiangong, Tan Xingyu
2014 Procedia Engineering  
A good ventilation system should reflect both safety reliable and economical reasonable. Safe and reliable mine ventilation system have high reliability and resilience during normal operation or in the disaster period. There is a close relationship between the reliability of mine ventilation network and the reliability of network branch. In order to make quantitative evaluation to the reliability of mine ventilation network . Based on the mine ventilation network equilibrium law, reliability
more » ... ory is applied to the calculation of the branch of ventilation network, disjoint Boolean algebra is used to calculate the reliability of the network . This method has the advantages of simple operation, small calculation error etc.It will be helpful to the design, management and technological transformation of mine ventilation network.
doi:10.1016/j.proeng.2014.10.492 fatcat:kxv2q2cfzfdfxgfbvffask33lq
« Previous Showing results 1 — 15 out of 325 results