arXiv subjects

Ke Ma

Publications and source records attributed to Ke Ma.

At least 73 records · Page 4Linked to original sources

arXiv2025

A Unified Longitudinal Trajectory Dataset for Automated Vehicle

Automated Vehicles (AVs) promise significant advances in transportation. Critical to these improvements is understanding AVs' longitudinal behavior, relying heavily on real-world trajectory data. Existing open-source trajectory datasets of AV, however, often fall short in refinement, reliability, and completeness, hindering effective performance metrics analysis and model development. This study addresses these challenges by creating a Unified Longitudinal TRAjectory dataset for AVs (Ultra-AV) to analyze their microscopic longitudinal driving behaviors. This dataset compiles data from 13 distinct sources, encompassing various AV types, test sites, and experiment scenarios. We established a three-step data processing: 1. extraction of longitudinal trajectory data, 2. general data cleaning, and 3. data-specific cleaning to obtain the longitudinal trajectory data and car-following trajectory data. The validity of the processed data is affirmed through performance evaluations across safety, mobility, stability, and sustainability, along with an analysis of the relationships between variables in car-following models. Our work not only furnishes researchers with standardized data and metrics for longitudinal AV behavior studies but also sets guidelines for data collection and model development.

cs.RO↗

arXiv2025

SURGEON: Memory-Adaptive Fully Test-Time Adaptation via Dynamic Activation Sparsity

Despite the growing integration of deep models into mobile terminals, the accuracy of these models declines significantly due to various deployment interferences. Test-time adaptation (TTA) has emerged to improve the performance of deep models by adapting them to unlabeled target data online. Yet, the significant memory cost, particularly in resource-constrained terminals, impedes the effective deployment of most backward-propagation-based TTA methods. To tackle memory constraints, we introduce SURGEON, a method that substantially reduces memory cost while preserving comparable accuracy improvements during fully test-time adaptation (FTTA) without relying on specific network architectures or modifications to the original training procedure. Specifically, we propose a novel dynamic activation sparsity strategy that directly prunes activations at layer-specific dynamic ratios during adaptation, allowing for flexible control of learning ability and memory cost in a data-sensitive manner. Among this, two metrics, Gradient Importance and Layer Activation Memory, are considered to determine the layer-wise pruning ratios, reflecting accuracy contribution and memory efficiency, respectively. Experimentally, our method surpasses the baselines by not only reducing memory usage but also achieving superior accuracy, delivering SOTA performance across diverse datasets, architectures, and tasks.

cs.CV↗

arXiv2025

Divide and Conquer: Heterogeneous Noise Integration for Diffusion-based Adversarial Purification

Existing diffusion-based purification methods aim to disrupt adversarial perturbations by introducing a certain amount of noise through a forward diffusion process, followed by a reverse process to recover clean examples. However, this approach is fundamentally flawed: the uniform operation of the forward process across all pixels compromises normal pixels while attempting to combat adversarial perturbations, resulting in the target model producing incorrect predictions. Simply relying on low-intensity noise is insufficient for effective defense. To address this critical issue, we implement a heterogeneous purification strategy grounded in the interpretability of neural networks. Our method decisively applies higher-intensity noise to specific pixels that the target model focuses on while the remaining pixels are subjected to only low-intensity noise. This requirement motivates us to redesign the sampling process of the diffusion model, allowing for the effective removal of varying noise levels. Furthermore, to evaluate our method against strong adaptative attack, our proposed method sharply reduces time cost and memory usage through a single-step resampling. The empirical evidence from extensive experiments across three datasets demonstrates that our method outperforms most current adversarial training and purification techniques by a substantial margin.

cs.CV↗

arXiv2025

Evolution-based Region Adversarial Prompt Learning for Robustness Enhancement in Vision-Language Models

