arXiv subjects

Zidong Wang

Publications and source records attributed to Zidong Wang.

At least 55 records · Page 3Linked to original sources

arXiv2023

Retinal Image Segmentation with Small Datasets

Many eye diseases like Diabetic Macular Edema (DME), Age-related Macular Degeneration (AMD), and Glaucoma manifest in the retina, can cause irreversible blindness or severely impair the central version. The Optical Coherence Tomography (OCT), a 3D scan of the retina with high qualitative information about the retinal morphology, can be used to diagnose and monitor changes in the retinal anatomy. Many Deep Learning (DL) methods have shared the success of developing an automated tool to monitor pathological changes in the retina. However, the success of these methods depend mainly on large datasets. To address the challenge from very small and limited datasets, we proposed a DL architecture termed CoNet (Coherent Network) for joint segmentation of layers and fluids in retinal OCT images on very small datasets (less than a hundred training samples). The proposed model was evaluated on the publicly available Duke DME dataset consisting of 110 B-Scans from 10 patients suffering from DME. Experimental results show that the proposed model outperformed both the human experts' annotation and the current state-of-the-art architectures by a clear margin with a mean Dice Score of 88% when trained on 55 images without any data augmentation.

eess.IV↗

arXiv2023

Prediction of transonic flow over supercritical airfoils using geometric-encoding and deep-learning strategies

The Reynolds-averaged Navier-Stokes equation for compressible flow over supercritical airfoils under various flow conditions must be rapidly and accurately solved to shorten design cycles for such airfoils. Although deep-learning methods can effectively predict flow fields, the accuracy of these predictions near sensitive regions and their generalizability to large-scale datasets in engineering applications must be enhanced. In this study, a modified vision transformer-based encoder-decoder network is designed for the prediction of transonic flow over supercritical airfoils. In addition, four methods are designed to encode the geometric input with various information points and the performances of these methods are compared. The statistical results show that these methods generate accurate predictions over the complete flow field, with a mean absolute error on the order of 1e-4. To increase accuracy near the shock area, multilevel wavelet transformation and gradient distribution losses are introduced into the loss function. This results in the maximum error that is typically observed near the shock area decreasing by 50%. Furthermore, the models are pretrained through transfer learning on large-scale datasets and finetuned on small datasets to improve their generalizability in engineering applications. The results generated by various pretrained models demonstrate that transfer learning yields a comparable accuracy from a reduced training time.

physics.flu-dyn↗

arXiv2023

nnUNet RASPP for Retinal OCT Fluid Detection, Segmentation and Generalisation over Variations of Data Sources

Retinal Optical Coherence Tomography (OCT), a noninvasive cross-sectional scan of the eye with qualitative 3D visualization of the retinal anatomy is use to study the retinal structure and the presence of pathogens. The advent of the retinal OCT has transformed ophthalmology and it is currently paramount for the diagnosis, monitoring and treatment of many eye pathogens including Macular Edema which impairs vision severely or Glaucoma that can cause irreversible blindness. However the quality of retinal OCT images varies among device manufacturers. Deep Learning methods have had their success in the medical image segmentation community but it is still not clear if the level of success can be generalised across OCT images collected from different device vendors. In this work we propose two variants of the nnUNet [8]. The standard nnUNet and an enhanced vision call nnUnet_RASPP (nnU-Net with residual and Atrous Spatial Pyramid Pooling) both of which are robust and generalise with consistent high performance across images from multiple device vendors. The algorithm was validated on the MICCAI 2017 RETOUCH challenge dataset [1] acquired from 3 device vendors across 3 medical centers from patients suffering from 2 retinal disease types. Experimental results show that our algorithms outperform the current state-of-the-arts algorithms by a clear margin for segmentation obtaining a mean Dice Score (DS) of 82.3% for the 3 retinal fluids scoring 84.0%, 80.0%, 83.0% for Intraretinal Fluid (IRF), Subretinal Fluid (SRF), and Pigment Epithelium Detachments (PED) respectively on the testing dataset. Also we obtained a perfect Area Under the Curve (AUC) score of 100% for the detection of the presence of fluid for all 3 fluid classes on the testing dataset.

