arXiv subjects

Wei Xi

Publications and source records attributed to Wei Xi.

At least 37 records · Page 2Linked to original sources

arXiv2025

One Snapshot is All You Need: A Generalized Method for mmWave Signal Generation

Wireless sensing systems, particularly those using mmWave technology, offer distinct advantages over traditional vision-based approaches, such as enhanced privacy and effectiveness in poor lighting conditions. These systems, leveraging FMCW signals, have shown success in human-centric applications like localization, gesture recognition, and so on. However, comprehensive mmWave datasets for diverse applications are scarce, often constrained by pre-processed signatures (e.g., point clouds or RA heatmaps) and inconsistent annotation formats. To overcome these limitations, we propose mmGen, a novel and generalized framework tailored for full-scene mmWave signal generation. By constructing physical signal transmission models, mmGen synthesizes human-reflected and environment-reflected mmWave signals from the constructed 3D meshes. Additionally, we incorporate methods to account for material properties, antenna gains, and multipath reflections, enhancing the realism of the synthesized signals. We conduct extensive experiments using a prototype system with commercial mmWave devices and Kinect sensors. The results show that the average similarity of Range-Angle and micro-Doppler signatures between the synthesized and real-captured signals across three different environments exceeds 0.91 and 0.89, respectively, demonstrating the effectiveness and practical applicability of mmGen.

cs.CV↗

arXiv2025

Ten Challenging Problems in Federated Foundation Models

Federated Foundation Models (FedFMs) represent a distributed learning paradigm that fuses general competences of foundation models as well as privacy-preserving capabilities of federated learning. This combination allows the large foundation models and the small local domain models at the remote clients to learn from each other in a teacher-student learning setting. This paper provides a comprehensive summary of the ten challenging problems inherent in FedFMs, encompassing foundational theory, utilization of private data, continual learning, unlearning, Non-IID and graph data, bidirectional knowledge transfer, incentive mechanism design, game mechanism design, model watermarking, and efficiency. The ten challenging problems manifest in five pivotal aspects: ``Foundational Theory," which aims to establish a coherent and unifying theoretical framework for FedFMs. ``Data," addressing the difficulties in leveraging domain-specific knowledge from private data while maintaining privacy; ``Heterogeneity," examining variations in data, model, and computational resources across clients; ``Security and Privacy," focusing on defenses against malicious attacks and model theft; and ``Efficiency," highlighting the need for improvements in training, communication, and parameter efficiency. For each problem, we offer a clear mathematical definition on the objective function, analyze existing methods, and discuss the key challenges and potential solutions. This in-depth exploration aims to advance the theoretical foundations of FedFMs, guide practical implementations, and inspire future research to overcome these obstacles, thereby enabling the robust, efficient, and privacy-preserving FedFMs in various real-world applications.

cs.LG↗

arXiv2024

Numerical Estimation of Spatial Distributions under Differential Privacy

Estimating spatial distributions is important in data analysis, such as traffic flow forecasting and epidemic prevention. To achieve accurate spatial distribution estimation, the analysis needs to collect sufficient user data. However, collecting data directly from individuals could compromise their privacy. Most previous works focused on private distribution estimation for one-dimensional data, which does not consider spatial data relation and leads to poor accuracy for spatial distribution estimation. In this paper, we address the problem of private spatial distribution estimation, where we collect spatial data from individuals and aim to minimize the distance between the actual distribution and estimated one under Local Differential Privacy (LDP). To leverage the numerical nature of the domain, we project spatial data and its relationships onto a one-dimensional distribution. We then use this projection to estimate the overall spatial distribution. Specifically, we propose a reporting mechanism called Disk Area Mechanism (DAM), which projects the spatial domain onto a line and optimizes the estimation using the sliced Wasserstein distance. Through extensive experiments, we show the effectiveness of our DAM approach on both real and synthetic data sets, compared with the state-of-the-art methods, such as Multi-dimensional Square Wave Mechanism (MDSW) and Subset Exponential Mechanism with Geo-I (SEM-Geo-I). Our results show that our DAM always performs better than MDSW and is better than SEM-Geo-I when the data granularity is fine enough.