Large pre-trained vision-language models (VLMs), such as CLIP, demonstrate impressive generalization but remain highly vulnerable to adversarial examples (AEs). Previous work has explored robust text prompts through adversarial training, achieving some improvement in both robustness and generalization. However, they primarily rely on singlegradient direction perturbations (e.g., PGD) to generate AEs, which lack diversity, resulting in limited improvement in adversarial robustness. To address these limitations, we propose an evolution-based region adversarial prompt tuning method called ER-APT, which combines gradient methods with genetic evolution to generate more diverse and challenging AEs. In each training iteration, we first generate AEs using traditional gradient-based methods. Subsequently, a genetic evolution mechanism incorporating selection, mutation, and crossover is applied to optimize the AEs, ensuring a broader and more aggressive perturbation distribution.The final evolved AEs are used for prompt tuning, achieving region-based adversarial optimization instead of conventional single-point adversarial prompt tuning. We also propose a dynamic loss weighting method to adjust prompt learning efficiency for accuracy and robustness. Experimental evaluations on various benchmark datasets demonstrate the superiority of our proposed method, outperforming stateof-the-art APT methods. The code is released at https://github.com/jiaxiaojunQAQ/ER-APT.

cs.CV↗

arXiv2025

CrowdHMTware: A Cross-level Co-adaptation Middleware for Context-aware Mobile DL Deployment

There are many deep learning (DL) powered mobile and wearable applications today continuously and unobtrusively sensing the ambient surroundings to enhance all aspects of human lives.To enable robust and private mobile sensing, DL models are often deployed locally on resource-constrained mobile devices using techniques such as model compression or offloading.However, existing methods, either front-end algorithm level (i.e. DL model compression/partitioning) or back-end scheduling level (i.e. operator/resource scheduling), cannot be locally online because they require offline retraining to ensure accuracy or rely on manually pre-defined strategies, struggle with dynamic adaptability.The primary challenge lies in feeding back runtime performance from the back-end level to the front-end level optimization decision. Moreover, the adaptive mobile DL model porting middleware with cross-level co-adaptation is less explored, particularly in mobile environments with diversity and dynamics. In response, we introduce CrowdHMTware, a dynamic context-adaptive DL model deployment middleware for heterogeneous mobile devices. It establishes an automated adaptation loop between cross-level functional components, i.e. elastic inference, scalable offloading, and model-adaptive engine, enhancing scalability and adaptability. Experiments with four typical tasks across 15 platforms and a real-world case study demonstrate that CrowdHMTware can effectively scale DL model, offloading, and engine actions across diverse platforms and tasks. It hides run-time system issues from developers, reducing the required developer expertise.

cs.LG↗

arXiv2025

MAMMOTH-Subaru IV. Large Scale Structure and Clustering Analysis of Ly$α$ Emitters and Ly$α$ Blobs at $z=2.2-2.3$

We report the large scale structure and clustering analysis of Ly$α$ emitters (LAEs) and Ly$α$ blobs (LABs) at $z=2.2-2.3$. Using 3,341 LAEs, 117 LABs, and 58 bright (Ly$α$ luminosity $L_{\rm Lyα}>10^{43.4}$ erg s$^{-1}$) LABs at $z=2.2-2.3$ selected with Subaru/Hyper Suprime-Cam, we calculate the LAE overdensity to investigate the large scale structure at $z=2$. We show that $79\%$ LABs and $83\%$ bright LABs locate in overdense regions, which is consistent with the trend found by previous studies that LABs generally locate in overdense regions. We find that one of our 8 fields dubbed J1349 contains $39/117\approx33\%$ of our LABs and $22/58\approx38\%$ of our bright LABs. A unique and overdense $24'\times12'$ ($40\times20$ comoving Mpc$^2$) region (J1347 protocluster) has 12 LABs (8 bright LABs). By comparing to SSA22 that is one of the most overdense LAB regions found by previous studies, we show that the J1347 protocluster region has a higher bright LAB density than the SSA22 protocluster region with a $1σ$ significance. We calculate the angular correlation functions (ACFs) of LAEs and LABs in the unique J1349 field and fit the ACFs with a power-law function to measure the slopes. The bright LABs show a $5σ$ larger slope suggesting that bright LABs are more clustered than faint LAEs. Our LABs have a large galaxy bias of $\sim 5-7$, which suggests that LABs generally reside in more massive dark matter halos (halo masses $M \gtrsim 10^{13}$ M$_{\odot}$) than faint LAEs.