eess.IV↗

arXiv2023

Solving Boltzmann equation with neural sparse representation

We consider the neural sparse representation to solve Boltzmann equation with BGK and quadratic collision model, where a network-based ansatz that can approximate the distribution function with extremely high efficiency is proposed. Precisely, fully connected neural networks are employed in the time and spatial space so as to avoid the discretization in space and time. The different low-rank representations are utilized in the microscopic velocity for the BGK and quadratic collision model, resulting in a significant reduction in the degree of freedom. We approximate the discrete velocity distribution in the BGK model using the canonical polyadic decomposition. For the quadratic collision model, a data-driven, SVD-based linear basis is built based on the BGK solution. All these will significantly improve the efficiency of the network when solving Boltzmann equation. Moreover, the specially designed adaptive-weight loss function is proposed with the strategies as multi-scale input and Maxwellian splitting applied to further enhance the approximation efficiency and speed up the learning process. Several numerical experiments, including 1D wave and Sod problems and 2D wave problem, demonstrate the effectiveness of these neural sparse representation methods.

math.NA↗

arXiv2023

Company-as-Tribe: Company Financial Risk Assessment on Tribe-Style Graph with Hierarchical Graph Neural Networks

Company financial risk is ubiquitous and early risk assessment for listed companies can avoid considerable losses. Traditional methods mainly focus on the financial statements of companies and lack the complex relationships among them. However, the financial statements are often biased and lagged, making it difficult to identify risks accurately and timely. To address the challenges, we redefine the problem as \textbf{company financial risk assessment on tribe-style graph} by taking each listed company and its shareholders as a tribe and leveraging financial news to build inter-tribe connections. Such tribe-style graphs present different patterns to distinguish risky companies from normal ones. However, most nodes in the tribe-style graph lack attributes, making it difficult to directly adopt existing graph learning methods (e.g., Graph Neural Networks(GNNs)). In this paper, we propose a novel Hierarchical Graph Neural Network (TH-GNN) for Tribe-style graphs via two levels, with the first level to encode the structure pattern of the tribes with contrastive learning, and the second level to diffuse information based on the inter-tribe relations, achieving effective and efficient risk assessment. Extensive experiments on the real-world company dataset show that our method achieves significant improvements on financial risk assessment over previous competing methods. Also, the extensive ablation studies and visualization comprehensively show the effectiveness of our method.

cs.LG↗

arXiv2022

Meta-Auto-Decoder for Solving Parametric Partial Differential Equations

Many important problems in science and engineering require solving the so-called parametric partial differential equations (PDEs), i.e., PDEs with different physical parameters, boundary conditions, shapes of computation domains, etc. Recently, building learning-based numerical solvers for parametric PDEs has become an emerging new field. One category of methods such as the Deep Galerkin Method (DGM) and Physics-Informed Neural Networks (PINNs) aim to approximate the solution of the PDEs. They are typically unsupervised and mesh-free, but require going through the time-consuming network training process from scratch for each set of parameters of the PDE. Another category of methods such as Fourier Neural Operator (FNO) and Deep Operator Network (DeepONet) try to approximate the solution mapping directly. Being fast with only one forward inference for each PDE parameter without retraining, they often require a large corpus of paired input-output observations drawn from numerical simulations, and most of them need a predefined mesh as well. In this paper, we propose Meta-Auto-Decoder (MAD), a mesh-free and unsupervised deep learning method that enables the pre-trained model to be quickly adapted to equation instances by implicitly encoding (possibly heterogenous) PDE parameters as latent vectors. The proposed method MAD can be interpreted by manifold learning in infinite-dimensional spaces, granting it a geometric insight. Extensive numerical experiments show that the MAD method exhibits faster convergence speed without losing accuracy than other deep learning-based methods. The project page with code is available: https://gitee.com/mindspore/mindscience/tree/master/MindElec/.

cs.LG↗

arXiv2022

PSP: Million-level Protein Sequence Dataset for Protein Structure Prediction

Proteins are essential component of human life and their structures are important for function and mechanism analysis. Recent work has shown the potential of AI-driven methods for protein structure prediction. However, the development of new models is restricted by the lack of dataset and benchmark training procedure. To the best of our knowledge, the existing open source datasets are far less to satisfy the needs of modern protein sequence-structure related research. To solve this problem, we present the first million-level protein structure prediction dataset with high coverage and diversity, named as PSP. This dataset consists of 570k true structure sequences (10TB) and 745k complementary distillation sequences (15TB). We provide in addition the benchmark training procedure for SOTA protein structure prediction model on this dataset. We validate the utility of this dataset for training by participating CAMEO contest in which our model won the first place. We hope our PSP dataset together with the training benchmark can enable a broader community of AI/biology researchers for AI-driven protein related research.