cs.DB↗

arXiv2024

Stereo-LiDAR Depth Estimation with Deformable Propagation and Learned Disparity-Depth Conversion

Accurate and dense depth estimation with stereo cameras and LiDAR is an important task for automatic driving and robotic perception. While sparse hints from LiDAR points have improved cost aggregation in stereo matching, their effectiveness is limited by the low density and non-uniform distribution. To address this issue, we propose a novel stereo-LiDAR depth estimation network with Semi-Dense hint Guidance, named SDG-Depth. Our network includes a deformable propagation module for generating a semi-dense hint map and a confidence map by propagating sparse hints using a learned deformable window. These maps then guide cost aggregation in stereo matching. To reduce the triangulation error in depth recovery from disparity, especially in distant regions, we introduce a disparity-depth conversion module. Our method is both accurate and efficient. The experimental results on benchmark tests show its superior performance. Our code is available at https://github.com/SJTU-ViSYS/SDG-Depth.

cs.CV↗

arXiv2024

FedFixer: Mitigating Heterogeneous Label Noise in Federated Learning

Federated Learning (FL) heavily depends on label quality for its performance. However, the label distribution among individual clients is always both noisy and heterogeneous. The high loss incurred by client-specific samples in heterogeneous label noise poses challenges for distinguishing between client-specific and noisy label samples, impacting the effectiveness of existing label noise learning approaches. To tackle this issue, we propose FedFixer, where the personalized model is introduced to cooperate with the global model to effectively select clean client-specific samples. In the dual models, updating the personalized model solely at a local level can lead to overfitting on noisy data due to limited samples, consequently affecting both the local and global models' performance. To mitigate overfitting, we address this concern from two perspectives. Firstly, we employ a confidence regularizer to alleviate the impact of unconfident predictions caused by label noise. Secondly, a distance regularizer is implemented to constrain the disparity between the personalized and global models. We validate the effectiveness of FedFixer through extensive experiments on benchmark datasets. The results demonstrate that FedFixer can perform well in filtering noisy label samples on different clients, especially in highly heterogeneous label noise scenarios.

cs.LG↗

arXiv2024

Ground-Fusion: A Low-cost Ground SLAM System Robust to Corner Cases

We introduce Ground-Fusion, a low-cost sensor fusion simultaneous localization and mapping (SLAM) system for ground vehicles. Our system features efficient initialization, effective sensor anomaly detection and handling, real-time dense color mapping, and robust localization in diverse environments. We tightly integrate RGB-D images, inertial measurements, wheel odometer and GNSS signals within a factor graph to achieve accurate and reliable localization both indoors and outdoors. To ensure successful initialization, we propose an efficient strategy that comprises three different methods: stationary, visual, and dynamic, tailored to handle diverse cases. Furthermore, we develop mechanisms to detect sensor anomalies and degradation, handling them adeptly to maintain system accuracy. Our experimental results on both public and self-collected datasets demonstrate that Ground-Fusion outperforms existing low-cost SLAM systems in corner cases. We release the code and datasets at https://github.com/SJTU-ViSYS/Ground-Fusion.

cs.RO↗

arXiv2023

UFDA: Universal Federated Domain Adaptation with Practical Assumptions

Conventional Federated Domain Adaptation (FDA) approaches usually demand an abundance of assumptions, which makes them significantly less feasible for real-world situations and introduces security hazards. This paper relaxes the assumptions from previous FDAs and studies a more practical scenario named Universal Federated Domain Adaptation (UFDA). It only requires the black-box model and the label set information of each source domain, while the label sets of different source domains could be inconsistent, and the target-domain label set is totally blind. Towards a more effective solution for our newly proposed UFDA scenario, we propose a corresponding methodology called Hot-Learning with Contrastive Label Disambiguation (HCLD). It particularly tackles UFDA's domain shifts and category gaps problems by using one-hot outputs from the black-box models of various source domains. Moreover, to better distinguish the shared and unknown classes, we further present a cluster-level strategy named Mutual-Voting Decision (MVD) to extract robust consensus knowledge across peer classes from both source and target domains. Extensive experiments on three benchmark datasets demonstrate that our method achieves comparable performance for our UFDA scenario with much fewer assumptions, compared to previous methodologies with comprehensive additional assumptions.

