arXiv subjects

Rui Zhou

Publications and source records attributed to Rui Zhou.

At least 127 records · Page 7Linked to original sources

arXiv2023

End-to-End Lane detection with One-to-Several Transformer

Although lane detection methods have shown impressive performance in real-world scenarios, most of methods require post-processing which is not robust enough. Therefore, end-to-end detectors like DEtection TRansformer(DETR) have been introduced in lane detection.However, one-to-one label assignment in DETR can degrade the training efficiency due to label semantic conflicts. Besides, positional query in DETR is unable to provide explicit positional prior, making it difficult to be optimized. In this paper, we present the One-to-Several Transformer(O2SFormer). We first propose the one-to-several label assignment, which combines one-to-many and one-to-one label assignment to solve label semantic conflicts while keeping end-to-end detection. To overcome the difficulty in optimizing one-to-one assignment. We further propose the layer-wise soft label which dynamically adjusts the positive weight of positive lane anchors in different decoder layers. Finally, we design the dynamic anchor-based positional query to explore positional prior by incorporating lane anchors into positional query. Experimental results show that O2SFormer with ResNet50 backbone achieves 77.83% F1 score on CULane dataset, outperforming existing Transformer-based and CNN-based detectors. Futhermore, O2SFormer converges 12.5x faster than DETR for the ResNet18 backbone.

cs.CV↗

arXiv2023

Nuclear Magnetic Resonance Measurements in High Flat-top Pulsed Magnetic Field up to 40 T at WHMFC

Nuclear magnetic resonance (NMR) technique benefits from high magnetic field not only due to the field-enhanced measurement sensitivity and resolution, but also because it is a powerful tool to investigate field-induced physics in modern material science. In this study, we successfully performed NMR measurements in high flat-top pulsed magnetic field (FTPMF) up to 40 T. A two-stage corrected FTPMF with fluctuation less than 10 mT and duration longer than 9 ms was established. Besides, a Giga-Hz NMR spectrometer and a sample probe suitable for pulsed-field condition were developed. Both free-induction-decay and spin-echo sequences were exploited for the measurements. The derived $^{93}$Nb NMR results show that the stability and homogeneity of the FTPMF reach an order of 10$^2$ ppm / 10 ms and 10$^2$ ppm / 10 mm$^3$ respectively, which is approaching a degree of maturity for some researches on condensed matter physics.

physics.ins-det↗

arXiv2023

Flashlights: An Off-Caustic Lensed Star at Redshift $z$ = 1.26 in Abell 370

We report the discovery of a transient seen in a strongly lensed arc at redshift $z_{\rm s}=1.2567$ in \emph{Hubble Space Telescope} imaging of the Abell 370 galaxy cluster. The transient is detected at $29.51\pm0.14$ AB mag in a WFC3/UVIS F200LP difference image made using observations from two different epochs, obtained in the framework of the \emph{Flashlights} program, and is also visible in the F350LP band ($m_{\rm F350LP} \approx 30.53\pm0.76$ AB mag). The transient is observed on the negative-parity side of the critical curve at a distance of $\sim 0.6"$ from it, greater than previous examples of lensed stars. The large distance from the critical curve yields a significantly smaller macromagnification, but our simulations show that bright, O/B-type supergiants can reach sufficiently high magnifications to be seen at the observed position and magnitude. In addition, the observed transient image is a trailing image with an observer-frame time delay of $\sim+0.8$ days from its expected counterpart, so that any transient lasting for longer than that should have also been seen on the minima side and is thus excluded. This, together with the blue colour we measure for the transient ($m_{\rm F200LP} - m_{\rm F350LP} \approx [-0.3,-1.6]$ AB), rules out most other transient candidates such as (kilo)novae, for example, and makes a lensed star the prime candidate. Assuming the transient is indeed a lensed star as suggested, many more such events should be detected in the near future in cluster surveys with the \emph{Hubble Space Telescope} and \emph{James Webb Space Telescope}.

astro-ph.CO↗

arXiv2023

Coherent perfect absorber and laser induced by directional emissions in the non-Hermitian photonic crystals