q-bio.BM↗

arXiv2022

Data and Physics Driven Learning Models for Fast MRI -- Fundamentals and Methodologies from CNN, GAN to Attention and Transformers

Research studies have shown no qualms about using data driven deep learning models for downstream tasks in medical image analysis, e.g., anatomy segmentation and lesion detection, disease diagnosis and prognosis, and treatment planning. However, deep learning models are not the sovereign remedy for medical image analysis when the upstream imaging is not being conducted properly (with artefacts). This has been manifested in MRI studies, where the scanning is typically slow, prone to motion artefacts, with a relatively low signal to noise ratio, and poor spatial and/or temporal resolution. Recent studies have witnessed substantial growth in the development of deep learning techniques for propelling fast MRI. This article aims to (1) introduce the deep learning based data driven techniques for fast MRI including convolutional neural network and generative adversarial network based methods, (2) survey the attention and transformer based models for speeding up MRI reconstruction, and (3) detail the research in coupling physics and data driven models for MRI acceleration. Finally, we will demonstrate through a few clinical applications, explain the importance of data harmonisation and explainable models for such fast MRI techniques in multicentre and multi-scanner studies, and discuss common pitfalls in current research and recommendations for future research directions.

eess.IV↗

arXiv2021

Solving Partial Differential Equations with Point Source Based on Physics-Informed Neural Networks

In recent years, deep learning technology has been used to solve partial differential equations (PDEs), among which the physics-informed neural networks (PINNs) emerges to be a promising method for solving both forward and inverse PDE problems. PDEs with a point source that is expressed as a Dirac delta function in the governing equations are mathematical models of many physical processes. However, they cannot be solved directly by conventional PINNs method due to the singularity brought by the Dirac delta function. We propose a universal solution to tackle this problem with three novel techniques. Firstly the Dirac delta function is modeled as a continuous probability density function to eliminate the singularity; secondly a lower bound constrained uncertainty weighting algorithm is proposed to balance the PINNs losses between point source area and other areas; and thirdly a multi-scale deep neural network with periodic activation function is used to improve the accuracy and convergence speed of the PINNs method. We evaluate the proposed method with three representative PDEs, and the experimental results show that our method outperforms existing deep learning-based methods with respect to the accuracy, the efficiency and the versatility.

cs.LG↗

arXiv2021

A CRF-based Framework for Tracklet Inactivation in Online Multi-Object Tracking

Online multi-object tracking (MOT) is an active research topic in the domain of computer vision. Although many previously proposed algorithms have exhibited decent results, the issue of tracklet inactivation has not been sufficiently studied. Simple strategies such as using a fixed threshold on classification scores are adopted, yielding undesirable tracking mistakes and limiting the overall performance. In this paper, a conditional random field (CRF) based framework is put forward to tackle the tracklet inactivation issue in online MOT problems. A discrete CRF which exploits the intra-frame relationship between tracking hypotheses is developed to improve the robustness of tracklet inactivation. Separate sets of feature functions are designed for the unary and binary terms in the CRF, which take into account various tracking challenges in practical scenarios. To handle the problem of varying CRF nodes in the MOT context, two strategies named as hypothesis filtering and dummy nodes are employed. In the proposed framework, the inference stage is conducted by using the loopy belief propagation algorithm, and the CRF parameters are determined by utilizing the maximum likelihood estimation method followed by slight manual adjustment. Experimental results show that the tracker combined with the CRF-based framework outperforms the baseline on the MOT16 and MOT17 benchmarks. The extensibility of the proposed framework is further validated by an extensive experiment.

cs.CV↗

arXiv2021

AsymptoticNG: A regularized natural gradient optimization algorithm with look-ahead strategy

