arXiv subjects

Xuhong Li

Publications and source records attributed to Xuhong Li.

At least 37 records · Page 2Linked to original sources

arXiv2024

A Belief Propagation Algorithm for Multipath-based SLAM with Multiple Map Features: A mmWave MIMO Application

In this paper, we present a multipath-based simultaneous localization and mapping (SLAM) algorithm that continuously adapts mulitiple map feature (MF) models describing specularly reflected multipath components (MPCs) from flat surfaces and point-scattered MPCs, respectively. We develop a Bayesian model for sequential detection and estimation of interacting MF model parameters, MF states and mobile agent's state including position and orientation. The Bayesian model is represented by a factor graph enabling the use of belief propagation (BP) for efficient computation of the marginal posterior distributions. The algorithm also exploits amplitude information enabling reliable detection of weak MFs associated with MPCs of very low signal-to-noise ratios (SNRs). The performance of the proposed algorithm is evaluated using real millimeter-wave (mmWave) multiple-input-multiple-output (MIMO) measurements with single base station setup. Results demonstrate the excellent localization and mapping performance of the proposed algorithm in challenging dynamic outdoor scenarios.

eess.SP↗

arXiv2024

Distributed MIMO Measurements for Integrated Communication and Sensing in an Industrial Environment

Many concepts for future generations of wireless communication systems use coherent processing of signals from many distributed antennas. The aim is to improve communication reliability, capacity, and energy efficiency and provide possibilities for new applications through integrated communication and sensing. The large bandwidths available in the higher bands have inspired much work regarding sensing in the mmWave and sub-THz bands; however, the sub-6 GHz cellular bands will still be the main provider of wide cellular coverage due to the more favorable propagation conditions. In this paper, we present a measurement system and results of sub-6 GHz distributed MIMO measurements performed in an industrial environment. From the measurements, we evaluated the diversity for both large-scale and small-scale fading and characterized the link reliability. We also analyzed the possibility of multistatic sensing and positioning of users in the environment, with the initial results showing a mean-square error below 20 cm on the estimated position. Further, the results clearly showed that new channel models are needed that are spatially consistent and deal with the nonstationary channel properties among the antennas.

cs.IT↗

arXiv2024

Interlayer ferroelectric polarization modulated anomalous Hall effects in four-layer MnBi2Te4 antiferromagnets

Van der Waals (vdW) assembly could efficiently modulate the symmetry of two-dimensional (2D) materials that ultimately governs their physical properties. Of particular interest is the ferroelectric polarization being introduced by proper vdW assembly that enables the realization of novel electronic, magnetic and transport properties of 2D materials. Four-layer antiferromagnetic MnBi2Te4 (F-MBT) offers an excellent platform to explore ferroelectric polarization effects on magnetic order and topological transport properties of nanomaterials. Here, by applying symmetry analyses and density-functional-theory calculations, the ferroelectric interface effects on magnetic order, anomalous Hall effect (AHE) or even quantum AHE (QAHE) on the F-MBT are analyzed. Interlayer ferroelectric polarization in F-MBT efficiently violates the PT symmetry (the combination symmetry of central inversion (P) and time reverse (T) of the F-MBT by conferring magnetoelectric couplings, and stabilizes a specific antiferromagnetic order encompassing a ferromagnetic interface in the F-MBT. We predict that engineering an interlayer polarization in the top or bottom interface of F-MBT allows converting F-MBT from a trivial insulator to a Chern insulator. The switching of ferroelectric polarization at the middle interfaces results in a direction reversal of the quantum anomalous Hall current. Additionally, the interlayer polarization of the top and bottom interfaces can be aligned in the same direction, and the switching of polarization direction also reverses the direction of anomalous Hall currents. Overall, our work highlights the occurrence of quantum-transport phenomena in 2D vdW four-layer antiferromagnets through vdW assembly. These phenomena are absent in the bulk or thin-film in bulk-like stacking forms of MnBi2Te4.

cond-mat.mtrl-sci↗

arXiv2024

Explanations of Classifiers Enhance Medical Image Segmentation via End-to-end Pre-training