astro-ph.GA↗

arXiv2025

Near-Field Communications with Block-Dominant Compressed Sensing: Fundamentals, Approaches, and Future Directions

In the context of extremely large-scale antenna arrays deployed in sixth-generation (6G) mobile networks, near-field (NF) communications have gained considerable attention. Unlike the planar waves formulated in the far-field, electromagnetic radiation propagates as spherical waves in the NF. This alteration affects the NF channel characteristics, particularly resulting in weak sparsity in angular-domain NF channels, which poses tricky challenges to the application of compressed sensing (CS). Motivated by these facts, the block-dominant compressed sensing (BD-CS) techniques are proposed to assist NF communications. This article starts with the introduction on why block sparsity exists in the distance-limited NF region. Then, block-dominant side-information (BD-SI) is exploited to facilitate the actual NF communication implementation. While BD-CS shows promise in providing exceptional channel estimation accuracy and high spectral efficiency, several key challenges, opportunities, and practical implementation issues in NF communications need careful consideration.

eess.SP↗

arXiv2025

Assessing Markov Property in Driving Behaviors: Insights from Statistical Tests

The Markov property serves as a foundational assumption in most existing work on vehicle driving behavior, positing that future states depend solely on the current state, not the series of preceding states. This study validates the Markov properties of vehicle trajectories for both Autonomous Vehicles (AVs) and Human-driven Vehicles (HVs). A statistical method used to test whether time series data exhibits Markov properties is applied to examine whether the trajectory data possesses Markov characteristics. t test and F test are additionally introduced to characterize the differences in Markov properties between AVs and HVs. Based on two public trajectory datasets, we investigate the presence and order of the Markov property of different types of vehicles through rigorous statistical tests. Our findings reveal that AV trajectories generally exhibit stronger Markov properties compared to HV trajectories, with a higher percentage conforming to the Markov property and lower Markov orders. In contrast, HV trajectories display greater variability and heterogeneity in decision-making processes, reflecting the complex perception and information processing involved in human driving. These results have significant implications for the development of driving behavior models, AV controllers, and traffic simulation systems. Our study also demonstrates the feasibility of using statistical methods to test the presence of Markov properties in driving trajectory data.

cs.LG↗

arXiv2024

Three mechanistically different variability and noise sources in the trial-to-trial fluctuations of responses to brain stimulation

Motor-evoked potentials (MEPs) are among the few directly observable responses to external brain stimulation and serve a variety of applications, often in the form of input-output (IO) curves. Previous statistical models with two variability sources inherently consider the small MEPs at the low-side plateau as part of the neural recruitment properties. However, recent studies demonstrated that small MEP responses under resting conditions are contaminated and over-shadowed by background noise of mostly technical quality, e.g., caused by the amplifier, and suggested that the neural recruitment curve should continue below this noise level. This work intends to separate physiological variability from background noise and improve the description of recruitment behaviour. We developed a triple-variability-source model around a logarithmic logistic function without a lower plateau and incorporated an additional source for background noise. Compared to models with two or fewer variability sources, our approach better described IO characteristics, evidenced by lower Bayesian Information Criterion scores across all subjects and pulse shapes. The model independently extracted hidden variability information across the stimulated neural system and isolated it from background noise, which led to an accurate estimation of the IO curve parameters. This new model offers a robust tool to analyse brain stimulation IO curves in clinical and experimental neuroscience and reduces the risk of spurious results from inappropriate statistical methods. The presented model together with the corresponding calibration method provides a more accurate representation of MEP responses and variability sources, advances our understanding of cortical excitability, and may improve the assessment of neuromodulation effects.

