arXiv subjects

Qing Xu

Publications and source records attributed to Qing Xu.

At least 73 records · Page 4Linked to original sources

arXiv2025

V2X-DGPE: Addressing Domain Gaps and Pose Errors for Robust Collaborative 3D Object Detection

In V2X collaborative perception, the domain gaps between heterogeneous nodes pose a significant challenge for effective information fusion. Pose errors arising from latency and GPS localization noise further exacerbate the issue by leading to feature misalignment. To overcome these challenges, we propose V2X-DGPE, a high-accuracy and robust V2X feature-level collaborative perception framework. V2X-DGPE employs a Knowledge Distillation Framework and a Feature Compensation Module to learn domain-invariant representations from multi-source data, effectively reducing the feature distribution gap between vehicles and roadside infrastructure. Historical information is utilized to provide the model with a more comprehensive understanding of the current scene. Furthermore, a Collaborative Fusion Module leverages a heterogeneous self-attention mechanism to extract and integrate heterogeneous representations from vehicles and infrastructure. To address pose errors, V2X-DGPE introduces a deformable attention mechanism, enabling the model to adaptively focus on critical parts of the input features by dynamically offsetting sampling points. Extensive experiments on the real-world DAIR-V2X dataset demonstrate that the proposed method outperforms existing approaches, achieving state-of-the-art detection performance. The code is available at https://github.com/wangsch10/V2X-DGPE.

cs.CV↗

arXiv2024

Conformal Symplectic Optimization for Stable Reinforcement Learning

Training deep reinforcement learning (RL) agents necessitates overcoming the highly unstable nonconvex stochastic optimization inherent in the trial-and-error mechanism. To tackle this challenge, we propose a physics-inspired optimization algorithm called relativistic adaptive gradient descent (RAD), which enhances long-term training stability. By conceptualizing neural network (NN) training as the evolution of a conformal Hamiltonian system, we present a universal framework for transferring long-term stability from conformal symplectic integrators to iterative NN updating rules, where the choice of kinetic energy governs the dynamical properties of resulting optimization algorithms. By utilizing relativistic kinetic energy, RAD incorporates principles from special relativity and limits parameter updates below a finite speed, effectively mitigating abnormal gradient influences. Additionally, RAD models NN optimization as the evolution of a multi-particle system where each trainable parameter acts as an independent particle with an individual adaptive learning rate. We prove RAD's sublinear convergence under general nonconvex settings, where smaller gradient variance and larger batch sizes contribute to tighter convergence. Notably, RAD degrades to the well-known adaptive moment estimation (ADAM) algorithm when its speed coefficient is chosen as one and symplectic factor as a small positive value. Experimental results show RAD outperforming nine baseline optimizers with five RL algorithms across twelve environments, including standard benchmarks and challenging scenarios. Notably, RAD achieves up to a 155.1% performance improvement over ADAM in Atari games, showcasing its efficacy in stabilizing and accelerating RL training.

cs.LG↗

arXiv2024

EDRF: Enhanced Driving Risk Field Based on Multimodal Trajectory Prediction and Its Applications

Driving risk assessment is crucial for both autonomous vehicles and human-driven vehicles. The driving risk can be quantified as the product of the probability that an event (such as collision) will occur and the consequence of that event. However, the probability of events occurring is often difficult to predict due to the uncertainty of drivers' or vehicles' behavior. Traditional methods generally employ kinematic-based approaches to predict the future trajectories of entities, which often yield unrealistic prediction results. In this paper, the Enhanced Driving Risk Field (EDRF) model is proposed, integrating deep learning-based multimodal trajectory prediction results with Gaussian distribution models to quantitatively capture the uncertainty of traffic entities' behavior. The applications of the EDRF are also proposed. It is applied across various tasks (traffic risk monitoring, ego-vehicle risk analysis, and motion and trajectory planning) through the defined concept Interaction Risk (IR). Adequate example scenarios are provided for each application to illustrate the effectiveness of the model.

eess.SY↗

arXiv2024

Mathematical Analysis and Numerical Computation of String Vibration Equations with Elastic Supports for Bridge Cable Force Evaluation

