arXiv subjects

Yuan Chen

Publications and source records attributed to Yuan Chen.

At least 91 records · Page 5Linked to original sources

arXiv2023

Cross-Dataset-Robust Method for Blind Real-World Image Quality Assessment

Although many effective models and real-world datasets have been presented for blind image quality assessment (BIQA), recent BIQA models usually tend to fit specific training set. Hence, it is still difficult to accurately and robustly measure the visual quality of an arbitrary real-world image. In this paper, a robust BIQA method, is designed based on three aspects, i.e., robust training strategy, large-scale real-world dataset, and powerful backbone. First, many individual models based on popular and state-of-the-art (SOTA) Swin-Transformer (SwinT) are trained on different real-world BIQA datasets respectively. Then, these biased SwinT-based models are jointly used to generate pseudo-labels, which adopts the probability of relative quality of two random images instead of fixed quality score. A large-scale real-world image dataset with 1,000,000 image pairs and pseudo-labels is then proposed for training the final cross-dataset-robust model. Experimental results on cross-dataset tests show that the performance of the proposed method is even better than some SOTA methods that are directly trained on these datasets, thus verifying the robustness and generalization of our method.

cs.CV↗

arXiv2023

Towards Vehicle-to-everything Autonomous Driving: A Survey on Collaborative Perception

Vehicle-to-everything (V2X) autonomous driving opens up a promising direction for developing a new generation of intelligent transportation systems. Collaborative perception (CP) as an essential component to achieve V2X can overcome the inherent limitations of individual perception, including occlusion and long-range perception. In this survey, we provide a comprehensive review of CP methods for V2X scenarios, bringing a profound and in-depth understanding to the community. Specifically, we first introduce the architecture and workflow of typical V2X systems, which affords a broader perspective to understand the entire V2X system and the role of CP within it. Then, we thoroughly summarize and analyze existing V2X perception datasets and CP methods. Particularly, we introduce numerous CP methods from various crucial perspectives, including collaboration stages, roadside sensors placement, latency compensation, performance-bandwidth trade-off, attack/defense, pose alignment, etc. Moreover, we conduct extensive experimental analyses to compare and examine current CP methods, revealing some essential and unexplored insights. Specifically, we analyze the performance changes of different methods under different bandwidths, providing a deep insight into the performance-bandwidth trade-off issue. Also, we examine methods under different LiDAR ranges. To study the model robustness, we further investigate the effects of various simulated real-world noises on the performance of different CP methods, covering communication latency, lossy communication, localization errors, and mixed noises. In addition, we look into the sim-to-real generalization ability of existing CP methods. At last, we thoroughly discuss issues and challenges, highlighting promising directions for future efforts. Our codes for experimental analysis will be public at https://github.com/memberRE/Collaborative-Perception.

cs.CV↗

arXiv2023

Parameterized Density Functional Models for Block Copolymer Melts

The derivation of density functional energies from the random phase approximation of self-consistent mean field theory is generalized and applied to a binary blend of diblock copolymers and homopolymers. A nonlocal transformation is incorporated into the density functional model prior to the strong segregation extrapolation step employed by Uneyama and Doi. The transformation affords a systematic parameterization of the free energy that preserves key structural features such as scattering structure factor. A simple choice of transformation is shown to incorporate the Tuebner and Strey microemulsion structure factor and provide a reduction to the microemulsion free energy. Without adjustable parameters, the associated phase diagrams are compared to experimental and self consistent mean field based results. A gradient descent of the free energy recovers dependence of end-state morphology on initial configurations, and identifies coexisting microstructures and transitions to two-phase behavior. Small angle x-ray data is simulated and used in classification of microphase morphology.

cond-mat.soft↗

arXiv2023

Supervised Auto-Encoding Twin-Bottleneck Hashing

Deep hashing has shown to be a complexity-efficient solution for the Approximate Nearest Neighbor search problem in high dimensional space. Many methods usually build the loss function from pairwise or triplet data points to capture the local similarity structure. Other existing methods construct the similarity graph and consider all points simultaneously. Auto-encoding Twin-bottleneck Hashing is one such method that dynamically builds the graph. Specifically, each input data is encoded into a binary code and a continuous variable, or the so-called twin bottlenecks. The similarity graph is then computed from these binary codes, which get updated consistently during the training. In this work, we generalize the original model into a supervised deep hashing network by incorporating the label information. In addition, we examine the differences of codes structure between these two networks and consider the class imbalance problem especially in multi-labeled datasets. Experiments on three datasets yield statistically significant improvement against the original model. Results are also comparable and competitive to other supervised methods.

