arXiv subjects

Zhigang Yang

Publications and source records attributed to Zhigang Yang.

6 recordsLinked to original sources

arXiv2026

Multi-Granularity Conformal Prediction for Reliable Neural-Operator Automotive Aerodynamic Surrogates

High-fidelity computational fluid dynamics (CFD) provides detailed aerodynamic data for vehicle design, but its cost limits design iteration. Neural-operator surrogates reduce this cost, yet their deterministic predictions do not indicate when a geometry or surface region is reliable. This study develops a conformal-prediction framework for reliability-aware automotive aerodynamic surrogate modeling on the DrivAerML dataset. GeoTransolver is the main backbone, while Transolver assesses transfer across neural-operator architectures. For drag coefficient prediction, conformalized quantile regression constructs calibrated case-level intervals. For surface pressure and wall shear stress (WSS), point prediction is combined with residual-scale estimation and residual-normalized conformal calibration to obtain spatially adaptive intervals. Global absolute, point-adaptive normalized, and case-wise normalized calibration are compared under split and cross-validation-assisted out-of-fold protocols. All experiments target 90% nominal coverage. Conformal calibration corrects the under-coverage of raw drag-coefficient quantile intervals, while out-of-fold score aggregation reduces the Monte Carlo coverage standard deviation from 10.41 to 3.10 percentage points. For surface fields, point-adaptive normalized calibration yields the narrowest near-nominal intervals, reducing mean width by 22.68% for pressure and 25.35%--27.09% for WSS under the out-of-fold protocol. Case-wise normalized calibration is more conservative but improves vehicle-level reliability. Smoothness regularization reduces the residual-scale local-variation score by 74.29% and lowers interval widths without material coverage loss. The framework converts deterministic neural-operator outputs into calibrated reliability indicators for prioritizing uncertain vehicle geometries and surface regions in follow-up CFD verification.

physics.flu-dyn↗

arXiv2026

Near-real-time, meter-scale 3D urban wind modeling for low-altitude micrometeorology: numerical verification of a GPU-accelerated lattice Boltzmann framework

This study presents a near-real-time, meter-scale three-dimensional urban wind simulation framework for low-altitude flight events in complex urban meteorological environments. It reconstructs high-resolution wind fields by combining sparse observations with efficient microscale flow modeling. The framework integrates lattice Boltzmann method large-eddy simulation (LBM-LES), high-fidelity urban morphology reconstruction that explicitly resolves real building details, and observation-driven boundary assimilation into a rapid end-to-end pipeline for realistic urban domains. Multi-site Doppler lidar measurements from dense urban Guangzhou, China, are used for evaluation. The system reconstructs three-dimensional wind fields at 5 m resolution over kilometer-scale domains within minutes. Robustness and accuracy are tested through controlled observation reduction, independent validation against withheld lidar stations, and sensitivity analyses of grid resolution and precursor domain extent. Results show stable reproduction of vertical wind structures and key local flow features under complex morphology and limited observations, providing a scalable pathway for near-real-time urban wind reconstruction.

physics.flu-dyn↗

arXiv2026

A Large-Scale Dataset and a New Method for RemoteSensing Traffic Object Segmentation

Remote sensing imagery plays a crucial role in evaluating regional transportation capacity. However, existing segmentation datasets often lack diversity in object categories and scenes, limiting the ability of models to comprehensively evaluate trans portation capacity in real-world scenes. To alleviate this gap, we construct a large-scale and diverse dataset for transportation object segmentation, named as NWPU-Traffic. This dataset encompass four traffic object categories (car, airplane, ship, and train) and a wide range of scenes from 49 cities across 7 countries, with instance-level annotations to ensure precise segmentation of individual objects, which bridges critical shortcomings in resolution and scene diversity in existing datasets. Leveraging this dataset, we establish a benchmark with several popular segmentation networks. Furthermore, we propose a novel segmentation method that leverages spatial-channel preserving feature interaction and an adaptive feature decoder, enabling robust segmentation across varying scales and complex environments. Extensive experiments and ablation studies validate the effectiveness of our approach. The dataset and code are publicly available at https://github.com/CVer-Yang/NWPU-Traffic.