This study focuses on a critical aspect of bridge engineering -- the evaluation of cable forces, paying particular attention to the cables that are internally constrained by elastic supports. Detecting these cable forces is important for the safety and stability of bridges. The practical problem introduces a novel mathematical challenge: how to effectively address string vibration equations with one or multiple internal elastic supports,~which remains a theoretical issue not fully solved in engineering. To tackle this, it is necessary to firstly establish an appropriate mathematical model and accurately define initial-boundary value problems. We then formulate the well-posedness of the solution using both classical and weak solution approaches, supplementing the existing numerical results available in engineering. Meanwhile, we attempt to use PINNs (Physics-Informed Neural Networks) instead of traditional FEM (Finite Element Method) in engineering. Consequently, in contrast to the classical solution method, we demonstrate that for a string with finite elastic supports, the weak solution method not only improves mathematical modeling efficiency but also simplifies the process of explaining the well-posedness of the solution.

math.AP↗

arXiv2024

Robust Data-EnablEd Predictive Leading Cruise Control via Reachability Analysis

Data-driven predictive control promises model-free wave-dampening strategies for Connected and Autonomous Vehicles (CAVs) in mixed traffic flow. However, its performance relies on data quality, which suffers from unknown noise and disturbances. This paper introduces a Robust Data-EnablEd Predictive Leading Cruise Control (RDeeP-LCC) method based on reachability analysis, aiming to achieve safe and optimal CAV control under bounded process noise and external disturbances. Precisely, the matrix zonotope set technique and Willems' Fundamental Lemma are employed to derive the over-approximated system dynamics directly from data, and a data-driven feedback control technique is utilized to obtain an additional feedback input for stability. We decouple the mixed platoon into an error system and a nominal system, where the error system provides data-driven reachability sets for the enhanced safety constraints in the nominal system. Finally, a data-driven predictive control framework is formulated in a tube-based control manner for robustness guarantees. Nonlinear simulations with noise-corrupted data demonstrate that the proposed method outperforms baseline methods in mitigating traffic waves.

eess.SY↗

arXiv2024

Vision-Driven 2D Supervised Fine-Tuning Framework for Bird's Eye View Perception

Visual bird's eye view (BEV) perception, due to its excellent perceptual capabilities, is progressively replacing costly LiDAR-based perception systems, especially in the realm of urban intelligent driving. However, this type of perception still relies on LiDAR data to construct ground truth databases, a process that is both cumbersome and time-consuming. Moreover, most massproduced autonomous driving systems are only equipped with surround camera sensors and lack LiDAR data for precise annotation. To tackle this challenge, we propose a fine-tuning method for BEV perception network based on visual 2D semantic perception, aimed at enhancing the model's generalization capabilities in new scene data. Considering the maturity and development of 2D perception technologies, our method significantly reduces the dependency on high-cost BEV ground truths and shows promising industrial application prospects. Extensive experiments and comparative analyses conducted on the nuScenes and Waymo public datasets demonstrate the effectiveness of our proposed method.

cs.CV↗

arXiv2024

Hierarchical and Decoupled BEV Perception Learning Framework for Autonomous Driving

Perception is essential for autonomous driving system. Recent approaches based on Bird's-eye-view (BEV) and deep learning have made significant progress. However, there exists challenging issues including lengthy development cycles, poor reusability, and complex sensor setups in perception algorithm development process. To tackle the above challenges, this paper proposes a novel hierarchical BEV perception paradigm, aiming to provide a library of fundamental perception modules and user-friendly graphical interface, enabling swift construction of customized models. We conduct the Pretrain-Finetune strategy to effectively utilize large scale public datasets and streamline development processes. Moreover, we present a Multi-Module Learning (MML) approach, enhancing performance through synergistic and iterative training of multiple models. Extensive experimental results on the Nuscenes dataset demonstrate that our approach renders significant improvement over the traditional training scheme.

cs.CV↗

arXiv2024

OE-BevSeg: An Object Informed and Environment Aware Multimodal Framework for Bird's-eye-view Vehicle Semantic Segmentation