In this study, we propose the application of non-Hermitian photonic crystals (PCs) with anisotropic emissions. Unlike a ring of exceptional points (EPs) in isotropic non-Hermitian PCs, the EPs of anisotropic non-Hermitian PCs appear as lines symmetrical about the $Γ$ point. The non-Hermitian Hamiltonian indicates that the formation of EPs is related to the non-Hermitian strength. The real spectrum appears in the $Γ$Y direction and has been validated as the complex conjugate medium (CCM) by effective medium theory (EMT). But for the $Γ$X direction, EMT indicates that the effective refractive index has a large imaginary part, which forms an evanescent wave inside the PCs. Thence, coherent perfect absorber (CPA) and laser effects can be achieved in the directional emission of the $Γ$Y. The outgoing wave in the $Γ$X direction is weak, which can significantly reduce the losses and electromagnetic interference caused by the leakage waves. Furthermore, the non-Hermitian PCs enable many fascinating applications such as signal amplification, collimation, and angle sensors.

physics.optics↗

arXiv2023

Multi-Exposure HDR Composition by Gated Swin Transformer

Fusing a sequence of perfectly aligned images captured at various exposures, has shown great potential to approach High Dynamic Range (HDR) imaging by sensors with limited dynamic range. However, in the presence of large motion of scene objects or the camera, mis-alignment is almost inevitable and leads to the notorious ``ghost'' artifacts. Besides, factors such as the noise in the dark region or color saturation in the over-bright region may also fail to fill local image details to the HDR image. This paper provides a novel multi-exposure fusion model based on Swin Transformer. Particularly, we design feature selection gates, which are integrated with the feature extraction layers to detect outliers and block them from HDR image synthesis. To reconstruct the missing local details by well-aligned and properly-exposed regions, we exploit the long distance contextual dependency in the exposure-space pyramid by the self-attention mechanism. Extensive numerical and visual evaluation has been conducted on a variety of benchmark datasets. The experiments show that our model achieves the accuracy on par with current top performing multi-exposure HDR imaging models, while gaining higher efficiency.

cs.CV↗

arXiv2023

CAB: Empathetic Dialogue Generation with Cognition, Affection and Behavior

Empathy is an important characteristic to be considered when building a more intelligent and humanized dialogue agent. However, existing methods did not fully comprehend empathy as a complex process involving three aspects: cognition, affection and behavior. In this paper, we propose CAB, a novel framework that takes a comprehensive perspective of cognition, affection and behavior to generate empathetic responses. For cognition, we build paths between critical keywords in the dialogue by leveraging external knowledge. This is because keywords in a dialogue are the core of sentences. Building the logic relationship between keywords, which is overlooked by the majority of existing works, can improve the understanding of keywords and contextual logic, thus enhance the cognitive ability. For affection, we capture the emotional dependencies with dual latent variables that contain both interlocutors' emotions. The reason is that considering both interlocutors' emotions simultaneously helps to learn the emotional dependencies. For behavior, we use appropriate dialogue acts to guide the dialogue generation to enhance the empathy expression. Extensive experiments demonstrate that our multi-perspective model outperforms the state-of-the-art models in both automatic and manual evaluation.

cs.CL↗

arXiv2023

Online Learning Based Mobile Robot Controller Adaptation for Slip Reduction

Slip is a very common phenomena present in wheeled mobile robotic systems. It has undesirable consequences such as wasting energy and impeding system stability. To tackle the challenge of mobile robot trajectory tracking under slippery conditions, we propose a hierarchical framework that learns and adapts gains of the tracking controllers simultaneously online. Concretely, a reinforcement learning (RL) module is used to auto-tune parameters in a lateral predictive controller and a longitudinal speed PID controller. Experiments show the necessity of simultaneous gain tuning, and have demonstrated that our online framework outperforms the best baseline controller using fixed gains. By utilizing online gain adaptation, our framework achieves robust tracking performance by rejecting slip and reducing tracking errors when the mobile robot travels through various terrains.