Medical image segmentation aims to identify and locate abnormal structures in medical images, such as chest radiographs, using deep neural networks. These networks require a large number of annotated images with fine-grained masks for the regions of interest, making pre-training strategies based on classification datasets essential for sample efficiency. Based on a large-scale medical image classification dataset, our work collects explanations from well-trained classifiers to generate pseudo labels of segmentation tasks. Specifically, we offer a case study on chest radiographs and train image classifiers on the CheXpert dataset to identify 14 pathological observations in radiology. We then use Integrated Gradients (IG) method to distill and boost the explanations obtained from the classifiers, generating massive diagnosis-oriented localization labels (DoLL). These DoLL-annotated images are used for pre-training the model before fine-tuning it for downstream segmentation tasks, including COVID-19 infectious areas, lungs, heart, and clavicles. Our method outperforms other baselines, showcasing significant advantages in model performance and training efficiency across various segmentation settings.

eess.IV↗

arXiv2024

Towards Explainable Artificial Intelligence (XAI): A Data Mining Perspective

Given the complexity and lack of transparency in deep neural networks (DNNs), extensive efforts have been made to make these systems more interpretable or explain their behaviors in accessible terms. Unlike most reviews, which focus on algorithmic and model-centric perspectives, this work takes a "data-centric" view, examining how data collection, processing, and analysis contribute to explainable AI (XAI). We categorize existing work into three categories subject to their purposes: interpretations of deep models, referring to feature attributions and reasoning processes that correlate data points with model outputs; influences of training data, examining the impact of training data nuances, such as data valuation and sample anomalies, on decision-making processes; and insights of domain knowledge, discovering latent patterns and fostering new knowledge from data and models to advance social values and scientific discovery. Specifically, we distill XAI methodologies into data mining operations on training and testing data across modalities, such as images, text, and tabular data, as well as on training logs, checkpoints, models and other DNN behavior descriptors. In this way, our study offers a comprehensive, data-centric examination of XAI from a lens of data mining methods and applications.

cs.AI↗

arXiv2023

CUPre: Cross-domain Unsupervised Pre-training for Few-Shot Cell Segmentation

While pre-training on object detection tasks, such as Common Objects in Contexts (COCO) [1], could significantly boost the performance of cell segmentation, it still consumes on massive fine-annotated cell images [2] with bounding boxes, masks, and cell types for every cell in every image, to fine-tune the pre-trained model. To lower the cost of annotation, this work considers the problem of pre-training DNN models for few-shot cell segmentation, where massive unlabeled cell images are available but only a small proportion is annotated. Hereby, we propose Cross-domain Unsupervised Pre-training, namely CUPre, transferring the capability of object detection and instance segmentation for common visual objects (learned from COCO) to the visual domain of cells using unlabeled images. Given a standard COCO pre-trained network with backbone, neck, and head modules, CUPre adopts an alternate multi-task pre-training (AMT2) procedure with two sub-tasks -- in every iteration of pre-training, AMT2 first trains the backbone with cell images from multiple cell datasets via unsupervised momentum contrastive learning (MoCo) [3], and then trains the whole model with vanilla COCO datasets via instance segmentation. After pre-training, CUPre fine-tunes the whole model on the cell segmentation task using a few annotated images. We carry out extensive experiments to evaluate CUPre using LIVECell [2] and BBBC038 [4] datasets in few-shot instance segmentation settings. The experiment shows that CUPre can outperform existing pre-training methods, achieving the highest average precision (AP) for few-shot cell segmentation and detection.

cs.CV↗

arXiv2023

MUSCLE: Multi-task Self-supervised Continual Learning to Pre-train Deep Models for X-ray Images of Multiple Body Parts

While self-supervised learning (SSL) algorithms have been widely used to pre-train deep models, few efforts [11] have been done to improve representation learning of X-ray image analysis with SSL pre-trained models. In this work, we study a novel self-supervised pre-training pipeline, namely Multi-task Self-super-vised Continual Learning (MUSCLE), for multiple medical imaging tasks, such as classification and segmentation, using X-ray images collected from multiple body parts, including heads, lungs, and bones. Specifically, MUSCLE aggregates X-rays collected from multiple body parts for MoCo-based representation learning, and adopts a well-designed continual learning (CL) procedure to further pre-train the backbone subject various X-ray analysis tasks jointly. Certain strategies for image pre-processing, learning schedules, and regularization have been used to solve data heterogeneity, overfitting, and catastrophic forgetting problems for multi-task/dataset learning in MUSCLE.We evaluate MUSCLE using 9 real-world X-ray datasets with various tasks, including pneumonia classification, skeletal abnormality classification, lung segmentation, and tuberculosis (TB) detection. Comparisons against other pre-trained models [7] confirm the proof-of-concept that self-supervised multi-task/dataset continual pre-training could boost the performance of X-ray image analysis.

