arXiv subjects

Xin Chen

Publications and source records attributed to Xin Chen.

At least 469 records · Page 26Linked to original sources

arXiv2022

Entanglement-assisted detection of fading targets via correlation-to-coherence conversion

Quantum illumination utilizes an entanglement-enhanced sensing system to outperform classical illumination in detecting a suspected target, despite the entanglement-breaking loss and noise. However, practical and optimal receiver design to fulfil the quantum advantage has been a long open problem. Recently, [arXiv:2207.06609] proposed the correlation-to-displacement (`C$\rightarrow$D') conversion module to enable an optimal receiver design that greatly reduces the complexity of the previous known optimal receiver [Phys. Rev. Lett. {\bf 118}, 040801 (2017)]. There, the analyses of the conversion module assume an ideal target with a known reflectivity and a fixed return phase. In practical applications, however, targets often induce a random return phase; moreover, their reflectivities can have fluctuations obeying a Rayleigh-distribution. In this work, we extend the analyses of the C$\rightarrow$D module to realistic targets and show that the entanglement advantage is maintained albeit reduced. In particular, the conversion module allows exact and efficient performance evaluation despite the non-Gaussian nature of the quantum channel involved.

quant-ph↗

arXiv2022

Entanglement-enhanced optomechanical sensor array for dark matter searches

The nature of dark matter is one of the most important open questions in modern physics. The search for dark matter is challenging since, besides gravitational interaction, it feebly interacts with ordinary matter. Mechanical sensors are one of the leading candidates for dark matter searches in the low frequency region. Here, we propose entanglement-enhanced optomechanical sensing systems to assist the search for DM with mechanical sensing devices. To assess the performance of our setup, we adopt the integrated sensitivity, which is particularly suitable for broadband sensing as it precisely quantifies the bandwidth-sensitivity tradeoff of the system. We then show that, by coherently operating the optomechanical sensor array and utilizing continuous-variable multi-partite entanglement between the optical fields, the array of sensors has a scaling advantage over independent sensors (i.e., $\sqrt{M}\rightarrow M$, where $M$ is the number of sensors) as well as a performance boost due to entanglement. Such an advantage is robust to imhomogeneities of the mechanical sensors and is achievable with off-the-shelf experimental components.

quant-ph↗

arXiv2022

High-Performance Transformer Tracking

Correlation has a critical role in the tracking field, especially in recent popular Siamese-based trackers. The correlation operation is a simple fusion method that considers the similarity between the template and the search region. However, the correlation operation is a local linear matching process, losing semantic information and easily falling into a local optimum, which may be the bottleneck in designing high-accuracy tracking algorithms. In this work, to determine whether a better feature fusion method exists than correlation, a novel attention-based feature fusion network, inspired by the transformer, is presented. This network effectively combines the template and search region features using attention. Specifically, the proposed method includes an ego-context augment module based on self-attention and a cross-feature augment module based on cross-attention. First, we present a transformer tracking (named TransT) method based on the Siamese-like feature extraction backbone, the designed attention-based fusion mechanism, and the classification and regression head. Based on the TransT baseline, we further design a segmentation branch to generate an accurate mask. Finally, we propose a stronger version of TransT by extending TransT with a multi-template scheme and an IoU prediction head, named TransT-M. Experiments show that our TransT and TransT-M methods achieve promising results on seven popular datasets. Code and models are available at https://github.com/chenxin-dlut/TransT-M.

cs.CV↗

arXiv2022

An Improved End-to-End Multi-Target Tracking Method Based on Transformer Self-Attention

This study proposes an improved end-to-end multi-target tracking algorithm that adapts to multi-view multi-scale scenes based on the self-attentive mechanism of the transformer's encoder-decoder structure. A multi-dimensional feature extraction backbone network is combined with a self-built semantic raster map, which is stored in the encoder for correlation and generates target position encoding and multi-dimensional feature vectors. The decoder incorporates four methods: spatial clustering and semantic filtering of multi-view targets, dynamic matching of multi-dimensional features, space-time logic-based multi-target tracking, and space-time convergence network (STCN)-based parameter passing. Through the fusion of multiple decoding methods, muti-camera targets are tracked in three dimensions: temporal logic, spatial logic, and feature matching. For the MOT17 dataset, this study's method significantly outperforms the current state-of-the-art method MiniTrackV2 [49] by 2.2% to 0.836 on Multiple Object Tracking Accuracy(MOTA) metric. Furthermore, this study proposes a retrospective mechanism for the first time, and adopts a reverse-order processing method to optimise the historical mislabeled targets for improving the Identification F1-score(IDF1). For the self-built dataset OVIT-MOT01, the IDF1 improves from 0.948 to 0.967, and the Multi-camera Tracking Accuracy(MCTA) improves from 0.878 to 0.909, which significantly improves the continuous tracking accuracy and scene adaptation. This research method introduces a new attentional tracking paradigm which is able to achieve state-of-the-art performance on multi-target tracking (MOT17 and OVIT-MOT01) tasks.