Optimizers that further adjust the scale of gradient, such as Adam, Natural Gradient (NG), etc., despite widely concerned and used by the community, are often found poor generalization performance, compared with Stochastic Gradient Descent (SGD). They tend to converge excellently at the beginning of training but are weak at the end. An immediate idea is to complement the strengths of these algorithms with SGD. However, a truncated replacement of optimizer often leads to a crash of the update pattern, and new algorithms often require many iterations to stabilize their search direction. Driven by this idea and to address this problem, we design and present a regularized natural gradient optimization algorithm with look-ahead strategy, named asymptotic natural gradient (ANG). According to the total iteration step, ANG dynamic assembles NG and Euclidean gradient, and updates parameters along the new direction using the intensity of NG. Validation experiments on CIFAR10 and CIFAR100 data sets show that ANG can update smoothly and stably at the second-order speed, and achieve better generalization performance.

cs.LG↗

arXiv2020

Eigenvalue-corrected Natural Gradient Based on a New Approximation

Using second-order optimization methods for training deep neural networks (DNNs) has attracted many researchers. A recently proposed method, Eigenvalue-corrected Kronecker Factorization (EKFAC) (George et al., 2018), proposes an interpretation of viewing natural gradient update as a diagonal method, and corrects the inaccurate re-scaling factor in the Kronecker-factored eigenbasis. Gao et al. (2020) considers a new approximation to the natural gradient, which approximates the Fisher information matrix (FIM) to a constant multiplied by the Kronecker product of two matrices and keeps the trace equal before and after the approximation. In this work, we combine the ideas of these two methods and propose Trace-restricted Eigenvalue-corrected Kronecker Factorization (TEKFAC). The proposed method not only corrects the inexact re-scaling factor under the Kronecker-factored eigenbasis, but also considers the new approximation method and the effective damping technique proposed in Gao et al. (2020). We also discuss the differences and relationships among the Kronecker-factored approximations. Empirically, our method outperforms SGD with momentum, Adam, EKFAC and TKFAC on several DNNs.

cs.LG↗

arXiv2020

A Trace-restricted Kronecker-Factored Approximation to Natural Gradient

Second-order optimization methods have the ability to accelerate convergence by modifying the gradient through the curvature matrix. There have been many attempts to use second-order optimization methods for training deep neural networks. Inspired by diagonal approximations and factored approximations such as Kronecker-Factored Approximate Curvature (KFAC), we propose a new approximation to the Fisher information matrix (FIM) called Trace-restricted Kronecker-factored Approximate Curvature (TKFAC) in this work, which can hold the certain trace relationship between the exact and the approximate FIM. In TKFAC, we decompose each block of the approximate FIM as a Kronecker product of two smaller matrices and scaled by a coefficient related to trace. We theoretically analyze TKFAC's approximation error and give an upper bound of it. We also propose a new damping technique for TKFAC on convolutional neural networks to maintain the superiority of second-order optimization methods during training. Experiments show that our method has better performance compared with several state-of-the-art algorithms on some deep network architectures.

cs.LG↗

arXiv2020

Topology-Dependent Brownian Gyromotion of a Single Skyrmion

Non-interacting particles exhibiting Brownian motion have been observed in many occasions of sciences, such as molecules suspended in liquids, optically trapped microbeads, and spin textures in magnetic materials. In particular, a detailed examination of Brownian motion of spin textures is important for designing thermally stable spintronic devices which motivates the present study. In this Letter, through using temporally and spatially resolved polar magneto-optic Kerr effect (MOKE) microscopy, we have experimentally observed the thermal fluctuation-induced random walk of a single isolated Néel-type magnetic skyrmion in an interfacially asymmetric Ta/CoFeB/TaOx multilayer. An intriguing topology dependent Brownian gyromotion behavior of skyrmions has been identified. The onset of Brownian gyromotion of a single skyrmion induced by the thermal effects, including a nonlinear temperature-dependent diffusion coefficient and topology-dependent gyromotion are further formulated based on the stochastic Thiele equation. The experimental and numerical demonstration of topology-dependent Brownian gyromotion of skyrmions can be useful for understanding the nonequilibrium magnetization dynamics and implementing spintronic devices.