Bird's-eye-view (BEV) semantic segmentation is becoming crucial in autonomous driving systems. It realizes ego-vehicle surrounding environment perception by projecting 2D multi-view images into 3D world space. Recently, BEV segmentation has made notable progress, attributed to better view transformation modules, larger image encoders, or more temporal information. However, there are still two issues: 1) a lack of effective understanding and enhancement of BEV space features, particularly in accurately capturing long-distance environmental features and 2) recognizing fine details of target objects. To address these issues, we propose OE-BevSeg, an end-to-end multimodal framework that enhances BEV segmentation performance through global environment-aware perception and local target object enhancement. OE-BevSeg employs an environment-aware BEV compressor. Based on prior knowledge about the main composition of the BEV surrounding environment varying with the increase of distance intervals, long-sequence global modeling is utilized to improve the model's understanding and perception of the environment. From the perspective of enriching target object information in segmentation results, we introduce the center-informed object enhancement module, using centerness information to supervise and guide the segmentation head, thereby enhancing segmentation performance from a local enhancement perspective. Additionally, we designed a multimodal fusion branch that integrates multi-view RGB image features with radar/LiDAR features, achieving significant performance improvements. Extensive experiments show that, whether in camera-only or multimodal fusion BEV segmentation tasks, our approach achieves state-of-the-art results by a large margin on the nuScenes dataset for vehicle segmentation, demonstrating superior applicability in the field of autonomous driving.

cs.CV↗

arXiv2024

Emotion Loss Attacking: Adversarial Attack Perception for Skeleton based on Multi-dimensional Features

Adversarial attack on skeletal motion is a hot topic. However, existing researches only consider part of dynamic features when measuring distance between skeleton graph sequences, which results in poor imperceptibility. To this end, we propose a novel adversarial attack method to attack action recognizers for skeletal motions. Firstly, our method systematically proposes a dynamic distance function to measure the difference between skeletal motions. Meanwhile, we innovatively introduce emotional features for complementary information. In addition, we use Alternating Direction Method of Multipliers(ADMM) to solve the constrained optimization problem, which generates adversarial samples with better imperceptibility to deceive the classifiers. Experiments show that our method is effective on multiple action classifiers and datasets. When the perturbation magnitude measured by l norms is the same, the dynamic perturbations generated by our method are much lower than that of other methods. What's more, we are the first to prove the effectiveness of emotional features, and provide a new idea for measuring the distance between skeletal motions.

cs.CV↗

arXiv2024

LLM-based Knowledge Pruning for Time Series Data Analytics on Edge-computing Devices

Limited by the scale and diversity of time series data, the neural networks trained on time series data often overfit and show unsatisfacotry performances. In comparison, large language models (LLMs) recently exhibit impressive generalization in diverse fields. Although massive LLM based approaches are proposed for time series tasks, these methods require to load the whole LLM in both training and reference. This high computational demands limit practical applications in resource-constrained settings, like edge-computing and IoT devices. To address this issue, we propose Knowledge Pruning (KP), a novel paradigm for time series learning in this paper. For a specific downstream task, we argue that the world knowledge learned by LLMs is much redundant and only the related knowledge termed as "pertinent knowledge" is useful. Unlike other methods, our KP targets to prune the redundant knowledge and only distill the pertinent knowledge into the target model. This reduces model size and computational costs significantly. Additionally, different from existing LLM based approaches, our KP does not require to load the LLM in the process of training and testing, further easing computational burdens. With our proposed KP, a lightweight network can effectively learn the pertinent knowledge, achieving satisfactory performances with a low computation cost. To verify the effectiveness of our KP, two fundamental tasks on edge-computing devices are investigated in our experiments, where eight diverse environments or benchmarks with different networks are used to verify the generalization of our KP. Through experiments, our KP demonstrates effective learning of pertinent knowledge, achieving notable performance improvements in regression (19.7% on average) and classification (up to 13.7%) tasks, showcasing state-of-the-art results.

cs.LG↗

arXiv2024

Cognitive Effort Measures Driven by Fixation Induced Retinal Flow in Visual Scanning Behavior during Virtual Driving

In this paper, we consider the problem of visual scanning mechanism underpinning sensorimotor tasks, such as walking and driving, in dynamic environments. We exploit eye tracking data for offering two new cognitive effort measures in visual scanning behavior of virtual driving. By utilizing the retinal flow induced by fixation, two novel measures of cognitive effort are proposed through the importance of grids in the viewing plane and the concept of information quantity, respectively. Psychophysical studies are conducted to reveal the effectiveness of the two proposed measures. Both these two cognitive effort measures have shown their significant correlation with pupil size change. Our results suggest that the quantitative exploitation of eye tracking data provides an effective approach for the evaluation of sensorimotor activities.

