arXiv subjects

Yu Fang

Publications and source records attributed to Yu Fang.

52 records · Page 3Linked to original sources

arXiv2023

Complex Locomotion Skill Learning via Differentiable Physics

Differentiable physics enables efficient gradient-based optimizations of neural network (NN) controllers. However, existing work typically only delivers NN controllers with limited capability and generalizability. We present a practical learning framework that outputs unified NN controllers capable of tasks with significantly improved complexity and diversity. To systematically improve training robustness and efficiency, we investigated a suite of improvements over the baseline approach, including periodic activation functions, and tailored loss functions. In addition, we find our adoption of batching and an Adam optimizer effective in training complex locomotion tasks. We evaluate our framework on differentiable mass-spring and material point method (MPM) simulations, with challenging locomotion tasks and multiple robot designs. Experiments show that our learning framework, based on differentiable physics, delivers better results than reinforcement learning and converges much faster. We demonstrate that users can interactively control soft robot locomotion and switch among multiple goals with specified velocity, height, and direction instructions using a unified NN controller trained in our system. Code is available at https://github.com/erizmr/Complex-locomotion-skill-learning-via-differentiable-physics.

cs.AI↗

arXiv2023

Multi-View Vertebra Localization and Identification from CT Images

Accurately localizing and identifying vertebrae from CT images is crucial for various clinical applications. However, most existing efforts are performed on 3D with cropping patch operation, suffering from the large computation costs and limited global information. In this paper, we propose a multi-view vertebra localization and identification from CT images, converting the 3D problem into a 2D localization and identification task on different views. Without the limitation of the 3D cropped patch, our method can learn the multi-view global information naturally. Moreover, to better capture the anatomical structure information from different view perspectives, a multi-view contrastive learning strategy is developed to pre-train the backbone. Additionally, we further propose a Sequence Loss to maintain the sequential structure embedded along the vertebrae. Evaluation results demonstrate that, with only two 2D networks, our method can localize and identify vertebrae in CT images accurately, and outperforms the state-of-the-art methods consistently. Our code is available at https://github.com/ShanghaiTech-IMPACT/Multi-View-Vertebra-Localization-and-Identification-from-CT-Images.

eess.IV↗

arXiv2023

Construction of unbiased dental template and parametric dental model for precision digital dentistry

Dental template and parametric dental models are important tools for various applications in digital dentistry. However, constructing an unbiased dental template and accurate parametric dental models remains a challenging task due to the complex anatomical and morphological dental structures and also low volume ratio of the teeth. In this study, we develop an unbiased dental template by constructing an accurate dental atlas from CBCT images with guidance of teeth segmentation. First, to address the challenges, we propose to enhance the CBCT images and their segmentation images, including image cropping, image masking and segmentation intensity reassigning. Then, we further use the segmentation images to perform co-registration with the CBCT images to generate an accurate dental atlas, from which an unbiased dental template can be generated. By leveraging the unbiased dental template, we construct parametric dental models by estimating point-to-point correspondences between the dental models and employing Principal Component Analysis to determine shape subspaces of the parametric dental models. A total of 159 CBCT images of real subjects are collected to perform the constructions. Experimental results demonstrate effectiveness of our proposed method in constructing unbiased dental template and parametric dental model. The developed dental template and parametric dental models are available at https://github.com/Marvin0724/Teeth_template.

cs.CV↗

arXiv2022

SNAF: Sparse-view CBCT Reconstruction with Neural Attenuation Fields

Cone beam computed tomography (CBCT) has been widely used in clinical practice, especially in dental clinics, while the radiation dose of X-rays when capturing has been a long concern in CBCT imaging. Several research works have been proposed to reconstruct high-quality CBCT images from sparse-view 2D projections, but the current state-of-the-arts suffer from artifacts and the lack of fine details. In this paper, we propose SNAF for sparse-view CBCT reconstruction by learning the neural attenuation fields, where we have invented a novel view augmentation strategy to overcome the challenges introduced by insufficient data from sparse input views. Our approach achieves superior performance in terms of high reconstruction quality (30+ PSNR) with only 20 input views (25 times fewer than clinical collections), which outperforms the state-of-the-arts. We have further conducted comprehensive experiments and ablation analysis to validate the effectiveness of our approach.

