arXiv subjects

Xiaodong Zhang

Publications and source records attributed to Xiaodong Zhang.

At least 55 records · Page 3Linked to original sources

arXiv2024

Segment Change Model (SCM) for Unsupervised Change detection in VHR Remote Sensing Images: a Case Study of Buildings

The field of Remote Sensing (RS) widely employs Change Detection (CD) on very-high-resolution (VHR) images. A majority of extant deep-learning-based methods hinge on annotated samples to complete the CD process. Recently, the emergence of Vision Foundation Model (VFM) enables zero-shot predictions in particular vision tasks. In this work, we propose an unsupervised CD method named Segment Change Model (SCM), built upon the Segment Anything Model (SAM) and Contrastive Language-Image Pre-training (CLIP). Our method recalibrates features extracted at different scales and integrates them in a top-down manner to enhance discriminative change edges. We further design an innovative Piecewise Semantic Attention (PSA) scheme, which can offer semantic representation without training, thereby minimize pseudo change phenomenon. Through conducting experiments on two public datasets, the proposed SCM increases the mIoU from 46.09% to 53.67% on the LEVIR-CD dataset, and from 47.56% to 52.14% on the WHU-CD dataset. Our codes are available at https://github.com/StephenApX/UCD-SCM.

cs.CV↗

arXiv2024

Enhancing Terrestrial Net Primary Productivity Estimation with EXP-CASA: A Novel Light Use Efficiency Model Approach

The Light Use Efficiency model, epitomized by the CASA model, is extensively applied in the quantitative estimation of vegetation Net Primary Productivity. However, the classic CASA model is marked by significant complexity: the estimation of environmental stress parameters, in particular, necessitates multi-source observation data, adding to the complexity and uncertainty of the model's operation. Additionally, the saturation effect of the Normalized Difference Vegetation Index (NDVI), a key variable in the CASA model, weakened the accuracy of CASA's NPP predictions in densely vegetated areas. To address these limitations, this study introduces the Exponential-CASA (EXP-CASA) model. The EXP-CASA model effectively improves the CASA model by using novel functions for estimating the fraction of absorbed photosynthetically active radiation (FPAR) and environmental stress, by utilizing long-term observational data from FLUXNET and MODIS surface reflectance data. In a comparative analysis of NPP estimation accuracy among four different NPP products, EXP-CASA ($R^2 = 0.68, RMSE= 1.1gC\cdot m^{-2} \cdot d^{-1}$) outperforms others, followed by GLASS-NPP, and lastly MODIS-NPP and classic CASA. Additionally, this research assesses the EXP-CASA model's adaptability to various vegetation indices, evaluates the sensitivity and stability of its parameters over time, and compares its accuracy against other leading NPP estimation products. The findings reveal that the EXP-CASA model exhibits strong adaptability to diverse vegetation indices and stability of model parameters over time series. By introducing a novel estimation approach that optimizes model construction, the EXP-CASA model remarkably improves the accuracy of NPP estimations and paves the way for global-scale, consistent, and continuous assessment of vegetation NPP.

q-bio.QM↗

arXiv2024

LitSim: A Conflict-aware Policy for Long-term Interactive Traffic Simulation

Simulation is pivotal in evaluating the performance of autonomous driving systems due to the advantages of high efficiency and low cost compared to on-road testing. Bridging the gap between simulation and the real world requires realistic agent behaviors. However, the existing works have the following shortcomings in achieving this goal: (1) log replay offers realistic scenarios but often leads to collisions due to the absence of dynamic interactions, and (2) both heuristic-based and data-based solutions, which are parameterized and trained on real-world datasets, encourage interactions but often deviate from real-world data over long horizons. In this work, we propose LitSim, a long-term interactive simulation approach that maximizes realism by minimizing the interventions in the log. Specifically, our approach primarily uses log replay to ensure realism and intervenes only when necessary to prevent potential conflicts. We then encourage interactions among the agents and resolve the conflicts, thereby reducing the risk of unrealistic behaviors. We train and validate our model on the real-world dataset NGSIM, and the experimental results demonstrate that LitSim outperforms the currently popular approaches in terms of realism and reactivity.

cs.RO↗

arXiv2024

Using Partial Structure R1 to Determine Small-Molecule Crystal Structures at the Lowest Resolution Limits