q-bio.NC↗

arXiv2024

Exploring Query Efficient Data Generation towards Data-free Model Stealing in Hard Label Setting

Data-free model stealing involves replicating the functionality of a target model into a substitute model without accessing the target model's structure, parameters, or training data. The adversary can only access the target model's predictions for generated samples. Once the substitute model closely approximates the behavior of the target model, attackers can exploit its white-box characteristics for subsequent malicious activities, such as adversarial attacks. Existing methods within cooperative game frameworks often produce samples with high confidence for the prediction of the substitute model, which makes it difficult for the substitute model to replicate the behavior of the target model. This paper presents a new data-free model stealing approach called Query Efficient Data Generation (\textbf{QEDG}). We introduce two distinct loss functions to ensure the generation of sufficient samples that closely and uniformly align with the target model's decision boundary across multiple classes. Building on the limitation of current methods, which typically yield only one piece of supervised information per query, we propose the query-free sample augmentation that enables the acquisition of additional supervised information without increasing the number of queries. Motivated by theoretical analysis, we adopt the consistency rate metric, which more accurately evaluates the similarity between the substitute and target models. We conducted extensive experiments to verify the effectiveness of our proposed method, which achieved better performance with fewer queries compared to the state-of-the-art methods on the real \textbf{MLaaS} scenario and five datasets.

cs.CR↗

arXiv2024

Slicing Vision Transformer for Flexible Inference

Vision Transformers (ViT) is known for its scalability. In this work, we target to scale down a ViT to fit in an environment with dynamic-changing resource constraints. We observe that smaller ViTs are intrinsically the sub-networks of a larger ViT with different widths. Thus, we propose a general framework, named Scala, to enable a single network to represent multiple smaller ViTs with flexible inference capability, which aligns with the inherent design of ViT to vary from widths. Concretely, Scala activates several subnets during training, introduces Isolated Activation to disentangle the smallest sub-network from other subnets, and leverages Scale Coordination to ensure each sub-network receives simplified, steady, and accurate learning objectives. Comprehensive empirical validations on different tasks demonstrate that with only one-shot training, Scala learns slimmable representation without modifying the original ViT structure and matches the performance of Separate Training. Compared with the prior art, Scala achieves an average improvement of 1.6% on ImageNet-1K with fewer parameters.

cs.CV↗

arXiv2024

AdaScale: Dynamic Context-aware DNN Scaling via Automated Adaptation Loop on Mobile Devices

Deep learning is reshaping mobile applications, with a growing trend of deploying deep neural networks (DNNs) directly to mobile and embedded devices to address real-time performance and privacy. To accommodate local resource limitations, techniques like weight compression, convolution decomposition, and specialized layer architectures have been developed. However, the \textit{dynamic} and \textit{diverse} deployment contexts of mobile devices pose significant challenges. Adapting deep models to meet varied device-specific requirements for latency, accuracy, memory, and energy is labor-intensive. Additionally, changing processor states, fluctuating memory availability, and competing processes frequently necessitate model re-compression to preserve user experience. To address these issues, we introduce AdaScale, an elastic inference framework that automates the adaptation of deep models to dynamic contexts. AdaScale leverages a self-evolutionary model to streamline network creation, employs diverse compression operator combinations to reduce the search space and improve outcomes, and integrates a resource availability awareness block and performance profilers to establish an automated adaptation loop. Our experiments demonstrate that AdaScale significantly enhances accuracy by 5.09%, reduces training overhead by 66.89%, speeds up inference latency by 1.51 to 6.2 times, and lowers energy costs by 4.69 times.

cs.AI↗

arXiv2024

Decentralized Network Topology Design for Task Offloading in Mobile Edge Computing