cs.RO↗

arXiv2022

Sequential Recommendation with Causal Behavior Discovery

The key of sequential recommendation lies in the accurate item correlation modeling. Previous models infer such information based on item co-occurrences, which may fail to capture the real causal relations, and impact the recommendation performance and explainability. In this paper, we equip sequential recommendation with a novel causal discovery module to capture causalities among user behaviors. Our general idea is firstly assuming a causal graph underlying item correlations, and then we learn the causal graph jointly with the sequential recommender model by fitting the real user behavior data. More specifically, in order to satisfy the causality requirement, the causal graph is regularized by a differentiable directed acyclic constraint. Considering that the number of items in recommender systems can be very large, we represent different items with a unified set of latent clusters, and the causal graph is defined on the cluster level, which enhances the model scalability and robustness. In addition, we provide theoretical analysis on the identifiability of the learned causal graph. To the best of our knowledge, this paper makes a first step towards combining sequential recommendation with causal discovery. For evaluating the recommendation performance, we implement our framework with different neural sequential architectures, and compare them with many state-of-the-art methods based on real-world datasets. Empirical studies manifest that our model can on average improve the performance by about 7% and 11% on f1 and NDCG, respectively. To evaluate the model explainability, we build a new dataset with human labeled explanations for both quantitative and qualitative analysis.

cs.IR↗

arXiv2022

A Data Quality Assessment Framework for AI-enabled Wireless Communication

Using artificial intelligent (AI) to re-design and enhance the current wireless communication system is a promising pathway for the future sixth-generation (6G) wireless network. The performance of AI-enabled wireless communication depends heavily on the quality of wireless air-interface data. Although there are various approaches to data quality assessment (DQA) for different applications, none has been designed for wireless air-interface data. In this paper, we propose a DQA framework to measure the quality of wireless air-interface data from three aspects: similarity, diversity, and completeness. The similarity measures how close the considered datasets are in terms of their statistical distributions; the diversity measures how well-rounded a dataset is, while the completeness measures to what degree the considered dataset satisfies the required performance metrics in an application scenario. The proposed framework can be applied to various types of wireless air-interface data, such as channel state information (CSI), signal-to-interference-plus-noise ratio (SINR), reference signal received power (RSRP), etc. For simplicity, the validity of our proposed DQA framework is corroborated by applying it to CSI data and using similarity and diversity metrics to improve CSI compression and recovery in Massive MIMO systems.

eess.SP↗

arXiv2022

Speech Dereverberation with A Reverberation Time Shortening Target

This work proposes a new learning target based on reverberation time shortening (RTS) for speech dereverberation. The learning target for dereverberation is usually set as the direct-path speech or optionally with some early reflections. This type of target suddenly truncates the reverberation, and thus it may not be suitable for network training. The proposed RTS target suppresses reverberation and meanwhile maintains the exponential decaying property of reverberation, which will ease the network training, and thus reduce signal distortion caused by the prediction error. Moreover, this work experimentally study to adapt our previously proposed FullSubNet speech denoising network to speech dereverberation. Experiments show that RTS is a more suitable learning target than direct-path speech and early reflections, in terms of better suppressing reverberation and signal distortion. FullSubNet is able to achieve outstanding dereverberation performance.

eess.AS↗

arXiv2022

Flashlights: More than A Dozen High-Significance Microlensing Events of Extremely Magnified Stars in Galaxies at Redshifts z=0.7-1.5