cs.LG↗

arXiv2023

Meta Generative Flow Networks with Personalization for Task-Specific Adaptation

Multi-task reinforcement learning and meta-reinforcement learning have been developed to quickly adapt to new tasks, but they tend to focus on tasks with higher rewards and more frequent occurrences, leading to poor performance on tasks with sparse rewards. To address this issue, GFlowNets can be integrated into meta-learning algorithms (GFlowMeta) by leveraging the advantages of GFlowNets on tasks with sparse rewards. However, GFlowMeta suffers from performance degradation when encountering heterogeneous transitions from distinct tasks. To overcome this challenge, this paper proposes a personalized approach named pGFlowMeta, which combines task-specific personalized policies with a meta policy. Each personalized policy balances the loss on its personalized task and the difference from the meta policy, while the meta policy aims to minimize the average loss of all tasks. The theoretical analysis shows that the algorithm converges at a sublinear rate. Extensive experiments demonstrate that the proposed algorithm outperforms state-of-the-art reinforcement learning algorithms in discrete environments.

cs.LG↗

arXiv2023

FeatureBooster: Boosting Feature Descriptors with a Lightweight Neural Network

We introduce a lightweight network to improve descriptors of keypoints within the same image. The network takes the original descriptors and the geometric properties of keypoints as the input, and uses an MLP-based self-boosting stage and a Transformer-based cross-boosting stage to enhance the descriptors. The boosted descriptors can be either real-valued or binary ones. We use the proposed network to boost both hand-crafted (ORB, SIFT) and the state-of-the-art learning-based descriptors (SuperPoint, ALIKE) and evaluate them on image matching, visual localization, and structure-from-motion tasks. The results show that our method significantly improves the performance of each task, particularly in challenging cases such as large illumination changes or repetitive patterns. Our method requires only 3.2ms on desktop GPU and 27ms on embedded GPU to process 2000 features, which is fast enough to be applied to a practical system. The code and trained weights are publicly available at github.com/SJTU-ViSYS/FeatureBooster.

cs.CV↗

arXiv2023

CRC-based Reliable WiFi Backscatter Communication for Supply Chain Management

Supply chain management is aimed to keep going long-term performance of the supply chain and minimize the costs. Backscatter technology provides a more efficient way of being able to identify items and real-time monitoring. Among the backscatter systems, the ambient backscatter communication (AmBC) system provides a prospect of ultra-low energy consumption and does not require controlled excitation devices. In this paper, we introduce CRCScatter, a CRC reverse algorithm-based AmBC system using a single access point (AP). A CRC reverse decoder is applied to reverse the ambient data from CRC32 sequence in the backscatter packet and realize single-AP decoding. Based on the nature of DBPSK modulation in WiFi signal, the CRCScatter system obtains the tag data by XOR and Differential decoder. Our simulation results verify the effectiveness of our proposed system in the low SNR regime. The average decoding time of CRCScatter system is independent of the length of tag data. Furthermore, our system can append redundant bits in the tag data to improve the decoding accuracy while not increasing the decoding time.

cs.NI↗

arXiv2023

Mastering Strategy Card Game (Legends of Code and Magic) via End-to-End Policy and Optimistic Smooth Fictitious Play

Deep Reinforcement Learning combined with Fictitious Play shows impressive results on many benchmark games, most of which are, however, single-stage. In contrast, real-world decision making problems may consist of multiple stages, where the observation spaces and the action spaces can be completely different across stages. We study a two-stage strategy card game Legends of Code and Magic and propose an end-to-end policy to address the difficulties that arise in multi-stage game. We also propose an optimistic smooth fictitious play algorithm to find the Nash Equilibrium for the two-player game. Our approach wins double championships of COG2022 competition. Extensive studies verify and show the advancement of our approach.