cs.HC↗

arXiv2024

From Algorithm to Hardware: A Survey on Efficient and Safe Deployment of Deep Neural Networks

Deep neural networks (DNNs) have been widely used in many artificial intelligence (AI) tasks. However, deploying them brings significant challenges due to the huge cost of memory, energy, and computation. To address these challenges, researchers have developed various model compression techniques such as model quantization and model pruning. Recently, there has been a surge in research of compression methods to achieve model efficiency while retaining the performance. Furthermore, more and more works focus on customizing the DNN hardware accelerators to better leverage the model compression techniques. In addition to efficiency, preserving security and privacy is critical for deploying DNNs. However, the vast and diverse body of related works can be overwhelming. This inspires us to conduct a comprehensive survey on recent research toward the goal of high-performance, cost-efficient, and safe deployment of DNNs. Our survey first covers the mainstream model compression techniques such as model quantization, model pruning, knowledge distillation, and optimizations of non-linear operations. We then introduce recent advances in designing hardware accelerators that can adapt to efficient model compression approaches. Additionally, we discuss how homomorphic encryption can be integrated to secure DNN deployment. Finally, we discuss several issues, such as hardware evaluation, generalization, and integration of various compression approaches. Overall, we aim to provide a big picture of efficient DNNs, from algorithm to hardware accelerators and security perspectives.

cs.LG↗

arXiv2024

Quantitative Evaluation of driver's situation awareness in virtual driving through Eye tracking analysis

In driving tasks, the driver's situation awareness of the surrounding scenario is crucial for safety driving. However, current methods of measuring situation awareness mostly rely on subjective questionnaires, which interrupt tasks and lack non-intrusive quantification. To address this issue, our study utilizes objective gaze motion data to provide an interference-free quantification method for situation awareness. Three quantitative scores are proposed to represent three different levels of awareness: perception, comprehension, and projection, and an overall score of situation awareness is also proposed based on above three scores. To validate our findings, we conducted experiments where subjects performed driving tasks in a virtual reality simulated environment. All the four proposed situation awareness scores have clearly shown a significant correlation with driving performance. The proposed not only illuminates a new path for understanding and evaluating the situation awareness but also offers a satisfying proxy for driving performance.

cs.HC↗

arXiv2024

Improve Knowledge Distillation via Label Revision and Data Selection

Knowledge distillation (KD) has become a widely used technique in the field of model compression, which aims to transfer knowledge from a large teacher model to a lightweight student model for efficient network development. In addition to the supervision of ground truth, the vanilla KD method regards the predictions of the teacher as soft labels to supervise the training of the student model. Based on vanilla KD, various approaches have been developed to further improve the performance of the student model. However, few of these previous methods have considered the reliability of the supervision from teacher models. Supervision from erroneous predictions may mislead the training of the student model. This paper therefore proposes to tackle this problem from two aspects: Label Revision to rectify the incorrect supervision and Data Selection to select appropriate samples for distillation to reduce the impact of erroneous supervision. In the former, we propose to rectify the teacher's inaccurate predictions using the ground truth. In the latter, we introduce a data selection technique to choose suitable training samples to be supervised by the teacher, thereby reducing the impact of incorrect predictions to some extent. Experiment results demonstrate the effectiveness of our proposed method, and show that our method can be combined with other distillation approaches, improving their performance.

cs.LG↗

arXiv2024

I/O Transit Caching for PMem-based Block Device

Byte-addressable non-volatile memory (NVM) sitting on the memory bus is employed to make persistent memory (PMem) in general-purpose computing systems and embedded systems for data storage. Researchers develop software drivers such as the block translation table (BTT) to build block devices on PMem, so programmers can keep using mature and reliable conventional storage stack while expecting high performance by exploiting fast PMem. However, our quantitative study shows that BTT underutilizes PMem and yields inferior performance, due to the absence of the imperative in-device cache. We add a conventional I/O staging cache made of DRAM space to BTT. As DRAM and PMem have comparable access latency, I/O staging cache is likely to be fully filled over time. Continual cache evictions and fsyncs thus cause on-demand flushes with severe stalls, such that the I/O staging cache is concretely unappealing for PMem-based block devices. We accordingly propose an algorithm named Caiti with novel I/O transit caching. Caiti eagerly evicts buffered data to PMem through CPU's multi-cores. It also conditionally bypasses a full cache and directly writes data into PMem to further alleviate I/O stalls. Experiments confirm that Caiti significantly boosts the performance with BTT by up to 3.6x, without loss of block-level write atomicity.