This paper explores the lowest data resolution at which the partial structure R1 (pR1) method can determine a small-molecule crystal structure. Three specific structures have been studied. For a structure having 4 S atoms out of total 32 atoms in its unit cell, the lowest structure-solvable resolution is 1.5 A, and at this resolution all the atoms are individually searchable by the sR1 method (a specialized form of the pR1 method in which the partial structure contains a single atom). For the other two samples, which have 46 and 156 C atoms in their unit cells, respectively, the lowest structure-solvable resolutions are 1.5 A and 1.2 A, respectively, and both require a combination of the pR1 and the sR1 methods to determine their structures at these resolution limits. In all three cases, the usual choice of method for solving a small-molecule crystal structure, namely, the SHELXT program, is not applicable. Therefore, the pR1 method complements the SHELXT for determination of a small-molecule crystal structure at these lowest resolution limits.

cond-mat.mtrl-sci↗

arXiv2024

LMFNet: An Efficient Multimodal Fusion Approach for Semantic Segmentation in High-Resolution Remote Sensing

Despite the rapid evolution of semantic segmentation for land cover classification in high-resolution remote sensing imagery, integrating multiple data modalities such as Digital Surface Model (DSM), RGB, and Near-infrared (NIR) remains a challenge. Current methods often process only two types of data, missing out on the rich information that additional modalities can provide. Addressing this gap, we propose a novel \textbf{L}ightweight \textbf{M}ultimodal data \textbf{F}usion \textbf{Net}work (LMFNet) to accomplish the tasks of fusion and semantic segmentation of multimodal remote sensing images. LMFNet uniquely accommodates various data types simultaneously, including RGB, NirRG, and DSM, through a weight-sharing, multi-branch vision transformer that minimizes parameter count while ensuring robust feature extraction. Our proposed multimodal fusion module integrates a \textit{Multimodal Feature Fusion Reconstruction Layer} and \textit{Multimodal Feature Self-Attention Fusion Layer}, which can reconstruct and fuse multimodal features. Extensive testing on public datasets such as US3D, ISPRS Potsdam, and ISPRS Vaihingen demonstrates the effectiveness of LMFNet. Specifically, it achieves a mean Intersection over Union ($mIoU$) of 85.09\% on the US3D dataset, marking a significant improvement over existing methods. Compared to unimodal approaches, LMFNet shows a 10\% enhancement in $mIoU$ with only a 0.5M increase in parameter count. Furthermore, against bimodal methods, our approach with trilateral inputs enhances $mIoU$ by 0.46 percentage points.

cs.CV↗

arXiv2024

Phase transition like behaviors of Propagation of Passenger Stranding phenomena in Subway Networks

The subway as the most important transportation for daily urban commuting is a typical non-equilibrium complex system, composed of 2 types of basic units with service relationship. One challenge to operate it is passengers be stranded at stations, which arise from the spatiotemporal mismatch of supply scale and demand scale. More seriously, there is a special phenomenon of the propagation of passenger stranding (PPS) by forming stranded stations clusters, which significantly reduces the service efficiency. In this study, Beijing subway as an example is studied to reveal the nature of PPS phenomena from a view point of statistical physics. The simulation results demonstrate phase-transition-like behaviors depending on the ratio of service supply scale and demand scale. The transition point can quantitatively characterize the resilience failure threshold of service. The eigen microstate method is used to extracting the fundamental patterns of PPS phenomena. Moreover, this study offers a theoretical foundation for strategies to improve service, such as topological planning and train timetable optimization. The methodology developed in present work has significant implications for study of other service systems.

physics.soc-ph↗

arXiv2024

Semi-supervised Medical Image Segmentation Method Based on Cross-pseudo Labeling Leveraging Strong and Weak Data Augmentation Strategies

Traditional supervised learning methods have historically encountered certain constraints in medical image segmentation due to the challenging collection process, high labeling cost, low signal-to-noise ratio, and complex features characterizing biomedical images. This paper proposes a semi-supervised model, DFCPS, which innovatively incorporates the Fixmatch concept. This significantly enhances the model's performance and generalizability through data augmentation processing, employing varied strategies for unlabeled data. Concurrently, the model design gives appropriate emphasis to the generation, filtration, and refinement processes of pseudo-labels. The novel concept of cross-pseudo-supervision is introduced, integrating consistency learning with self-training. This enables the model to fully leverage pseudo-labels from multiple perspectives, thereby enhancing training diversity. The DFCPS model is compared with both baseline and advanced models using the publicly accessible Kvasir-SEG dataset. Across all four subdivisions containing different proportions of unlabeled data, our model consistently exhibits superior performance. Our source code is available at https://github.com/JustlfC03/DFCPS.