cs.LG↗

arXiv2023

$SL(2,R)\times U(1)$ symmetry and quasinormal modes in the self-dual warped AdS black hole

The algebraic approach to the spectrum of quasinormal modes has been made as simple as possible for the BTZ black hole by the strategy developed in \cite{Zhang}. By working with the self-dual warped AdS black hole, we demonstrate in an explicit way that such a strategy can be well adapted to those warped AdS balck holes with the $SL(2,R)\times U(1)$ isometry. To this end, we first introduce two associated tensor fields with the quadratic Casimir of $SL(2,R)\times U(1)$ Lie algebra in the self-dual warped AdS black hole and show that they correspond essentially to the metric and volume element up to a constant prefactor, respectively. Then without appealing to any concrete coordinate system, we can further show that the solutions to the equations of motion for the scalar, vector, spinor fields all fall into the representations of the $SL(2,R)\times U(1)$ Lie algebra by a purely abstract tensor and spinor analysis. Accordingly, the corresponding spectrum of quasinormal modes for each fixed azimuthal quantum number can be derived algebraically as the infinite tower of descendants of the highest weight mode of the $SL(2,R)$ Lie subalgebra.

hep-th↗

arXiv2023

Sufficient conditions for the existence of path-factors with given properties

A spanning subgraph $H$ of a graph $G$ is called a $P_{\geq k}$-factor of $G$ if every component of $H$ is isomorphic to a path of order at least $k$, where $k\geq2$ is an integer. A graph $G$ is called a $(P_{\geq k},l)$-factor critical graph if $G-V'$ contains a $P_{\geq k}$-factor for any $V'\subseteq V(G)$ with $|V'|=l$. A graph $G$ is called a $(P_{\geq k},m)$-factor deleted graph if $G-E'$ has a $P_{\geq k}$-factor for any $E'\subseteq E(G)$ with $|E'|=m$. Intuitively, if a graph is dense enough, it will have a $P_{\geq 3}$-factor. In this paper, we give some sufficient conditions for a graph to be a $(P_{\geq 3},l)$-factor critical graph or a $(P_{\geq 3},m)$-factor deleted graph. In this paper, we demonstrate that (i) $G$ is a $(P_{\geq 3},l)$-factor critical graph if its sun toughness $s(G)>\frac{l+1}{3}$ and $κ(G)\geq l+2$. (ii) $G$ is a $(P_{\geq 3},l)$-factor critical graph if its degree sum $σ_3(G)\geq n+2l$ and $κ(G)\geq l+1$. (iii) $G$ is a $(P_{\geq 3},m)$-factor deleted graph if its sun toughness $s(G)\geq \frac{m+1}{m+2}$ and $κ(G)\geq 2m+1$. (iv) $G$ is a $(P_{\geq 3},m)$-factor deleted graph if its degree sum $σ_3(G)\geq n+2m$ and $κ(G)\geq 2m+1$.

math.CO↗

arXiv2023

Learning Stochastic Dynamical System via Flow Map Operator

We present a numerical framework for learning unknown stochastic dynamical systems using measurement data. Termed stochastic flow map learning (sFML), the new framework is an extension of flow map learning (FML) that was developed for learning deterministic dynamical systems. For learning stochastic systems, we define a stochastic flow map that is a superposition of two sub-flow maps: a deterministic sub-map and a stochastic sub-map. The stochastic training data are used to construct the deterministic sub-map first, followed by the stochastic sub-map. The deterministic sub-map takes the form of residual network (ResNet), similar to the work of FML for deterministic systems. For the stochastic sub-map, we employ a generative model, particularly generative adversarial networks (GANs) in this paper. The final constructed stochastic flow map then defines a stochastic evolution model that is a weak approximation, in term of distribution, of the unknown stochastic system. A comprehensive set of numerical examples are presented to demonstrate the flexibility and effectiveness of the proposed sFML method for various types of stochastic systems.