eess.IV↗

arXiv2022

Imbalanced Node Processing Method in Graph Neural Network Classification Task

In recent years, the node classification task in graph neural networks(GNNs) has developed rapidly, driving the development of research in various fields. However, there are a large number of class imbalances in the graph data, and there is a large gap between the number of different classes, resulting in suboptimal results in classification. Proposing a solution to the imbalance problem has become indispensable for the successful advancement of our downstream missions. Therefore, we start with the loss function and try to find a loss function that can effectively solve the imbalance of graph nodes to participate in the node classification task. thence, we introduce GHMC Loss into the graph neural networks to deal with difficult samples that are not marginal. Attenuate the loss contribution of marginal samples and simple samples. Experiments on multiple benchmarks show that our method can effectively deal with the class imbalance problem, and our method improves the accuracy by 3% compared to the traditional loss function.

cs.LG↗

arXiv2022

Specialized Re-Ranking: A Novel Retrieval-Verification Framework for Cloth Changing Person Re-Identification

Cloth changing person re-identification(Re-ID) can work under more complicated scenarios with higher security than normal Re-ID and biometric techniques and is therefore extremely valuable in applications. Meanwhile, higher flexibility in appearance always leads to more similar-looking confusing images, which is the weakness of the widely used retrieval methods. In this work, we shed light on how to handle these similar images. Specifically, we propose a novel retrieval-verification framework. Given an image, the retrieval module can search for similar images quickly. Our proposed verification network will then compare the input image and the candidate images by contrasting those local details and give a similarity score. An innovative ranking strategy is also introduced to take a good balance between retrieval and verification results. Comprehensive experiments are conducted to show the effectiveness of our framework and its capability in improving the state-of-the-art methods remarkably on both synthetic and realistic datasets.

cs.CV↗

arXiv2021

Trudinger-Moser inequalities on a closed Riemann surface with a symmetric conical metric

This is a continuation of our previous work [13]. Let $(Σ,g)$ be a closed Riemann surface, where the metric $g$ has conical singularities at finite points. Suppose $\mathbf{G}$ is a group whose elements are isometries acting on $(Σ,g)$. Trudinger-Moser inequalities involving $\mathbf{G}$ are established via the method of blow-up analysis, and the corresponding extremals are also obtained. This extends previous results of Chen [7], Iula-Manicini [21], and the authors [13].

math.AP↗

arXiv2021

BFEMP: Interpenetration-Free MPM-FEM Coupling with Barrier Contact

This paper introduces BFEMP, a new approach for monolithically coupling the Material Point Method (MPM) with the Finite Element Method (FEM) through barrier energy-based particle-mesh frictional contact using a variational time-stepping formulation. The fully implicit time integration of the coupled system is recast into a barrier-augmented unconstrained nonlinear optimization problem. A modified line-search Newton's method is adopted to strictly prevent material points from penetrating the FEM domain, ensuring convergence and feasibility regardless of the time step size or the mesh resolutions. The proposed coupling scheme also reduces to a new approach for imposing separable frictional kinematic boundaries for MPM when all nodal displacements in the FEM domain are prescribed with Dirichlet boundary conditions. Compared to standard implicit time integration, the extra algorithmic components associated with the contact treatment only depend on simple point-segment (or point-triangle in 3D) geometric queries which robustly handle arbitrary FEM mesh boundaries represented with codimension-1 simplices. Experiments and analyses are performed to demonstrate the robustness and accuracy of the proposed method.