Once only accessible in nearby galaxies, we can now study individual stars across much of the observable universe aided by galaxy-cluster gravitational lenses. When a star, compact object, or multiple such objects in the foreground galaxy-cluster lens become aligned, they can magnify a background individual star, and the timescale of a magnification peak can limit its size to tens of AU. The number and frequency of microlensing events therefore opens a window into the population of stars and compact objects, as well as high-redshift stars. To assemble the first statistical sample of stars in order to constrain the initial mass function (IMF) of massive stars at redshift z=0.7-1.5, the abundance of primordial black holes in galaxy-cluster dark matter, and the IMF of the stars making up the intracluster light, we are carrying out a 192-orbit program with the Hubble Space Telescope called "Flashlights," which is now two-thirds complete owing to scheduling challenges. We use the ultrawide F200LP and F350LP long-pass WFC3 UVIS filters and conduct two 16-orbit visits separated by one year. Having an identical roll angle during both visits, while difficult to schedule, yields extremely clean subtraction. Here we report the discovery of more than a dozen bright microlensing events, including multiple examples in the famous "Dragon Arc" discovered in the 1980s, as well as the "Spocks" and "Warhol" arcs that have hosted already known supergiants. The ultradeep observer-frame ultraviolet-through-optical imaging is sensitive to hot stars, which will complement deep James Webb Space Telescope infrared imaging. We are also acquiring Large Binocular Telescope LUCI and Keck-I MOSFIRE near-infrared spectra of the highly magnified arcs to constrain their recent star-formation histories.

astro-ph.CO↗

arXiv2022

Early results from GLASS-JWST VIII: An Extremely Magnified Blue Supergiant Star at Redshift 2.65 in the Abell 2744 Cluster Field

We report the discovery of an extremely magnified star at redshift $z=2.65$ in James Webb Space Telescope (JWST) NIRISS pre-imaging of the Abell 2744 galaxy-cluster field. The star's background host galaxy lies on a fold caustic of the foreground lens, and the cluster creates a pair of images of the region close to the lensed star. We identified the bright transient in one of the merging images at a distance of $\sim 0.15"$ from the critical curve, by subtracting the JWST F115W and F150W imaging from coadditions of archival Hubble Space Telescope (HST) F105W and F125W images and F140W and F160W images, respectively. Since the time delay between the two images should be only hours, the transient must be the microlensing event of an individual star, as opposed to a luminous stellar explosion which would persist for days to months. Analysis of individual exposures suggests that the star's magnification is not changing rapidly during the observations. From photometry of the point source through the F115W, F150W, and F200W filters, we identify a strong Balmer break, and modeling allows us to constrain the star's temperature to be approximately 7,000--12,000 K.

astro-ph.GA↗

arXiv2022

PVT-COV19D: Pyramid Vision Transformer for COVID-19 Diagnosis

With the outbreak of COVID-19, a large number of relevant studies have emerged in recent years. We propose an automatic COVID-19 diagnosis framework based on lung CT scan images, the PVT-COV19D. In order to accommodate the different dimensions of the image input, we first classified the images using Transformer models, then sampled the images in the dataset according to normal distribution, and fed the sampling results into the modified PVTv2 model for training. A large number of experiments on the COV19-CT-DB dataset demonstrate the effectiveness of the proposed method.

eess.IV↗

arXiv2022

Dynamic optimal reinsurance and dividend-payout in finite time horizon

This paper studies a dynamic optimal reinsurance and dividend-payout problem for an insurance company in a finite time horizon. The goal of the company is to maximize the expected cumulative discounted dividend payouts until bankruptcy or maturity which comes earlier. The company is allowed to buy reinsurance contracts dynamically over the whole time horizon to cede its risk exposure with other reinsurance companies. This is a mixed singular-classical control problem and the corresponding Hamilton-Jacobi-Bellman equation is a variational inequality with a fully nonlinear operator and subject to a gradient constraint. We obtain the $C^{2,1}$ smoothness of the value function and a comparison principle for its gradient function by the penalty approximation method so that one can establish an efficient numerical scheme to compute the value function. We find that the surplus-time space can be divided into three non-overlapping regions by a risk-magnitude and time-dependent reinsurance barrier and a time-dependent dividend-payout barrier. The insurance company should be exposed to a higher risk as its surplus increases; be exposed to the entire risk once its surplus upward crosses the reinsurance barrier; and pay out all its reserves exceeding the dividend-payout barrier. The estimated localities of these regions are also provided.

q-fin.MF↗

arXiv2022

Grouptron: Dynamic Multi-Scale Graph Convolutional Networks for Group-Aware Dense Crowd Trajectory Forecasting