cond-mat.mes-hall↗

arXiv2020

Thermal generation, manipulation and detection of skyrmions

Recent years have witnessed significant progresses in realizing skyrmions in chiral magnets1-4 and asymmetric magnetic multilayers5-13, as well as their electrical manipulation2,7,8,10. Equally important, thermal generation, manipulation and detection of skyrmions can be exploited for prototypical new architecture with integrated computation14 and energy harvesting15. It has yet to verify if skyrmions can be purely generated by heating16,17, and if their resultant direction of motion driven by temperature gradients follows the diffusion or, oppositely, the magnonic spin torque17-21. Here, we address these important issues in microstructured devices made of multilayers: (Ta_CoFeB_MgO)15, (Pt_CoFeB_MgO_Ta)15 and (Pt_Co_Ta)15 integrated with on-chip heaters, by using a full-field soft X-ray microscopy. The thermal generation of densely packed skyrmions is attributed to the low energy barrier at the device edge, together with the thermally induced morphological transition from stripe domains to skyrmions. The unidirectional diffusion of skyrmions from the hot region towards the cold region is experimentally observed. It can be theoretically explained by the combined contribution from repulsive forces between skyrmions, and thermal spin-orbit torques in competing with magnonic spin torques17,18,20,21 and entropic forces22. These thermally generated skyrmions can be further electrically detected by measuring the accompanied anomalous Nernst voltages23. The on-chip thermoelectric generation, manipulation and detection of skyrmions could open another exciting avenue for enabling skyrmionics, and promote interdisciplinary studies among spin caloritronics15, magnonics24 and skyrmionics3,4,12.

cond-mat.mes-hall↗

arXiv2019

Generation and Hall effect of skyrmions enabled via using nonmagnetic point contacts

To enable functional skyrmion based spintronic devices, the controllable generation and manipulation of skyrmions is essential. While the generation of skyrmions by using a magnetic geometrical constriction has already been demonstrated, this approach is difficult to combine with a subsequent controlled manipulation of skyrmions. The high efficiency of skyrmion generation from magnetic constrictions limits the useful current density, resulting in stochastic skyrmion motion, which may obscure topological phenomena such as the skyrmion Hall effect. In order to address this issue, we designed a nonmagnetic conducting Ti/Au point contact in devices made of Ta/CoFeB/TaOx trilayer films. By applying high voltage pulses, we experimentally demonstrated that skyrmions can be dynamically generated. Moreover, the accompanied spin topology dependent skyrmion dynamics, the skyrmion Hall effect is also experimentally observed in the same devices. The creation process has been numerically reproduced through micromagnetic simulations in which the important role of skyrmion-antiskyrmion pair generation is identified. The motion and Hall effect of the skyrmions, immediately after their creation is described using a modified Thiele equation after taking into account the contribution from spatially inhomogeneous spin-orbit torques and the Magnus force. The simultaneous generation and manipulation of skyrmions using a nonmagnetic point contact could provide a useful pathway for designing novel skyrmion based devices.

cond-mat.mes-hall↗

arXiv2016

Magnetic Bloch Skyrmion Transport by Electric Fields in a Composite Bilayer

We investigate a mechanical method to manipulate magnetic Bloch Skyrmions by applying an electric field in a composite chiral-magnetic (CM)/ferroelectric (FE) bilayer. The magnetoelectric coupling at the interface allows the electric field to stimulate magnetic ordering. Therefore it offers the possibility to generate Skyrmions [Phys. Rev. B 94, 014311 (2016)]. Here, we design a movable and localized electric field source to drive skyrmion transport along the bilayer. A traveling velocity of the electric field source must be carefully chosen to show the stability and effciency of this process. The effects of high speed operation will be discussed.

cond-mat.mes-hall↗

arXiv2016

Ferroelectrics Manipulate Magnetic Bloch Skyrmions in a Composite Bilayer

Theoretical investigation demonstrates that the composite bilayer (i.e., chiral-magnetic/ferroelectric bilayer) offers the possibility of electric-induced magnetic Skyrmions [Phys. Rev. B \textbf{94}, 014311 (2016)]. In this Article, we propose a micromagnetic model to physically manipulate magnetic Bloch Skyrmions propagating in a chiral-magnetic thin film with a polarized ferroelectric essential to drive the system through the converse magnetoelectric effect. Effects caused by different velocities of the propagation, sizes of the thin film, and strength of the magnetoelectric couplings strongly impact on quality and quantity of the magnetic Skyrmions.

cond-mat.mes-hall↗