math.NA↗

arXiv2021

MHD analysis on the physical designs of CFETR and HFRC

The China Fusion Engineering Test Reactor (CFETR) and the Huazhong Field Reversed Configuration (HFRC), currently both under intensive physical and engineering designs in China, are the two major projects representative of the low-density steady-state and high-density pulsed pathways to fusion. One of the primary tasks of the physics designs for both CFETR and HFRC is the assessment and analysis of the magnetohydrodynamic (MHD) stability of the proposed design schemes. Comprehensive efforts on the assessment of MHD stability of CFETR and HFRC baseline scenarios have led to preliminary progresses that may further benefit engineering designs.

physics.plasm-ph↗

arXiv2020

Measurements of the growth and saturation of electron Weibel instability in optical-field ionized plasmas

The temporal evolution of the magnetic field associated with electron thermal Weibel instability in optical-field ionized plasmas is measured using ultrashort (1.8 ps), relativistic (45 MeV) electron bunches from a linear accelerator. The self-generated magnetic fields are found to self-organize into a quasi-static structure consistent with a helicoid topology within a few ps and such a structure lasts for tens of ps in underdense plasmas. The measured growth rate agrees well with that predicted by the kinetic theory of plasmas taking into account collisions. Magnetic trapping is identified as the dominant saturation mechanism.

physics.plasm-ph↗

arXiv2020

High-throughput injection-acceleration of electron bunches from a linear accelerator to a laser wakefield accelerator

Plasma-based accelerators (PBAs) driven by either intense lasers (laser wakefield accelerators, LWFAs) or particle beams (plasma wakefield accelerators, PWFAs), can accelerate charged particles at extremely high gradients compared to conventional radio-frequency (RF) accelerators. In the past two decades, great strides have been made in this field, making PBA a candidate for next-generation light sources and colliders. However, these challenging applications necessarily require beams with good stability, high quality, controllable polarization and excellent reproducibility. To date, such beams are generated only by conventional RF accelerators. Therefore, it is important to demonstrate the injection and acceleration of beams first produced using a conventional RF accelerator, by a PBA. In some recent studies on LWFA staging and external injection-acceleration in PWFA only a very small fraction (from below 0.1% to few percent) of the injected charge (the coupling efficiency) was accelerated. For future colliders where beam energy will need to be boosted using multiple stages, the coupling efficiency per stage must approach 100%. Here we report the first demonstration of external injection from a photocathode-RF-gun-based conventional linear accelerator (LINAC) into a LWFA and subsequent acceleration without any significant loss of charge or degradation of quality, which is achieved by properly shaping and matching the beam into the plasma structure. This is an important step towards realizing a high-throughput, multi-stage, high-energy, hybrid conventional-plasma accelerator.

physics.plasm-ph↗

arXiv2020

Hierarchical Optimization Time Integration for CFL-rate MPM Stepping

We propose Hierarchical Optimization Time Integration (HOT) for efficient implicit time-stepping of the Material Point Method (MPM) irrespective of simulated materials and conditions. HOT is an MPM-specialized hierarchical optimization algorithm that solves nonlinear time step problems for large-scale MPM systems near the CFL-limit. HOT provides convergent simulations "out-of-the-box" across widely varying materials and computational resolutions without parameter tuning. As an implicit MPM time stepper accelerated by a custom-designed Galerkin multigrid wrapped in a quasi-Newton solver, HOT is both highly parallelizable and robustly convergent. As we show in our analysis, HOT maintains consistent and efficient performance even as we grow stiffness, increase deformation, and vary materials over a wide range of finite strain, elastodynamic and plastic examples. Through careful benchmark ablation studies, we compare the effectiveness of HOT against seemingly plausible alternative combinations of MPM with standard multigrid and other Newton-Krylov models. We show how these alternative designs result in severe issues and poor performance. In contrast, HOT outperforms the existing state-of-the-art, heavily optimized implicit MPM codes with an up to 10x performance speedup across a wide range of challenging benchmark test simulations.

cs.GR↗

arXiv2019

Visualizing the melting processes in ultrashort intense laser triggered gold mesh with high energy electron radiography