cs.LG↗

arXiv2023

Mixed-Response State-Space Model for Analyzing Multi-Dimensional Digital Phenotypes

Digital technologies (e.g., mobile phones) can be used to obtain objective, frequent, and real-world digital phenotypes from individuals. However, modeling these data poses substantial challenges since observational data are subject to confounding and various sources of variabilities. For example, signals on patients' underlying health status and treatment effects are mixed with variation due to the living environment and measurement noises. The digital phenotype data thus shows extensive variabilities between- and within-patient as well as across different health domains (e.g., motor, cognitive, and speaking). Motivated by a mobile health study of Parkinson's disease (PD), we develop a mixed-response state-space (MRSS) model to jointly capture multi-dimensional, multi-modal digital phenotypes and their measurement processes by a finite number of latent state time series. These latent states reflect the dynamic health status and personalized time-varying treatment effects and can be used to adjust for informative measurements. For computation, we use the Kalman filter for Gaussian phenotypes and importance sampling with Laplace approximation for non-Gaussian phenotypes. We conduct comprehensive simulation studies and demonstrate the advantage of MRSS in modeling a mobile health study that remotely collects real-time digital phenotypes from PD patients.

stat.AP↗

arXiv2023

Deep Reinforcement Learning for Localizability-Enhanced Navigation in Dynamic Human Environments

Reliable localization is crucial for autonomous robots to navigate efficiently and safely. Some navigation methods can plan paths with high localizability (which describes the capability of acquiring reliable localization). By following these paths, the robot can access the sensor streams that facilitate more accurate location estimation results by the localization algorithms. However, most of these methods require prior knowledge and struggle to adapt to unseen scenarios or dynamic changes. To overcome these limitations, we propose a novel approach for localizability-enhanced navigation via deep reinforcement learning in dynamic human environments. Our proposed planner automatically extracts geometric features from 2D laser data that are helpful for localization. The planner learns to assign different importance to the geometric features and encourages the robot to navigate through areas that are helpful for laser localization. To facilitate the learning of the planner, we suggest two techniques: (1) an augmented state representation that considers the dynamic changes and the confidence of the localization results, which provides more information and allows the robot to make better decisions, (2) a reward metric that is capable to offer both sparse and dense feedback on behaviors that affect localization accuracy. Our method exhibits significant improvements in lost rate and arrival rate when tested in previously unseen environments.

cs.RO↗

arXiv2023

High energy beam energy measurement with microwave-electron Compton backscattering

The uncertainty of the energy measurement of the electron beam on circular electron positron collider (CEPC) must be smaller than 10$\mathrm{MeV}$ to make sure the accurate measurement of the mass of the Higgs boson. In order to simplify the energy measurement system, a new method is proposed by fitting the Compton edge of the energy distribution of the gamma ray from a microwave-electron Compton scattering. With our method, the uncertainty of the energy measurement is 6$\mathrm{MeV}$ for the electron energy of $120\mathrm{GeV}$ in the Higgs mode. In this system, the energy resolution of the gamma detection needs to reach $10^{-4}$. Therefore, only the high-purity germanium (HPGe) detector can meet the critical requirement. In a head-on collision mode, the initial photons should be microwave photons with the wavelength of 3.04 centimeters. A cylindrical resonant cavity with selected ${TM_{010}}$ mode is used to transmit microwaves. After the microwave-electron Compton backscattering, the scattered photons and the synchrotron-radiation background transmit a shielding structure and then are detected by a HPGe detector at the end of the beam line of the synchrotron-radiation applications. The hole radius in the side wall of the cavity is about $1.5\mathrm{mm}$ to allow the electron beam passing through. The results of the computer simulation technology (CST) software shows that the influence of the hole radius on the cavity field is negligible. The change of the resonance frequency can be easily corrected by fine-tuning the cavity size.

hep-ex↗

arXiv2023

The linear and nonlinear inverse Compton scattering between microwaves and electrons in a resonant cavity