cs.AR↗

arXiv2024

UN-SAM: Universal Prompt-Free Segmentation for Generalized Nuclei Images

In digital pathology, precise nuclei segmentation is pivotal yet challenged by the diversity of tissue types, staining protocols, and imaging conditions. Recently, the segment anything model (SAM) revealed overwhelming performance in natural scenarios and impressive adaptation to medical imaging. Despite these advantages, the reliance of labor-intensive manual annotation as segmentation prompts severely hinders their clinical applicability, especially for nuclei image analysis containing massive cells where dense manual prompts are impractical. To overcome the limitations of current SAM methods while retaining the advantages, we propose the Universal prompt-free SAM framework for Nuclei segmentation (UN-SAM), by providing a fully automated solution with remarkable generalization capabilities. Specifically, to eliminate the labor-intensive requirement of per-nuclei annotations for prompt, we devise a multi-scale Self-Prompt Generation (SPGen) module to revolutionize clinical workflow by automatically generating high-quality mask hints to guide the segmentation tasks. Moreover, to unleash the generalization capability of SAM across a variety of nuclei images, we devise a Domain-adaptive Tuning Encoder (DT-Encoder) to seamlessly harmonize visual features with domain-common and domain-specific knowledge, and further devise a Domain Query-enhanced Decoder (DQ-Decoder) by leveraging learnable domain queries for segmentation decoding in different nuclei domains. Extensive experiments prove that UN-SAM with exceptional performance surpasses state-of-the-arts in nuclei instance and semantic segmentation, especially the generalization capability in zero-shot scenarios. The source code is available at https://github.com/CUHK-AIM-Group/UN-SAM.

eess.IV↗

arXiv2023

Cloud Control of Connected Vehicle under Bi-directional Time-varying delay: An Application of Predictor-observer Structured Controller

This article is devoted to addressing the cloud control of connected vehicles, specifically focusing on analyzing the effect of bi-directional communication-induced delays. To mitigate the adverse effects of such delays, a novel predictor-observer structured controller is proposed which compensate for both measurable output delays and unmeasurable, yet bounded, input delays simultaneously. The study begins by novelly constructing an equivalent delay-free inter-connected system model that incorporates the Predictor-Observer controller, considering certain delay boundaries and model uncertainties. Subsequently, a stability analysis is conducted to assess the system's robustness under these conditions. Next, the connected vehicle lateral control scenario is built which contain high-fidelity vehicle dynamic model. The results demonstrate the controller's ability to accurately predict the system states, even under time-varying bi-directional delays. Finally, the proposed method is deployed in a real connected vehicle lateral control system. Comparative tests with a conventional linear feedback controller showcase significantly improved control performance under dominant bi-directional delay conditions, affirming the superiority of the proposed method against the delay.

eess.SY↗

arXiv2023

Information Flow Topology in Mixed Traffic: A Comparative Study between "Looking Ahead" and "Looking Behind"

The emergence of connected and automated vehicles (CAVs) promises smoother traffic flow. In mixed traffic where human-driven vehicles (HDVs) also exist, existing research mostly focuses on "looking ahead" (i.e., the CAVs receive information from preceding vehicles) strategies for CAVs, while recent work reveals that "looking behind" (i.e., the CAVs receive information from their rear vehicles) strategies might provide more possibilities for CAV longitudinal control. This paper presents a comparative study between these two types of information flow topology (IFT) from the string stability perspective, with the role of maximum platoon size (MPS) also under investigation. Precisely, we provide a dynamical modeling framework for the mixed platoon under the multi-predecessor-following (MPF) topology and the multi-successor-leading (MSL) topology. Then, a unified method for string stability analysis is presented, with explicit consideration of both IFT and MPS. Numerical results suggest that MSL ("looking behind") outperforms MPF ("looking ahead" ) in mitigating traffic perturbations. In addition, increasing MPS could further improve string stability of mixed traffic flow.

eess.SY↗