cs.CV↗

arXiv2025

FeatureLens: A Highly Generalizable and Interpretable Framework for Detecting Adversarial Examples Based on Image Features

Although the remarkable performance of deep neural networks (DNNs) in image classification, their vulnerability to adversarial attacks remains a critical challenge. Most existing detection methods rely on complex and poorly interpretable architectures, which compromise interpretability and generalization. To address this, we propose FeatureLens, a lightweight framework that acts as a lens to scrutinize anomalies in image features. Comprising an Image Feature Extractor (IFE) and shallow classifiers (e.g., SVM, MLP, or XGBoost) with model sizes ranging from 1,000 to 30,000 parameters, FeatureLens achieves high detection accuracy ranging from 97.8% to 99.75% in closed-set evaluation and 86.17% to 99.6% in generalization evaluation across FGSM, PGD, CW, and DAmageNet attacks, using only 51 dimensional features. By combining strong detection performance with excellent generalization, interpretability, and computational efficiency, FeatureLens offers a practical pathway toward transparent and effective adversarial defense.

cs.CV↗

arXiv2025

A Large-Scale Referring Remote Sensing Image Segmentation Dataset and Benchmark

Referring Remote Sensing Image Segmentation is a complex and challenging task that integrates the paradigms of computer vision and natural language processing. Existing datasets for RRSIS suffer from critical limitations in resolution, scene diversity, and category coverage, which hinders the generalization and real-world applicability of refer segmentation models. To facilitate the development of this field, we introduce NWPU-Refer, the largest and most diverse RRSIS dataset to date, comprising 15,003 high-resolution images (1024-2048px) spanning 30+ countries with 49,745 annotated targets supporting single-object, multi-object, and non-object segmentation scenarios. Additionally, we propose the Multi-scale Referring Segmentation Network (MRSNet), a novel framework tailored for the unique demands of RRSIS. MRSNet introduces two key innovations: (1) an Intra-scale Feature Interaction Module (IFIM) that captures fine-grained details within each encoder stage, and (2) a Hierarchical Feature Interaction Module (HFIM) to enable seamless cross-scale feature fusion, preserving spatial integrity while enhancing discriminative power. Extensive experiments conducte on the proposed NWPU-Refer dataset demonstrate that MRSNet achieves state-of-the-art performance across multiple evaluation metrics, validating its effectiveness. The dataset and code are publicly available at https://github.com/CVer-Yang/NWPU-Refer.

cs.CV↗

arXiv2020

Explorative gradient method for active drag reduction of the fluidic pinball and slanted Ahmed body

We address a challenge of active flow control: the optimization of many actuation parameters guaranteeing fast convergence and avoiding suboptimal local minima. This challenge is addressed by a new optimizer, called explorative gradient method (EGM). EGM alternatively performs one exploitive downhill simplex step and an explorative Latin hypercube sampling iteration. Thus, the convergence rate of a gradient based method is guaranteed while, at the same time, better minima are explored. For an analytical multi-modal test function, EGM is shown to significantly outperform the downhill simplex method, the random restart variant, Latin hypercube sampling, Monte Carlo iterations and the genetic algorithm. EGM is applied to minimize the net drag power of the two-dimensional fluidic pinball benchmark with three cylinder rotations as actuation parameters. The net drag power is reduced by $40\%$ employing direct numerical simulations at a Reynolds number of $100$ based on the cylinder diameter. This optimal actuation leads to $98\%$ drag reduction employing Coanda forcing for boat tailing and partial stabilization of vortex shedding. The price is an actuation energy corresponding to $58\%$ of the unforced parasitic drag power. EGM is also used to minimize drag of the $35^\circ$ slanted Ahmed body employing distributed steady blowing with 10 inputs. $17\%$ drag reduction are achieved using Reynolds-Averaged Navier-Stokes simulations (RANS) at the Reynolds number $Re_H=1.9 \times 10^5$ based on the height of the Ahmed body. The optimal actuation emulates boat tailing by inward-directed blowing with velocities which are comparable to the oncoming velocity. We expect that EGM will be employed as efficient optimizer in many future active flow control plants.

physics.flu-dyn↗