cs.CV↗

arXiv2022

Pangu-Weather: A 3D High-Resolution Model for Fast and Accurate Global Weather Forecast

In this paper, we present Pangu-Weather, a deep learning based system for fast and accurate global weather forecast. For this purpose, we establish a data-driven environment by downloading $43$ years of hourly global weather data from the 5th generation of ECMWF reanalysis (ERA5) data and train a few deep neural networks with about $256$ million parameters in total. The spatial resolution of forecast is $0.25^\circ\times0.25^\circ$, comparable to the ECMWF Integrated Forecast Systems (IFS). More importantly, for the first time, an AI-based method outperforms state-of-the-art numerical weather prediction (NWP) methods in terms of accuracy (latitude-weighted RMSE and ACC) of all factors (e.g., geopotential, specific humidity, wind speed, temperature, etc.) and in all time ranges (from one hour to one week). There are two key strategies to improve the prediction accuracy: (i) designing a 3D Earth Specific Transformer (3DEST) architecture that formulates the height (pressure level) information into cubic data, and (ii) applying a hierarchical temporal aggregation algorithm to alleviate cumulative forecast errors. In deterministic forecast, Pangu-Weather shows great advantages for short to medium-range forecast (i.e., forecast time ranges from one hour to one week). Pangu-Weather supports a wide range of downstream forecast scenarios, including extreme weather forecast (e.g., tropical cyclone tracking) and large-member ensemble forecast in real-time. Pangu-Weather not only ends the debate on whether AI-based methods can surpass conventional NWP methods, but also reveals novel directions for improving deep learning weather forecast systems.

physics.ao-ph↗

arXiv2022

Configuring Intelligent Reflecting Surface with Performance Guarantees: Blind Beamforming

This work gives a blind beamforming strategy for intelligent reflecting surface (IRS), aiming to boost the received signal-to-noise ratio (SNR) by coordinating phase shifts across reflective elements in the absence of channel information. While the existing methods of IRS beamforming typically first estimate channels and then optimize phase shifts, we propose a conditional sample mean based statistical approach that explores the wireless environment via random sampling without performing any channel estimation. Remarkably, the new method just requires a polynomial number of random samples to yield an SNR boost that is quadratic in the number of reflective elements, whereas the standard random-max sampling algorithm can only achieve a linear boost under the same condition. Moreover, we gain additional insight into blind beamforming by interpreting it as a least squares problem. Field tests demonstrate the significant advantages of the proposed blind beamforming algorithm over the benchmark algorithms in enhancing wireless transmission.

cs.IT↗

arXiv2022

Towards Relation-centered Pooling and Convolution for Heterogeneous Graph Learning Networks

Heterogeneous graph neural network has unleashed great potential on graph representation learning and shown superior performance on downstream tasks such as node classification and clustering. Existing heterogeneous graph learning networks are primarily designed to either rely on pre-defined meta-paths or use attention mechanisms for type-specific attentive message propagation on different nodes/edges, incurring many customization efforts and computational costs. To this end, we design a relation-centered Pooling and Convolution for Heterogeneous Graph learning Network, namely PC-HGN, to enable relation-specific sampling and cross-relation convolutions, from which the structural heterogeneity of the graph can be better encoded into the embedding space through the adaptive training process. We evaluate the performance of the proposed model by comparing with state-of-the-art graph learning models on three different real-world datasets, and the results show that PC-HGN consistently outperforms all the baseline and improves the performance maximumly up by 17.8%.