The rise of delay-sensitive yet computing-intensive Internet of Things (IoT) applications poses challenges due to the limited processing power of IoT devices. Mobile Edge Computing (MEC) offers a promising solution to address these challenges by placing computing servers close to end users. Despite extensive research on MEC, optimizing network topology to improve computational efficiency remains underexplored. Recognizing the critical role of network topology, we introduce a novel decentralized network topology design strategy for task offloading (DNTD-TO) that jointly considers topology design and task allocation. Inspired by communication and sensor networks, DNTD-TO efficiently constructs three-layered network structures for task offloading and generates optimal task allocations for these structures. Comparisons with existing topology design methods demonstrate the promising performance of our approach.

cs.NI↗

arXiv2024

Semantic-Aligned Adversarial Evolution Triangle for High-Transferability Vision-Language Attack

Vision-language pre-training (VLP) models excel at interpreting both images and text but remain vulnerable to multimodal adversarial examples (AEs). Advancing the generation of transferable AEs, which succeed across unseen models, is key to developing more robust and practical VLP models. Previous approaches augment image-text pairs to enhance diversity within the adversarial example generation process, aiming to improve transferability by expanding the contrast space of image-text features. However, these methods focus solely on diversity around the current AEs, yielding limited gains in transferability. To address this issue, we propose to increase the diversity of AEs by leveraging the intersection regions along the adversarial trajectory during optimization. Specifically, we propose sampling from adversarial evolution triangles composed of clean, historical, and current adversarial examples to enhance adversarial diversity. We provide a theoretical analysis to demonstrate the effectiveness of the proposed adversarial evolution triangle. Moreover, we find that redundant inactive dimensions can dominate similarity calculations, distorting feature matching and making AEs model-dependent with reduced transferability. Hence, we propose to generate AEs in the semantic image-text feature contrast space, which can project the original feature space into a semantic corpus subspace. The proposed semantic-aligned subspace can reduce the image feature redundancy, thereby improving adversarial transferability. Extensive experiments across different datasets and models demonstrate that the proposed method can effectively improve adversarial transferability and outperform state-of-the-art adversarial attack methods. The code is released at https://github.com/jiaxiaojunQAQ/SA-AET.

cs.CV↗

arXiv2024

Generalized Out-of-distribution Fault Diagnosis (GOOFD) via Internal Contrastive Learning

Fault diagnosis is crucial in monitoring machines within industrial processes. With the increasing complexity of working conditions and demand for safety during production, diverse diagnosis methods are required, and an integrated fault diagnosis system capable of handling multiple tasks is highly desired. However, the diagnosis subtasks are often studied separately, and the current methods still need improvement for such a generalized system. To address this issue, we propose the Generalized Out-of-distribution Fault Diagnosis (GOOFD) framework to integrate diagnosis subtasks. Additionally, a unified fault diagnosis method based on internal contrastive learning and Mahalanobis distance is put forward to underpin the proposed generalized framework. The method involves feature extraction through internal contrastive learning and outlier recognition based on the Mahalanobis distance. Our proposed method can be applied to multiple faults diagnosis tasks and achieve better performance than the existing single-task methods. Experiments are conducted on benchmark and practical process datasets, indicating the effectiveness of the proposed framework.

cs.AI↗

arXiv2024

AdaShadow: Responsive Test-time Model Adaptation in Non-stationary Mobile Environments

On-device adapting to continual, unpredictable domain shifts is essential for mobile applications like autonomous driving and augmented reality to deliver seamless user experiences in evolving environments. Test-time adaptation (TTA) emerges as a promising solution by tuning model parameters with unlabeled live data immediately before prediction. However, TTA's unique forward-backward-reforward pipeline notably increases the latency over standard inference, undermining the responsiveness in time-sensitive mobile applications. This paper presents AdaShadow, a responsive test-time adaptation framework for non-stationary mobile data distribution and resource dynamics via selective updates of adaptation-critical layers. Although the tactic is recognized in generic on-device training, TTA's unsupervised and online context presents unique challenges in estimating layer importance and latency, as well as scheduling the optimal layer update plan. AdaShadow addresses these challenges with a backpropagation-free assessor to rapidly identify critical layers, a unit-based runtime predictor to account for resource dynamics in latency estimation, and an online scheduler for prompt layer update planning. Also, AdaShadow incorporates a memory I/O-aware computation reuse scheme to further reduce latency in the reforward pass. Results show that AdaShadow achieves the best accuracy-latency balance under continual shifts. At low memory and energy costs, Adashadow provides a 2x to 3.5x speedup (ms-level) over state-of-the-art TTA methods with comparable accuracy and a 14.8% to 25.4% accuracy boost over efficient supervised methods with similar latency.