cs.LG↗

arXiv2023

Dynamic Private Task Assignment under Differential Privacy

Data collection is indispensable for spatial crowdsourcing services, such as resource allocation, policymaking, and scientific explorations. However, privacy issues make it challenging for users to share their information unless receiving sufficient compensation. Differential Privacy (DP) is a promising mechanism to release helpful information while protecting individuals' privacy. However, most DP mechanisms only consider a fixed compensation for each user's privacy loss. In this paper, we design a task assignment scheme that allows workers to dynamically improve their utility with dynamic distance privacy leakage. Specifically, we propose two solutions to improve the total utility of task assignment results, namely Private Utility Conflict-Elimination (PUCE) approach and Private Game Theory (PGT) approach, respectively. We prove that PUCE achieves higher utility than the state-of-the-art works. We demonstrate the efficiency and effectiveness of our PUCE and PGT approaches on both real and synthetic data sets compared with the recent distance-based approach, Private Distance Conflict-Elimination (PDCE). PUCE is always better than PDCE slightly. PGT is 50% to 63% faster than PDCE and can improve 16% utility on average when worker range is large enough.

cs.CR↗

arXiv2022

On the Effectiveness of Pinyin-Character Dual-Decoding for End-to-End Mandarin Chinese ASR

End-to-end automatic speech recognition (ASR) has achieved promising results. However, most existing end-to-end ASR methods neglect the use of specific language characteristics. For Mandarin Chinese ASR tasks, there exist mutual promotion relationship between Pinyin and Character where Chinese characters can be romanized by Pinyin. Based on the above intuition, we first investigate types of end-to-end encoder-decoder based models in the single-input dual-output (SIDO) multi-task framework, after which a novel asynchronous decoding with fuzzy Pinyin sampling method is proposed according to the one-to-one correspondence characteristics between Pinyin and Character. Furthermore, we proposed a two-stage training strategy to make training more stable and converge faster. The results on the test sets of AISHELL-1 dataset show that the proposed enhanced dual-decoder model without a language model is improved by a big margin compared to strong baseline models.

cs.CL↗

arXiv2021

Eliminating the Barriers: Demystifying Wi-Fi Baseband Design and Introducing the PicoScenes Wi-Fi Sensing Platform

The research on Wi-Fi sensing has been thriving over the past decade but the process has not been smooth. Three barriers always hamper the research: unknown baseband design and its influence, inadequate hardware, and the lack of versatile and flexible measurement software. This paper tries to eliminate these barriers through the following work. First, we present an in-depth study of the baseband design of the Qualcomm Atheros AR9300 (QCA9300) NIC. We identify a missing item of the existing CSI model, namely, the CSI distortion, and identify the baseband filter as its origin. We also propose a distortion removal method. Second, we reintroduce both the QCA9300 and software-defined radio (SDR) as powerful hardware for research. For the QCA9300, we unlock the arbitrary tuning of both the carrier frequency and bandwidth. For SDR, we develop a high?performance software implementation of the 802.11a/g/n/ac/ax baseband, allowing users to fully control the baseband and access the complete physical-layer information. Third, we release the PicoScenes software, which supports concurrent CSI measure?ment from multiple QCA9300, Intel Wireless Link (IWL5300) and SDR hardware. PicoScenes features rich low-level controls, packet injection and software baseband implementation. It also allows users to develop their own measurement plugins. Finally, we report state-of-the-art results in the extensive evaluations of the PicoScenes system, such as the >2 GHz available spectrum on the QCA9300, concurrent CSI measurement, and up to 40 kHz and 1 kHz CSI measurement rates achieved by the QCA9300 and SDR. PicoScenes is available at https://ps.zpj.io.

cs.AR↗

arXiv2018

A two-dimensional position-sensitive microchannel plate detector realized with two independent one-dimensional resistive anodes

A two-dimensional position-sensitive microchannel plate detector, with a Ø100 mm sensitive area and equipped with four integrated amplifiers, is realized with a new anode scheme. The anode is constructed by two independent one-dimensional resistive anodes, each consisting of an array of parallel copper strips connected by resistors in series on a printed circuit board. The arrays are perpendicularly aligned to realize two-dimensional position resolution, with the intervals between the adjacent strips on the PCB nearer to the MCP cut out to allow electrons passing through. The detector is tested with an 55Fe x-ray source, and a position resolution of 0.38 mm is achieved.