cs.LG↗

arXiv2022

Efficient Visual Tracking via Hierarchical Cross-Attention Transformer

In recent years, target tracking has made great progress in accuracy. This development is mainly attributed to powerful networks (such as transformers) and additional modules (such as online update and refinement modules). However, less attention has been paid to tracking speed. Most state-of-the-art trackers are satisfied with the real-time speed on powerful GPUs. However, practical applications necessitate higher requirements for tracking speed, especially when edge platforms with limited resources are used. In this work, we present an efficient tracking method via a hierarchical cross-attention transformer named HCAT. Our model runs about 195 fps on GPU, 45 fps on CPU, and 55 fps on the edge AI platform of NVidia Jetson AGX Xavier. Experiments show that our HCAT achieves promising results on LaSOT, GOT-10k, TrackingNet, NFS, OTB100, UAV123, and VOT2020. Code and models are available at https://github.com/chenxin-dlut/HCAT.

cs.CV↗

arXiv2022

2D and 3D CT Radiomic Features Performance Comparison in Characterization of Gastric Cancer: A Multi-center Study

Objective: Radiomics, an emerging tool for medical image analysis, is potential towards precisely characterizing gastric cancer (GC). Whether using one-slice 2D annotation or whole-volume 3D annotation remains a long-time debate, especially for heterogeneous GC. We comprehensively compared 2D and 3D radiomic features' representation and discrimination capacity regarding GC, via three tasks. Methods: Four-center 539 GC patients were retrospectively enrolled and divided into the training and validation cohorts. From 2D or 3D regions of interest (ROIs) annotated by radiologists, radiomic features were extracted respectively. Feature selection and model construction procedures were customed for each combination of two modalities (2D or 3D) and three tasks. Subsequently, six machine learning models (Model_2D^LNM, Model_3D^LNM; Model_2D^LVI, Model_3D^LVI; Model_2D^pT, Model_3D^pT) were derived and evaluated to reflect modalities' performances in characterizing GC. Furthermore, we performed an auxiliary experiment to assess modalities' performances when resampling spacing is different. Results: Regarding three tasks, the yielded areas under the curve (AUCs) were: Model_2D^LNM's 0.712 (95% confidence interval, 0.613-0.811), Model_3D^LNM's 0.680 (0.584-0.775); Model_2D^LVI's 0.677 (0.595-0.761), Model_3D^LVI's 0.615 (0.528-0.703); Model_2D^pT's 0.840 (0.779-0.901), Model_3D^pT's 0.813 (0.747-0.879). Moreover, the auxiliary experiment indicated that Models_2D are statistically more advantageous than Models3D with different resampling spacings. Conclusion: Models constructed with 2D radiomic features revealed comparable performances with those constructed with 3D features in characterizing GC. Significance: Our work indicated that time-saving 2D annotation would be the better choice in GC, and provided a related reference to further radiomics-based researches.

eess.IV↗

arXiv2022

Learning Variational Motion Prior for Video-based Motion Capture

Motion capture from a monocular video is fundamental and crucial for us humans to naturally experience and interact with each other in Virtual Reality (VR) and Augmented Reality (AR). However, existing methods still struggle with challenging cases involving self-occlusion and complex poses due to the lack of effective motion prior modeling. In this paper, we present a novel variational motion prior (VMP) learning approach for video-based motion capture to resolve the above issue. Instead of directly building the correspondence between the video and motion domain, We propose to learn a generic latent space for capturing the prior distribution of all natural motions, which serve as the basis for subsequent video-based motion capture tasks. To improve the generalization capacity of prior space, we propose a transformer-based variational autoencoder pretrained over marker-based 3D mocap data, with a novel style-mapping block to boost the generation quality. Afterward, a separate video encoder is attached to the pretrained motion generator for end-to-end fine-tuning over task-specific video datasets. Compared to existing motion prior models, our VMP model serves as a motion rectifier that can effectively reduce temporal jittering and failure modes in frame-wise pose estimation, leading to temporally stable and visually realistic motion capture results. Furthermore, our VMP-based framework models motion at sequence level and can directly generate motion clips in the forward pass, achieving real-time motion capture during inference. Extensive experiments over both public datasets and in-the-wild videos have demonstrated the efficacy and generalization capability of our framework.

cs.CV↗

arXiv2022

DIICAN: Dual Time-scale State-Coupled Co-estimation of SOC, SOH and RUL for Lithium-Ion Batteries