cs.CV↗

arXiv2024

REDriver: Runtime Enforcement for Autonomous Vehicles

Autonomous driving systems (ADSs) integrate sensing, perception, drive control, and several other critical tasks in autonomous vehicles, motivating research into techniques for assessing their safety. While there are several approaches for testing and analysing them in high-fidelity simulators, ADSs may still encounter additional critical scenarios beyond those covered once they are deployed on real roads. An additional level of confidence can be established by monitoring and enforcing critical properties when the ADS is running. Existing work, however, is only able to monitor simple safety properties (e.g., avoidance of collisions) and is limited to blunt enforcement mechanisms such as hitting the emergency brakes. In this work, we propose REDriver, a general and modular approach to runtime enforcement, in which users can specify a broad range of properties (e.g., national traffic laws) in a specification language based on signal temporal logic (STL). REDriver monitors the planned trajectory of the ADS based on a quantitative semantics of STL, and uses a gradient-driven algorithm to repair the trajectory when a violation of the specification is likely. We implemented REDriver for two versions of Apollo (i.e., a popular ADS), and subjected it to a benchmark of violations of Chinese traffic laws. The results show that REDriver significantly improves Apollo's conformance to the specification with minimal overhead.

cs.SE↗

arXiv2023

Experimental test of the Rosenzweig-Porter model for the transition from Poisson to Gaussian unitary ensemble statistics

We report on an experimental investigation of the transition of a quantum system with integrable classical dynamics to one with violated time-reversal (T) invariance and chaotic classical counterpart. High-precision experiments are performed with a flat superconducting microwave resonator with circular shape in which T-invariance violation and chaoticity are induced by magnetizing a ferrite disk placed at its center, which above the cutoff frequency of the first transverse-electric mode acts as a random potential. We determine a complete sequence of approx. 1000 eigenfrequencies and find good agreement with analytical predictions for the spectral properties of the Rosenzweig-Porter (RP) model, which interpolates between Poisson statistics expected for typical integrable systems and Gaussian unitary ensemble statistics predicted for chaotic systems with violated T invariance. Furthermore, we combine the RP model and the Heidelberg approach for quantum-chaotic scattering to construct a random-matrix model for the scattering (S) matrix of the corresponding open quantum system and show that it perfectly reproduces the fluctuation properties of the measured S matrix of the microwave resonator.

quant-ph↗

arXiv2023

Introducing the Single-Atom Real-Space Global Minimization Method for Solving Small Structures in Single Crystal X-ray Crystallography

A new method for solving small X-ray structures with up to couple of hundreds of atoms in the unit cell has been developed. The method works by locating atoms one-by-one via global minimization of a newly defined single-atom R1 factor in real-space. In total forty test cases (of twenty samples), every resulting model has at least 52% atoms located correctly, and in more than half of the cases this percentage is 90% and higher. For most heavier-atoms-containing (heavier than Si) small structures it is sufficient to use a single-solution strategy (using the as-collected reflection intensities). But for most lighter-atoms-only (C, N, O and F) small structures it is necessary to try multi-solution strategy: try different B values for modifying the reflection intensities by multiplying them with exp(B s2) before feeding to the method, where s = sinθ/λ, and pick the best solution. This method has been demonstrated to be very effective for locating heavier atoms, so, it has potential applications in macromolecular crystallography by assisting determination of heavy-atom substructures.

physics.data-an↗

arXiv2023

Optimal Hub Placement and Deadlock-Free Routing for Payment Channel Network Scalability

As a promising implementation model of payment channel network (PCN), payment channel hub (PCH) could achieve high throughput by providing stable off-chain transactions through powerful hubs. However, existing PCH schemes assume hubs preplaced in advance, not considering payment requests' distribution and may affect network scalability, especially network load balancing. In addition, current source routing protocols with PCH allow each sender to make routing decision on his/her own request, which may have a bad effect on performance scalability (e.g., deadlock) for not considering other senders' requests. This paper proposes a novel multi-PCHs solution with high scalability. First, we are the first to study the PCH placement problem and propose optimal/approximation solutions with load balancing for small-scale and large-scale scenarios, by trading off communication costs among participants and turning the original NP-hard problem into a mixed-integer linear programming (MILP) problem solving by supermodular techniques. Then, on global network states and local directly connected clients' requests, a routing protocol is designed for each PCH with a dynamic adjustment strategy on request processing rates, enabling high-performance deadlock-free routing. Extensive experiments show that our work can effectively balance the network load, and improve the performance on throughput by 29.3% on average compared with state-of-the-arts.