High energy electron radiography (HEER) is a promising tool for high energy density physics diagnostics, apart from other tools like X/γ ray shadowgraphy and high energy proton radiography. Impressive progresses have been made in development and application of HEER in past few years, and proved its potentials for high-resolution imaging of static opaque objects. By taking advantages of short pulse duration and tunable time structure of high energy electron probes, time-resolved imaging measurement of high energy density gold irradiated by ultrashort intense lasers has been performed. Phenomena of different time periods from picosecond to microsecond have been observed, thus proving feasibilities of this technique for imaging of static and dynamic objects.

physics.app-ph↗

arXiv2018

A balanced energy consumption clustering algorithm for heterogeneous energy wireless sensor networks

In this paper, a balanced energy consumption clustering algorithm (BECC) is proposed. This new scheme is a cluster-based algorithm designed for heterogeneous energy wireless sensor networks. A polarized energy factor is introduced to adjust the probability with which each node may become a cluster head in the election of the new clustering scheme. Under the condition that the expected number of cluster heads in the network preserves the theoretical optimal number, BECC makes sure that nodes with higher residual energy will become cluster heads with higher probabilities while nodes with lower residual energy will not become cluster heads. Simulation results show that this new scheme provides longer lifetime than the classical clustering algorithms including LEACH and other improved algorithms in heterogeneous networks, and BECC also reaches larger amount of messages received at the sink.

eess.SP↗

arXiv2018

Trudinger-Moser inequalities on a closed Riemannian surface with the action of a finite isometric group

Let $(Σ,g)$ be a closed Riemannian surface, $W^{1,2}(Σ,g)$ be the usual Sobolev space, $\textbf{G}$ be a finite isometric group acting on $(Σ,g)$, and $\mathscr{H}_\textbf{G}$ be a function space including all functions $u\in W^{1,2}(Σ,g)$ with $\int_Σudv_g=0$ and $u(σ(x))=u(x)$ for all $σ\in \textbf{G}$ and all $x\inΣ$. Denote the number of distinct points of the set $\{σ(x): σ\in \textbf{G}\}$ by $I(x)$ and $\ell=\inf_{x\in Σ}I(x)$. Let $λ_1^\textbf{G}$ be the first eigenvalue of the Laplace-Beltrami operator on the space $\mathscr{H}_\textbf{G}$. Using blow-up analysis, we prove that if $α<λ_1^\textbf{G}$ and $β\leq 4π\ell$, then there holds $$\sup_{u\in\mathscr{H}_\textbf{G},\,\int_Σ|\nabla_gu|^2dv_g-α\int_Σu^2dv_g\leq 1}\int_Σe^{βu^2}dv_g<\infty;$$ if $α<λ_1^\textbf{G}$ and $β>4π\ell$, or $α\geq λ_1^\textbf{G}$ and $β>0$, then the above supremum is infinity; if $α<λ_1^\textbf{G}$ and $β\leq 4π\ell$, then the above supremum can be attained. Moreover, similar inequalities involving higher order eigenvalues are obtained. Our results partially improve original inequalities of J. Moser \cite{Moser}, L. Fontana \cite{Fontana} and W. Chen \cite{Chen-90}.

math.AP↗

arXiv2011

Aggregation of ferromagnetic and paramagnetic atoms at edges of graphenes and graphite

In this work, we report that when ferromagnetic metals (Fe, Co and Ni) are thermally evaporated onto n-layer graphenes and graphite, a metal nanowire and adjacent nanogaps can be found along the edges regardless of its zigzag or armchair structure. Similar features can also be observed for paramagnetic metals, such as Mn, Al and Pd. Meanwhile, metal nanowires and adjacent nanogaps can not be found for diamagnetic metals (Au and Ag). An external magnetic field during the evaporation of metals can make these unique features disappear for ferromagnetic and paramagnetic metal; and the morphologies of diamagnetic metal do not change after the application of an external magnetic field. We discuss the possible reasons for these novel and interesting results, which include possible one dimensional ferromagnets along the edge and edge-related binding energy.

physics.chem-ph↗