Accurate co-estimations of battery states, such as state-of-charge (SOC), state-of-health (SOH,) and remaining useful life (RUL), are crucial to the battery management systems to assure safe and reliable management. Although the external properties of the battery charge with the aging degree, batteries' degradation mechanism shares similar evolving patterns. Since batteries are complicated chemical systems, these states are highly coupled with intricate electrochemical processes. A state-coupled co-estimation method named Deep Inter and Intra-Cycle Attention Network (DIICAN) is proposed in this paper to estimate SOC, SOH, and RUL, which organizes battery measurement data into the intra-cycle and inter-cycle time scales. And to extract degradation-related features automatically and adapt to practical working conditions, the convolutional neural network is applied. The state degradation attention unit is utilized to extract the battery state evolution pattern and evaluate the battery degradation degree. To account for the influence of battery aging on the SOC estimation, the battery degradation-related state is incorporated in the SOC estimation for capacity calibration. The DIICAN method is validated on the Oxford battery dataset. The experimental results show that the proposed method can achieve SOH and RUL co-estimation with high accuracy and effectively improve SOC estimation accuracy for the whole lifespan.

eess.SY↗

arXiv2022

Motion-related Artefact Classification Using Patch-based Ensemble and Transfer Learning in Cardiac MRI

Cardiac Magnetic Resonance Imaging (MRI) plays an important role in the analysis of cardiac function. However, the acquisition is often accompanied by motion artefacts because of the difficulty of breath-hold, especially for acute symptoms patients. Therefore, it is essential to assess the quality of cardiac MRI for further analysis. Time-consuming manual-based classification is not conducive to the construction of an end-to-end computer aided diagnostic system. To overcome this problem, an automatic cardiac MRI quality estimation framework using ensemble and transfer learning is proposed in this work. Multiple pre-trained models were initialised and fine-tuned on 2-dimensional image patches sampled from the training data. In the model inference process, decisions from these models are aggregated to make a final prediction. The framework has been evaluated on CMRxMotion grand challenge (MICCAI 2022) dataset which is small, multi-class, and imbalanced. It achieved a classification accuracy of 78.8% and 70.0% on the training set (5-fold cross-validation) and a validation set, respectively. The final trained model was also evaluated on an independent test set by the CMRxMotion organisers, which achieved the classification accuracy of 72.5% and Cohen's Kappa of 0.6309 (ranked top 1 in this grand challenge). Our code is available on Github: https://github.com/ruizhe-l/CMRxMotion.

eess.IV↗

arXiv2022

Transfer Deep Reinforcement Learning-based Large-scale V2G Continuous Charging Coordination with Renewable Energy Sources

Due to the increasing popularity of electric vehicles (EVs) and the technological advancement of EV electronics, the vehicle-to-grid (V2G) technique and large-scale scheduling algorithms have been developed to achieve a high level of renewable energy and power grid stability. This paper proposes a deep reinforcement learning (DRL) method for the continuous charging/discharging coordination strategy in aggregating large-scale EVs in V2G mode with renewable energy sources (RES). The DRL coordination strategy can efficiently optimize the electric vehicle aggregator's (EVA's) real-time charging/discharging power with the state of charge (SOC) constraints of the EVA and the individual EV. Compared with uncontrolled charging, the load variance is reduced by 97.37$\%$ and the charging cost by 76.56$\%$. The DRL coordination strategy further demonstrates outstanding transfer learning ability to microgrids with RES and large-scale EVA, as well as the complicated weekly scheduling. The DRL coordination strategy demonstrates flexible, adaptable, and scalable performance for the large-scale V2G under realistic operating conditions.

eess.SY↗

arXiv2022

ConvTransSeg: A Multi-resolution Convolution-Transformer Network for Medical Image Segmentation

Convolutional neural networks (CNNs) achieved the state-of-the-art performance in medical image segmentation due to their ability to extract highly complex feature representations. However, it is argued in recent studies that traditional CNNs lack the intelligence to capture long-term dependencies of different image regions. Following the success of applying Transformer models on natural language processing tasks, the medical image segmentation field has also witnessed growing interest in utilizing Transformers, due to their ability to capture long-range contextual information. However, unlike CNNs, Transformers lack the ability to learn local feature representations. Thus, to fully utilize the advantages of both CNNs and Transformers, we propose a hybrid encoder-decoder segmentation model (ConvTransSeg). It consists of a multi-layer CNN as the encoder for feature learning and the corresponding multi-level Transformer as the decoder for segmentation prediction. The encoder and decoder are interconnected in a multi-resolution manner. We compared our method with many other state-of-the-art hybrid CNN and Transformer segmentation models on binary and multiple class image segmentation tasks using several public medical image datasets, including skin lesion, polyp, cell and brain tissue. The experimental results show that our method achieves overall the best performance in terms of Dice coefficient and average symmetric surface distance measures with low model complexity and memory consumption. In contrast to most Transformer-based methods that we compared, our method does not require the use of pre-trained models to achieve similar or better performance. The code is freely available for research purposes on Github: (the link will be added upon acceptance).