physics.ins-det↗

arXiv2013

Twins:Device-free Object Tracking using Passive Tags

Without requiring objects to carry any transceiver, device-free based object tracking provides a promising solution for many localization and tracking systems to monitor non-cooperative objects such as intruders. However, existing device-free solutions mainly use sensors and active RFID tags, which are much more expensive compared to passive tags. In this paper, we propose a novel motion detection and tracking method using passive RFID tags, named Twins. The method leverages a newly observed phenomenon called critical state caused by interference among passive tags. We contribute to both theory and practice of such phenomenon by presenting a new interference model that perfectly explains this phenomenon and using extensive experiments to validate it. We design a practical Twins based intrusion detection scheme and implement a real prototype with commercial off-the-shelf reader and tags. The results show that Twins is effective in detecting the moving object, with low location error of 0.75m in average.

cs.NI↗

arXiv2013

Communicating Is Crowdsourcing: Wi-Fi Indoor Localization with CSI-based Speed Estimation

Numerous indoor localization techniques have been proposed recently to meet the intensive demand for location based service, and Wi-Fi fingerprint-based approaches are the most popular and inexpensive solutions. Among them, one of the main trends is to incorporate the built-in sensors of smartphone and to exploit crowdsourcing potentials. However the noisy built-in sensors and multi-tasking limitation of underline OS often hinder the effectiveness of these schemes. In this work, we propose a passive crowdsourcing CSI-based indoor localization scheme, C2 IL. Our scheme C2 IL only requires the locating-device (e.g., a phone) to have a 802.11n wireless connection, and it does not rely on inertial sensors only existing in some smartphones. C2 IL is built upon our innovative method to accurately estimate the moving distance purely based on 802.11n Channel State Information (CSI). Our extensive evaluations show that the moving distance estimation error of our scheme is within 3% of the actual moving distance regardless of varying speeds and environment. Relying on the accurate moving distance estimation as constraints, we are able to construct a more accurate mapping between RSS fingerprints and location. To address the challenges of collecting fingerprints, a crowdsourcing- based scheme is designed to gradually establish the mapping and populate the fingerprints. In C2 IL, we design a trajectory clustering-based localization algorithm to provide precise real-time indoor localization and tracking. We developed and deployed a practical working system of C2 IL in a large office environment. Extensive evaluation results indicate that our scheme C2 IL provides accurate localization with error 2m at 80% at very complex indoor environment with minimal overhead.

cs.NI↗

arXiv2013

Rejecting the Attack: Source Authentication for Wi-Fi Management Frames using CSI Information

Comparing to well protected data frames, Wi-Fi management frames (MFs) are extremely vulnerable to various attacks. Since MFs are transmitted without encryption, attackers can forge them easily. Such attacks can be detected in cooperative environment such as Wireless Intrusion Detection System (WIDS). However, in non-cooperative environment it is difficult for a single station to identify these spoofing attacks using Received Signal Strength (RSS)-based detection, due to the strong correlation of RSS to both the transmission power (Txpower) and the location of the sender. By exploiting some unique characteristics (i.e., rapid spatial decorrelation, independence of Txpower, and much richer dimensions) of the Channel State Information (CSI), a standard feature in 802.11n Specification, we design a prototype, called CSITE, to authenticate the Wi-Fi management frames by a single station without external support. Our design CSITE, built upon off-the-shelf hardware, achieves precise spoofing detection without collaboration and in-advance finger-print. Several novel techniques are designed to address the challenges caused by user mobility and channel dynamics. To verify the performances of our solution, we implement a prototype of our design and conduct extensive evaluations in various scenarios. Our test results show that our design significantly outperforms the RSS-based method in terms of accuracy, robustness, and efficiency: we observe about 8 times improvement by CSITE over RSS-based method on the falsely accepted attacking frames.

cs.NI↗