The new scheme of the energy measurement of the extremely high energy electron beam with the inverse Compton scattering between electrons and microwave photons requires the precise calculation of the interaction cross section of electrons and microwave photons in a resonant cavity. In the local space of the cavity, the electromagnetic field is expressed by Bessel functions. Although Bessel functions can form a complete set of orthogonal basis, it is difficult to quantify them directly as fundamental wave functions. Fortunately, with the Fourier expansion of Bessel functions, the local electromagnetic field can be considered as the superposition of a series of plane waves. Therefore, with corresponding corrections of the cross section formula of the classical Compton scattering, the cross section of the linear or nonlinear microwave Compton scattering in the local space can be described accurately. As an important application of our results in astrophysics, corresponding ground verification devices can be designed to perform experimental verifications on the prediction of the Sunyaev-Zeldovich (SZ) effect of the cosmic microwave background radiation. Our results could also provide a new way to generate wave sources with strong practical value, such as the terahertz waves, the ultra-violet (EUV) waves, or the mid-infrared beams.

physics.plasm-ph↗

arXiv2022

Post-Training Quantization for Cross-Platform Learned Image Compression

It has been witnessed that learned image compression has outperformed conventional image coding techniques and tends to be practical in industrial applications. One of the most critical issues that need to be considered is the non-deterministic calculation, which makes the probability prediction cross-platform inconsistent and frustrates successful decoding. We propose to solve this problem by introducing well-developed post-training quantization and making the model inference integer-arithmetic-only, which is much simpler than presently existing training and fine-tuning based approaches yet still keeps the superior rate-distortion performance of learned image compression. Based on that, we further improve the discretization of the entropy parameters and extend the deterministic inference to fit Gaussian mixture models. With our proposed methods, the current state-of-the-art image compression models can infer in a cross-platform consistent manner, which makes the further development and practice of learned image compression more promising.

eess.IV↗

arXiv2022

Where is VALDO? VAscular Lesions Detection and segmentatiOn challenge at MICCAI 2021

Imaging markers of cerebral small vessel disease provide valuable information on brain health, but their manual assessment is time-consuming and hampered by substantial intra- and interrater variability. Automated rating may benefit biomedical research, as well as clinical assessment, but diagnostic reliability of existing algorithms is unknown. Here, we present the results of the \textit{VAscular Lesions DetectiOn and Segmentation} (\textit{Where is VALDO?}) challenge that was run as a satellite event at the international conference on Medical Image Computing and Computer Aided Intervention (MICCAI) 2021. This challenge aimed to promote the development of methods for automated detection and segmentation of small and sparse imaging markers of cerebral small vessel disease, namely enlarged perivascular spaces (EPVS) (Task 1), cerebral microbleeds (Task 2) and lacunes of presumed vascular origin (Task 3) while leveraging weak and noisy labels. Overall, 12 teams participated in the challenge proposing solutions for one or more tasks (4 for Task 1 - EPVS, 9 for Task 2 - Microbleeds and 6 for Task 3 - Lacunes). Multi-cohort data was used in both training and evaluation. Results showed a large variability in performance both across teams and across tasks, with promising results notably for Task 1 - EPVS and Task 2 - Microbleeds and not practically useful results yet for Task 3 - Lacunes. It also highlighted the performance inconsistency across cases that may deter use at an individual level, while still proving useful at a population level.

cs.CV↗

arXiv2022

Multi-channel end-to-end neural network for speech enhancement, source localization, and voice activity detection

Speech enhancement and source localization has been active research for several decades with a wide range of real-world applications. Recently, the Deep Complex Convolution Recurrent network (DCCRN) has yielded impressive enhancement performance for single-channel systems. In this study, a neural beamformer consisting of a beamformer and a novel multi-channel DCCRN is proposed for speech enhancement and source localization. Complex-valued filters estimated by the multi-channel DCCRN serve as the weights of beamformer. In addition, a one-stage learning-based procedure is employed for speech enhancement and source localization. The proposed network composed of the multi-channel DCCRN and the auxiliary network models the sound field, while minimizing the distortionless response loss function. Simulation results show that the proposed neural beamformer is effective in enhancing speech signals, with speech quality well preserved. The proposed neural beamformer also provides source localization and voice activity detection (VAD) functions.