cs.CV↗

arXiv2022

AstBERT: Enabling Language Model for Financial Code Understanding with Abstract Syntax Trees

Using the pre-trained language models to understand source codes has attracted increasing attention from financial institutions owing to the great potential to uncover financial risks. However, there are several challenges in applying these language models to solve programming language-related problems directly. For instance, the shift of domain knowledge between natural language (NL) and programming language (PL) requires understanding the semantic and syntactic information from the data from different perspectives. To this end, we propose the AstBERT model, a pre-trained PL model aiming to better understand the financial codes using the abstract syntax tree (AST). Specifically, we collect a sheer number of source codes (both Java and Python) from the Alipay code repository and incorporate both syntactic and semantic code knowledge into our model through the help of code parsers, in which AST information of the source codes can be interpreted and integrated. We evaluate the performance of the proposed model on three tasks, including code question answering, code clone detection and code refinement. Experiment results show that our AstBERT achieves promising performance on three different downstream tasks.

cs.AI↗

arXiv2022

Assortment Optimization Under the Multivariate MNL Model

We study an assortment optimization problem under a multi-purchase choice model in which customers choose a bundle of up to one product from each of two product categories. Different bundles have different utilities and the bundle price is the summation of the prices of products in it. For the uncapacitated setting where any set of products can be offered, we prove that this problem is strongly NP-hard. We show that an adjusted-revenue-ordered assortment provides a 1/2-approximation. Furthermore, we develop an approximation framework based on a linear programming relaxation of the problem and obtain a 0.74-approximation algorithm. This approximation ratio almost matches the integrality gap of the linear program, which is proven to be at most 0.75. For the capacitated setting, we prove that there does not exist a constant-factor approximation algorithm assuming the Exponential Time Hypothesis. The same hardness result holds for settings with general bundle prices or more than two categories. Finally, we conduct numerical experiments on randomly generated problem instances. The average approximation ratios of our algorithms are over 99%.

cs.DS↗

arXiv2022

Online and semi-online scheduling on two hierarchical machines with a common due date to maximize the total early work

In this study, we investigated several online and semi-online scheduling problems on two hierarchical machines with a common due date to maximize the total early work. For the pure online case, we designed an optimal online algorithm with a competitive ratio of $\sqrt 2$. For the case when the total processing time is known, we proposed an optimal semi-online algorithm with a competitive ratio of $\frac{4}{3}$. Additionally, for the cases when the largest processing time is known, we gave optimal algorithms with a competitive ratio of $\frac{6}{5}$ if the largest job is a lower hierarchy one, and of $\sqrt 5-1$ if the largest job is a higher hierarchy one, respectively.

cs.DS↗

arXiv2022

Magnetization switching in polycrystalline Mn3Sn thin film induced by self-generated spin-polarized current

Electrical manipulation of spins is essential to design state-of-the-art spintronic devices and commonly relies on the spin current injected from a second heavy-metal material. The fact that chiral antiferromagnets produce spin current inspires us to explore the magnetization switching of chiral spins using self-generated spin torque. Here, we demonstrate the electric switching of noncollinear antiferromagnetic state in Mn3Sn by observing a crossover from conventional spin-orbit torque to the self-generated spin torque when increasing the MgO thickness in Ta/MgO/Mn3Sn polycrystalline films. The spin current injection from the Ta layer can be controlled and even blocked by varying the MgO thickness, but the switching sustains even at a large MgO thickness. Furthermore, the switching polarity reverses when the MgO thickness exceeds around 3 nm, which cannot be explained by the spin-orbit torque scenario due to spin current injection from the Ta layer. Evident current-induced switching is also observed in MgO/Mn3Sn and Ti/Mn3Sn bilayers, where external injection of spin Hall current to Mn3Sn is negligible. The inter-grain spin-transfer torque induced by spin-polarized current explains the experimental observations. Our findings provide an alternative pathway for electrical manipulation of non-collinear antiferromagnetic state without resorting to the conventional bilayer structure.

cond-mat.mtrl-sci↗