cs.CV↗

arXiv2023

Propagation Modeling for Physically Large Arrays: Measurements and Multipath Component Visibility

This paper deals with propagation and channel modeling for physically large arrays. The focus lies on acquiring a spatially consistent model, which is essential, especially for positioning and sensing applications. Ultra-wideband, synthetic array measurement data have been acquired with large positioning devices to support this research. We present a modified multipath channel model that accounts for a varying visibility of multipath components along a large array. Based on a geometric model of the measurement environment, we analyze the visibility of specular components. We show that, depending on the size of the reflecting surface, geometric visibility and amplitude estimates obtained with a super-resolution channel estimation algorithm show a strong correspondence. Furthermore, we highlight the capabilities of the developed synthetic array measurement system.

eess.SP↗

arXiv2023

Large Intelligent Surface Measurements for Joint Communication and Sensing

Multiple concepts for future generations of wireless communication standards utilize coherent processing of signals from many distributed antennas. Names for these concepts include distributed MIMO, cell-free massive MIMO, XL-MIMO, and large intelligent surfaces. They aim to improve communication reliability, capacity, as well as energy efficiency and provide possibilities for new applications through joint communication and sensing. One such recently proposed solution is the concept of RadioWeaves. It proposes a new radio infrastructure for distributed MIMO with distributed internal processing, storage, and compute resources integrated into the infrastructure. The large bandwidths available in the higher bands have inspired much work regarding sensing in the mmWave- and sub-THz-bands, however, sub-6 GHz cellular bands will still be the main provider of broad cellular coverage due to the more favorable propagation conditions. In this paper, we present results from a sub-6 GHz measurement campaign targeting the non-stationary spatial channel statistics for a large RadioWeave and the temporal non-stationarity in a dynamic scenario with RadioWeaves. From the results, we also predict the possibility of multi-static sensing and positioning of users in the environment.

cs.IT↗

arXiv2023

High-Resolution Channel Sounding and Parameter Estimation in Multi-Site Cellular Networks

Accurate understanding of electromagnetic propagation properties in real environments is necessary for efficient design and deployment of cellular systems. In this paper, we show a method to estimate high-resolution channel parameters with a massive antenna array in real network deployments. An antenna array mounted on a vehicle is used to receive downlink long-term evolution (LTE) reference signals from neighboring base stations (BS) with mutual interference. Delay and angular information of multipath components is estimated with a novel inter-cell interference cancellation algorithm and an extension of the RIMAX algorithm. The estimated high-resolution channel parameters are consistent with the movement pattern of the vehicle and the geometry of the environment and allow for refined channel modeling and precise cellular positioning.

eess.SP↗

arXiv2023

Doubly Stochastic Models: Learning with Unbiased Label Noises and Inference Stability

Random label noises (or observational noises) widely exist in practical machine learning settings. While previous studies primarily focus on the affects of label noises to the performance of learning, our work intends to investigate the implicit regularization effects of the label noises, under mini-batch sampling settings of stochastic gradient descent (SGD), with assumptions that label noises are unbiased. Specifically, we analyze the learning dynamics of SGD over the quadratic loss with unbiased label noises, where we model the dynamics of SGD as a stochastic differentiable equation (SDE) with two diffusion terms (namely a Doubly Stochastic Model). While the first diffusion term is caused by mini-batch sampling over the (label-noiseless) loss gradients as many other works on SGD, our model investigates the second noise term of SGD dynamics, which is caused by mini-batch sampling over the label noises, as an implicit regularizer. Our theoretical analysis finds such implicit regularizer would favor some convergence points that could stabilize model outputs against perturbation of parameters (namely inference stability). Though similar phenomenon have been investigated, our work doesn't assume SGD as an Ornstein-Uhlenbeck like process and achieve a more generalizable result with convergence of approximation proved. To validate our analysis, we design two sets of empirical studies to analyze the implicit regularizer of SGD with unbiased random label noises for deep neural networks training and linear regression.