Accurate, long-term forecasting of pedestrian trajectories in highly dynamic and interactive scenes is a long-standing challenge. Recent advances in using data-driven approaches have achieved significant improvements in terms of prediction accuracy. However, the lack of group-aware analysis has limited the performance of forecasting models. This is especially nonnegligible in highly crowded scenes, where pedestrians are moving in groups and the interactions between groups are extremely complex and dynamic. In this paper, we present Grouptron, a multi-scale dynamic forecasting framework that leverages pedestrian group detection and utilizes individual-level, group-level and scene-level information for better understanding and representation of the scenes. Our approach employs spatio-temporal clustering algorithms to identify pedestrian groups, creates spatio-temporal graphs at the individual, group, and scene levels. It then uses graph neural networks to encode dynamics at different scales and aggregate the embeddings for trajectory prediction. We conducted extensive comparisons and ablation experiments to demonstrate the effectiveness of our approach. Our method achieves 9.3% decrease in final displacement error (FDE) compared with state-of-the-art methods on ETH/UCY benchmark datasets, and 16.1% decrease in FDE in more crowded scenes where extensive human group interactions are more frequently present.

cs.CV↗

arXiv2022

Transfer Learning for Retinal Vascular Disease Detection: A Pilot Study with Diabetic Retinopathy and Retinopathy of Prematurity

Retinal vascular diseases affect the well-being of human body and sometimes provide vital signs of otherwise undetected bodily damage. Recently, deep learning techniques have been successfully applied for detection of diabetic retinopathy (DR). The main obstacle of applying deep learning techniques to detect most other retinal vascular diseases is the limited amount of data available. In this paper, we propose a transfer learning technique that aims to utilize the feature similarities for detecting retinal vascular diseases. We choose the well-studied DR detection as a source task and identify the early detection of retinopathy of prematurity (ROP) as the target task. Our experimental results demonstrate that our DR-pretrained approach dominates in all metrics the conventional ImageNet-pretrained transfer learning approach, currently adopted in medical image analysis. Moreover, our approach is more robust with respect to the stochasticity in the training process and with respect to reduced training samples. This study suggests the potential of our proposed transfer learning approach for a broad range of retinal vascular diseases or pathologies, where data is limited.

cs.LG↗

arXiv2021

Photoelectron Transportation Dynamics in GaAs Photocathodes

We report here a general theory describing photoelectron transportation dynamics in GaAs semiconductor photocathodes. Gradient doping is incorporated in the model through the inclusion of directional carrier drift. The time-evolution of electron concentration in the active layer upon the injection of an excitation pulse is solved both numerically and analytically. The predictions of the model are compared with experiments via carrier-induced transient reflectivity change, which is measured for gradient-doped and uniform-doped photocathodes using femtosecond pump-probe reflectometry. Excellent agreement is found between the experiments and the theory, leading to the characterization of key device parameters such as diffusion constant and electron decay rates. Comparisons are also made between uniform doping and gradient doping for their characteristics in photoelectron transportation. Doping gradient is found to be able to accelerate electron accumulation on the device surface. These results offer new insights into the dynamics of III-V photocathodes and potentially open a new avenue toward experimental characterization of device parameters.

physics.app-ph↗

arXiv2021

Edwards-Anderson parameter and local Ising-nematicity in FeSe revealed via NMR spectral broadening

The NMR spectrum of FeSe shows a dramatic broadening on cooling towards the bulk nematic phase at $T_s=90$ K, due to the formation of a quasi-static, short-range-ordered nematic domain structure. However, a quantitative understanding of the NMR broadening and its relationship to the nematic susceptibility is still lacking. Here, we show that the temperature and pressure dependence of the broadening is in quantitative agreement with the mean-field Edwards-Anderson parameter of an Ising-nematic model in the presence of random-field disorder introduced by non-magnetic impurities. Furthermore, these results reconcile the interpretation of NMR and Raman spectroscopy data in FeSe under pressure.

cond-mat.str-el↗