cs.DC↗

arXiv2023

Time-reversal Invariance Violation and Quantum Chaos Induced by Magnetization in Ferrite-Loaded Resonators

We investigate the fluctuation properties in the eigenfrequency spectra of flat cylindrical microwave cavities that are homogeneously filled with magnetized ferrite. These studies are motivated by experiments in which only small pieces of ferrite were embedded in the cavity and magnetized with an external static magnetic field to induce partial time-reversal (T ) invariance violation. We use two different shapes of the cavity, one exhibiting an integrable wave dynamics, the other one a chaotic one. We demonstrate that in the frequency region where only transverse-magnetic modes exist, the magnetization of the ferrites has no effect on the wave dynamics and does not induce T -invariance violation whereas it is fully violated above the cutoff frequency of the first transverse-electric mode. Above all, independently of the shape of the resonator, it induces a chaotic wave dynamics in that frequency range in the sense that for both resonator geometries the spectral properties coincide with those of quantum systems with a chaotic classical dynamics and same invariance properties under application of the generalized T operator associated with the resonator geometry.

nlin.CD↗

arXiv2023

Properties of the eigenmodes and quantum-chaotic scattering in a superconducting microwave Dirac billiard with threefold rotational symmetry

We report on experimental studies that were performed with a microwave Dirac billiard (DB), that is, a flat resonator containing metallic cylinders arranged on a triangular grid, whose shape has a threefold rotational C3 symmetry. Its band structure exhibits two Dirac points (DPs) that are separated by a nearly flat band. We present a procedure which we employed to identify eigenfrequencies and to separate the eigenstates according to their transformation properties under rotation by 60 degree into the three C3 subspaces. This allows us to verify previous numerical results of Ref. [W.Zhang and B. Dietz, Phys. Rev. B 104, 064310 (2021)], thus confirming that the properties of the eigenmodes coincide with those of artificial graphene around the lower DP, and are well described by a tight-binding model (TBM) for a honeycomb-kagome lattice of corresponding shape. Above all, we investigate properties of the wave-function components in terms of the fluctuation properties of the measured scattering matrix, which are numerically not accessible. They are compared to random-matrix theory predictions for quantum-chaotic scattering systems exhibiting extended or localized states in the interaction region, that is, the DB. Even in regions, where the wave functions are localized, the spectral properties coincide with those of typical quantum systems with chaotic classical counterpart.

physics.class-ph↗

arXiv2022

Intensity modulated proton arc therapy via geometry-based energy selection for ependymoma

We developed a novel method of creating intensity modulated proton arc therapy (IMPAT) plans that uses computing resources efficiently and may offer a dosimetric benefit for patients with ependymoma or similar tumor geometries. Our IMPAT planning method consists of a geometry-based energy selection step with major scanning spot contributions as inputs computed using ray-tracing and single-Gaussian approximation of lateral spot profiles. Based on the geometric relation of scanning spots and dose voxels, our energy selection module selects a minimum set of energy layers at each gantry angle such that each target voxel is covered by sufficient scanning spots as specified by the planner, with dose contributions above the specified threshold. Finally, IMPAT plans are generated by robustly optimizing scanning spots of the selected energy layers using a commercial proton treatment planning system. The IMPAT plan quality was assessed for four ependymoma patients. Reference three-field IMPT plans were created with similar planning objective functions and compared with the IMPAT plans. In all plans, the prescribed dose covered 95% of the clinical target volume (CTV) while maintaining similar maximum doses for the brainstem. While IMPAT and IMPT achieved comparable plan robustness, the IMPAT plans achieved better homogeneity and conformity than the IMPT plans. The IMPAT plans also exhibited higher relative biological effectiveness (RBE) enhancement than did the corresponding reference IMPT plans for the CTV in all four patients and brainstem in three of them. The proposed method demonstrated potential as an efficient technique for IMPAT planning and may offer a dosimetric benefit for patients with ependymoma or tumors in close proximity to critical organs. IMPAT plans created using this method had elevated RBE enhancement associated with increased linear energy transfer.