cs.LG↗

arXiv2022

Learning from Training Dynamics: Identifying Mislabeled Data Beyond Manually Designed Features

While mislabeled or ambiguously-labeled samples in the training set could negatively affect the performance of deep models, diagnosing the dataset and identifying mislabeled samples helps to improve the generalization power. Training dynamics, i.e., the traces left by iterations of optimization algorithms, have recently been proved to be effective to localize mislabeled samples with hand-crafted features. In this paper, beyond manually designed features, we introduce a novel learning-based solution, leveraging a noise detector, instanced by an LSTM network, which learns to predict whether a sample was mislabeled using the raw training dynamics as input. Specifically, the proposed method trains the noise detector in a supervised manner using the dataset with synthesized label noises and can adapt to various datasets (either naturally or synthesized label-noised) without retraining. We conduct extensive experiments to evaluate the proposed method. We train the noise detector based on the synthesized label-noised CIFAR dataset and test such noise detector on Tiny ImageNet, CUB-200, Caltech-256, WebVision and Clothing1M. Results show that the proposed method precisely detects mislabeled samples on various datasets without further adaptation, and outperforms state-of-the-art methods. Besides, more experiments demonstrate that the mislabel identification can guide a label correction, namely data debugging, providing orthogonal improvements of algorithm-centric state-of-the-art techniques from the data aspect.

cs.CV↗

arXiv2022

Interpretable Deep Learning: Interpretation, Interpretability, Trustworthiness, and Beyond

Deep neural networks have been well-known for their superb handling of various machine learning and artificial intelligence tasks. However, due to their over-parameterized black-box nature, it is often difficult to understand the prediction results of deep models. In recent years, many interpretation tools have been proposed to explain or reveal how deep models make decisions. In this paper, we review this line of research and try to make a comprehensive survey. Specifically, we first introduce and clarify two basic concepts -- interpretations and interpretability -- that people usually get confused about. To address the research efforts in interpretations, we elaborate the designs of a number of interpretation algorithms, from different perspectives, by proposing a new taxonomy. Then, to understand the interpretation results, we also survey the performance metrics for evaluating interpretation algorithms. Further, we summarize the current works in evaluating models' interpretability using "trustworthy" interpretation algorithms. Finally, we review and discuss the connections between deep models' interpretations and other factors, such as adversarial robustness and learning from interpretations, and we introduce several open-source libraries for interpretation algorithms and evaluation approaches.

cs.LG↗

arXiv2022

Distilling Ensemble of Explanations for Weakly-Supervised Pre-Training of Image Segmentation Models

While fine-tuning pre-trained networks has become a popular way to train image segmentation models, such backbone networks for image segmentation are frequently pre-trained using image classification source datasets, e.g., ImageNet. Though image classification datasets could provide the backbone networks with rich visual features and discriminative ability, they are incapable of fully pre-training the target model (i.e., backbone+segmentation modules) in an end-to-end manner. The segmentation modules are left to random initialization in the fine-tuning process due to the lack of segmentation labels in classification datasets. In our work, we propose a method that leverages Pseudo Semantic Segmentation Labels (PSSL), to enable the end-to-end pre-training for image segmentation models based on classification datasets. PSSL was inspired by the observation that the explanation results of classification models, obtained through explanation algorithms such as CAM, SmoothGrad and LIME, would be close to the pixel clusters of visual objects. Specifically, PSSL is obtained for each image by interpreting the classification results and aggregating an ensemble of explanations queried from multiple classifiers to lower the bias caused by single models. With PSSL for every image of ImageNet, the proposed method leverages a weighted segmentation learning procedure to pre-train the segmentation network en masse. Experiment results show that, with ImageNet accompanied by PSSL as the source dataset, the proposed end-to-end pre-training strategy successfully boosts the performance of various segmentation models, i.e., PSPNet-ResNet50, DeepLabV3-ResNet50, and OCRNet-HRNetW18, on a number of segmentation tasks, such as CamVid, VOC-A, VOC-C, ADE20K, and CityScapes, with significant improvements. The source code is availabel at https://github.com/PaddlePaddle/PaddleSeg.