cs.LG↗

arXiv2024

A Multi-Layered Distributed Computing Framework for Enhanced Edge Computing

The rise of the Internet of Things and edge computing has shifted computing resources closer to end-users, benefiting numerous delay-sensitive, computation-intensive applications. To speed up computation, distributed computing is a promising technique that allows parallel execution of tasks across multiple compute nodes. However, current research predominantly revolves around the master-worker paradigm, limiting resource sharing within one-hop neighborhoods. This limitation can render distributed computing ineffective in scenarios with limited nearby resources or constrained/dynamic connectivity. In this paper, we address this limitation by introducing a new distributed computing framework that extends resource sharing beyond one-hop neighborhoods through exploring layered network structures. Our framework involves transforming the network graph into a sink tree and formulating a joint optimization problem based on the layered tree structure for task allocation and scheduling. To solve this problem, we propose two exact methods that find optimal solutions and three heuristic strategies to improve efficiency and scalability. The performances of these methods are analyzed and evaluated through theoretical analyses and comprehensive simulation studies. The results demonstrate their promising performances over the traditional distributed computing and computation offloading strategies.

cs.DC↗

arXiv2024

MAMMOTH-Subaru. II. Diverse Populations of Circumgalactic Ly$α$ Nebulae at Cosmic Noon

Circumgalactic Lyman-alpha (Ly$α$) nebulae are gaseous halos around galaxies exhibiting luminous extended Ly$α$ emission. This work investigates Ly$α$ nebulae from deep imaging of $\sim12~\mathrm{deg}^2$ sky, targeted by the MAMMOTH-Subaru survey. Utilizing the wide-field capability of Hyper Suprime-Cam (HSC), we present one of the largest blind Ly$α$ nebula selections, including QSO nebulae, Ly$α$ blobs, and radio galaxy nebulae down to typical $2σ$ Ly$α$ surface brightness of $(5-10)\times10^{-18}\mathrm{~erg~s^{-1}~cm^{-2}~arcsec^{-2}}$. The sample contains 117 nebulae with Ly$α$ sizes of 40 - 400 kpc, and the most gigantic one spans about 365 kpc, referred to as the Ivory Nebula. Combining multiwavelength data, we investigate diverse nebula populations and associated galaxies. We find a small fraction of Ly$α$ nebulae have QSOs ($\sim7\%$), luminous infrared galaxies ($\sim1\%$), and radio galaxies ($\sim 2\%$). Remarkably, among the 28 enormous Ly$α$ nebulae (ELANe) exceeding 100 kpc, about 80\% are associated with UV-faint galaxies ($M_\mathrm{UV} > -22$), categorized as Type II ELANe. We underscore that Type II ELANe constitute the majority but remain largely hidden in current galaxy and QSO surveys. Dusty starburst and obscured AGN activity are proposed to explain the nature of Type II ELANe. The SED of stacking all Ly$α$ nebulae also reveals signs of massive dusty star-forming galaxies with obscured AGNs. We propose a model to explain the dusty nature where the diverse populations of Ly$α$ nebulae capture massive galaxies at different evolutionary stages undergoing violent assembling. Ly$α$ nebulae provide critical insights into the formation and evolution of today's massive cluster galaxies at cosmic noon.

astro-ph.GA↗