eess.AS↗

arXiv2022

PO-ELIC: Perception-Oriented Efficient Learned Image Coding

In the past years, learned image compression (LIC) has achieved remarkable performance. The recent LIC methods outperform VVC in both PSNR and MS-SSIM. However, the low bit-rate reconstructions of LIC suffer from artifacts such as blurring, color drifting and texture missing. Moreover, those varied artifacts make image quality metrics correlate badly with human perceptual quality. In this paper, we propose PO-ELIC, i.e., Perception-Oriented Efficient Learned Image Coding. To be specific, we adapt ELIC, one of the state-of-the-art LIC models, with adversarial training techniques. We apply a mixture of losses including hinge-form adversarial loss, Charbonnier loss, and style loss, to finetune the model towards better perceptual quality. Experimental results demonstrate that our method achieves comparable perceptual quality with HiFiC with much lower bitrate.

eess.IV↗

arXiv2022

S3E-GNN: Sparse Spatial Scene Embedding with Graph Neural Networks for Camera Relocalization

Camera relocalization is the key component of simultaneous localization and mapping (SLAM) systems. This paper proposes a learning-based approach, named Sparse Spatial Scene Embedding with Graph Neural Networks (S3E-GNN), as an end-to-end framework for efficient and robust camera relocalization. S3E-GNN consists of two modules. In the encoding module, a trained S3E network encodes RGB images into embedding codes to implicitly represent spatial and semantic embedding code. With embedding codes and the associated poses obtained from a SLAM system, each image is represented as a graph node in a pose graph. In the GNN query module, the pose graph is transformed to form a embedding-aggregated reference graph for camera relocalization. We collect various scene datasets in the challenging environments to perform experiments. Our results demonstrate that S3E-GNN method outperforms the traditional Bag-of-words (BoW) for camera relocalization due to learning-based embedding and GNN powered scene matching mechanism.

cs.CV↗

arXiv2022

Non-reciprocal frequency conversion and mode routing in a microresonator

The transportation of photons and phonons typically obeys the principle of reciprocity. Breaking reciprocity of these bosonic excitations will enable the corresponding non-reciprocal devices, such as isolators and circulators. Here, we use two optical modes and two mechanical modes in a microresonator to form a four-mode plaquette via radiation pressure force. The phase-controlled non-reciprocal routing between any two modes with completely different frequencies is demonstrated, including the routing of phonon to phonon (MHz to MHz), photon to phonon (THz to MHz), and especially photon to photon with frequency difference of around 80 THz for the first time. In addition, one more mechanical mode is introduced to this plaquette to realize a phononic circulator in such single microresonator. The non-reciprocity is derived from interference between multi-mode transfer processes involving optomechanical interactions in an optomechanical resonator. It not only demonstrates the non-reciprocal routing of photons and phonons in a single resonator but also realizes the non-reciprocal frequency conversion for photons and circulation for phonons, laying a foundation for studying directional routing and thermal management in an optomechanical hybrid network.

physics.optics↗

arXiv2021

Coexistence of Type-II and Type-IV Dirac Fermions in SrAgBi

Relativistic massless Weyl and Dirac fermions have isotropic and linear dispersion relations to maintain Poincaré symmetry, which is the most basic symmetry in high-energy physics. The situation in condensed matter physics is less constrained; only certain subgroups of Poincaré symmetry -- the 230 space groups that exist in 3D lattices -- need be respected. Then, the free fermionic excitations that have no high energy analogues could exist in solid state systems. Here, We discovered a type of nonlinear Dirac fermion without high-energy analogue in SrAgBi and named it type-IV Dirac fermion. The type-IV Dirac fermion has a nonlinear dispersion relationship and is similar to the type-II Dirac fermion, which has electron pocket and hole pocket. The effective model for the type-IV Dirac fermion is also found. It is worth pointing out that there is a type-II Dirac fermion near this new Dirac fermion. So we used two models to describe the coexistence of these two Dirac fermions. Topological surface states of these two Dirac points are also calculated. We envision that our findings will stimulate researchers to study novel physics of type-IV Dirac fermions, as well as the interplay of type-II and type-IV Dirac fermions.

cond-mat.mtrl-sci↗