cs.CV↗

arXiv2022

Sequential Detection and Estimation of Multipath Channel Parameters Using Belief Propagation

This paper proposes a belief propagation (BP)-based algorithm for sequential detection and estimation of multipath component (MPC) parameters based on radio signals. Under dynamic channel conditions with moving transmitter/receiver, the number of MPCs, the MPC dispersion parameters, and the number of false alarm contributions are unknown and time-varying. We develop a Bayesian model for sequential detection and estimation of MPC dispersion parameters, and represent it by a factor graph enabling the use of BP for efficient computation of the marginal posterior distributions. At each time step, a snapshot-based parametric channel estimator provides parameter estimates of a set of MPCs which are used as noisy measurements by the proposed BP-based algorithm. It performs joint probabilistic data association, and estimation of the time-varying MPC parameters and the mean number of false alarm measurements, by means of the sum-product algorithm rules. The algorithm also exploits amplitude information enabling the reliable detection of "weak" MPCs with very low component signal-to-noise ratios (SNRs). The performance of the proposed algorithm compares well to state-of-the-art algorithms for high SNR MPCs, but it significantly outperforms them for medium or low SNR MPCs. Results using real radio measurements demonstrate the excellent performance of the proposed algorithm in realistic and challenging scenarios.

cs.IT↗

arXiv2022

From Distributed Machine Learning to Federated Learning: A Survey

In recent years, data and computing resources are typically distributed in the devices of end users, various regions or organizations. Because of laws or regulations, the distributed data and computing resources cannot be directly shared among different regions or organizations for machine learning tasks. Federated learning emerges as an efficient approach to exploit distributed data and computing resources, so as to collaboratively train machine learning models, while obeying the laws and regulations and ensuring data security and data privacy. In this paper, we provide a comprehensive survey of existing works for federated learning. We propose a functional architecture of federated learning systems and a taxonomy of related techniques. Furthermore, we present the distributed training, data communication, and security of FL systems. Finally, we analyze their limitations and propose future research directions.

cs.DC↗

arXiv2022

Towards Accurate Knowledge Transfer via Target-awareness Representation Disentanglement

Fine-tuning deep neural networks pre-trained on large scale datasets is one of the most practical transfer learning paradigm given limited quantity of training samples. To obtain better generalization, using the starting point as the reference (SPAR), either through weights or features, has been successfully applied to transfer learning as a regularizer. However, due to the domain discrepancy between the source and target task, there exists obvious risk of negative transfer in a straightforward manner of knowledge preserving. In this paper, we propose a novel transfer learning algorithm, introducing the idea of Target-awareness REpresentation Disentanglement (TRED), where the relevant knowledge with respect to the target task is disentangled from the original source model and used as a regularizer during fine-tuning the target model. Specifically, we design two alternative methods, maximizing the Maximum Mean Discrepancy (Max-MMD) and minimizing the mutual information (Min-MI), for the representation disentanglement. Experiments on various real world datasets show that our method stably improves the standard fine-tuning by more than 2% in average. TRED also outperforms related state-of-the-art transfer learning regularizers such as L2-SP, AT, DELTA, and BSS.

cs.LG↗

arXiv2021

Cross-Model Consensus of Explanations and Beyond for Image Classification Models: An Empirical Study

Existing interpretation algorithms have found that, even deep models make the same and right predictions on the same image, they might rely on different sets of input features for classification. However, among these sets of features, some common features might be used by the majority of models. In this paper, we are wondering what are the common features used by various models for classification and whether the models with better performance may favor those common features. For this purpose, our works uses an interpretation algorithm to attribute the importance of features (e.g., pixels or superpixels) as explanations, and proposes the cross-model consensus of explanations to capture the common features. Specifically, we first prepare a set of deep models as a committee, then deduce the explanation for every model, and obtain the consensus of explanations across the entire committee through voting. With the cross-model consensus of explanations, we conduct extensive experiments using 80+ models on 5 datasets/tasks. We find three interesting phenomena as follows: (1) the consensus obtained from image classification models is aligned with the ground truth of semantic segmentation; (2) we measure the similarity of the explanation result of each model in the committee to the consensus (namely consensus score), and find positive correlations between the consensus score and model performance; and (3) the consensus score coincidentally correlates to the interpretability.

cs.LG↗