physics.med-ph↗

arXiv2022

Understanding Real-world Threats to Deep Learning Models in Android Apps

Famous for its superior performance, deep learning (DL) has been popularly used within many applications, which also at the same time attracts various threats to the models. One primary threat is from adversarial attacks. Researchers have intensively studied this threat for several years and proposed dozens of approaches to create adversarial examples (AEs). But most of the approaches are only evaluated on limited models and datasets (e.g., MNIST, CIFAR-10). Thus, the effectiveness of attacking real-world DL models is not quite clear. In this paper, we perform the first systematic study of adversarial attacks on real-world DNN models and provide a real-world model dataset named RWM. Particularly, we design a suite of approaches to adapt current AE generation algorithms to the diverse real-world DL models, including automatically extracting DL models from Android apps, capturing the inputs and outputs of the DL models in apps, generating AEs and validating them by observing the apps' execution. For black-box DL models, we design a semantic-based approach to build suitable datasets and use them for training substitute models when performing transfer-based attacks. After analyzing 245 DL models collected from 62,583 real-world apps, we have a unique opportunity to understand the gap between real-world DL models and contemporary AE generation algorithms. To our surprise, the current AE generation algorithms can only directly attack 6.53% of the models. Benefiting from our approach, the success rate upgrades to 47.35%.

cs.CR↗

arXiv2022

Experimental study of closed and open microwave waveguide graphs with preserved and partially violated time-reversal invariance

We report on experiments that were performed with microwave waveguide systems and demonstrate that in the frequency range of a single transversal mode they may serve as a model for closed and open quantum graphs. These consist of bonds that are connected at vertices. On the bonds, they are governed by the one-dimensional Schrödinger equation with boundary conditions imposed at the vertices. The resulting transport properties through the vertices may be expressed in terms of a vertex scattering matrix. Quantum graphs with incommensurate bond lengths attracted interest within the field of quantum chaos because, depending on the characteristics of the vertex scattering matrix, its wave dynamic may exhibit features of a typical quantum system with chaotic counterpart. In distinction to microwave networks, which serve as an experimental model of quantum graphs with Neumann boundary conditions, the vertex scattering matrices associated with a waveguide system depend on the wavenumber and the wave functions can be determined experimentally. We analyze the spectral properties of microwave waveguide systems with preserved and partially violated time-reversal invariance, and the properties of the associated wave functions. Furthermore, we study properties of the scattering matrix describing the measurement process within the frame work of random matrix theory for quantum chaotic scattering systems.

quant-ph↗

arXiv2022

Automatic segmentation of meniscus based on MAE self-supervision and point-line weak supervision paradigm

Medical image segmentation based on deep learning is often faced with the problems of insufficient datasets and long time-consuming labeling. In this paper, we introduce the self-supervised method MAE(Masked Autoencoders) into knee joint images to provide a good initial weight for the segmentation model and improve the adaptability of the model to small datasets. Secondly, we propose a weakly supervised paradigm for meniscus segmentation based on the combination of point and line to reduce the time of labeling. Based on the weak label ,we design a region growing algorithm to generate pseudo-label. Finally we train the segmentation network based on pseudo-labels with weight transfer from self-supervision. Sufficient experimental results show that our proposed method combining self-supervision and weak supervision can almost approach the performance of purely fully supervised models while greatly reducing the required labeling time and dataset size.

cs.CV↗

arXiv2022

An Industrial Experience Report on Retro-inspection

To reinforce the quality of code delivery, especially to improve future coding quality, one global Information and Communication Technology (ICT) enterprise has institutionalized a retrospective style inspection (namely retro-inspection), which is similar to Fagan inspection but differs in terms of stage, participants, etc. This paper reports an industrial case study that aims to investigate the experiences and lessons from this software practice. To this end, we collected and analyzed various empirical evidence for data triangulation. The results reflect that retro-inspection distinguishes itself from peer code review by identifying more complicated and underlying defects, providing more indicative and suggestive comments. Many experienced inspectors indicate defects together with their rationale behind and offer suggestions for correction and prevention. As a result, retro-inspection can benefit not only quality assurance (like Fagan inspection), but also internal audit, inter-division communication, and competence promotion. On the other side, we identify several lessons of retro-inspection at this stage, e.g., developers' acceptance and organizers' predicament, for next-step improvement of this practice. To be specific, some recommendations are discussed for retro-inspection, e.g., more adequate preparation and more careful publicity. This study concludes that most of the expected benefits of retro-inspection can be empirically confirmed in this enterprise and its value on the progress to continuous maturity can be recognized organization-wide. The experiences on executing this altered practice in a large enterprise provide reference value on code quality assurance to other software organizations.

cs.SE↗