Searcharxiv⌕ Search

arXiv subjects

Jun Liu

Publications and source records attributed to Jun Liu.

At least 505 records · Page 28Linked to original sources
arXiv2023

Ab initio description of bcc iron with correlation matrix renormalization theory

We applied the ab initio spin-polarized Correlation Matrix Renormalization Theory (CMRT) to the ferromagnetic state of the bulk BCC iron. We showed that it was capable of reproducing the equilibrium physical properties and the pressure-volume curve in good comparison with experiments. We then focused on the analysis of its local electronic correlations. By exploiting different local fluctuation-related physical quantities as measures of electronic correlation within target orbits, we elucidated the different roles of $t_{2g}$ and $e_g$ states in both spin channels and presented compelling evidence to showcase this distinction in their electronic correlation.

cond-mat.str-el↗
arXiv2023

High order numerical methods based on quadratic spline collocation method and averaged L1 scheme for the variable-order time fractional mobile/immobile diffusion equation

In this paper, we consider the variable-order time fractional mobile/immobile diffusion (TF-MID) equation in two-dimensional spatial domain, where the fractional order $α(t)$ satisfies $0<α_{*}\leq α(t)\leq α^{*}<1$. We combine the quadratic spline collocation (QSC) method and the $L1^+$ formula to propose a QSC-$L1^+$ scheme. It can be proved that, the QSC-$L1^+$ scheme is unconditionally stable and convergent with $\mathcal{O}(τ^{\min{\{3-α^*-α(0),2\}}} + Δx^{2}+Δy^{2})$, where $τ$, $Δx$ and $Δy$ are the temporal and spatial step sizes, respectively. With some proper assumptions on $α(t)$, the QSC-$L1^+$ scheme has second temporal convergence order even on the uniform mesh, without any restrictions on the solution of the equation. We further construct a novel alternating direction implicit (ADI) framework to develop an ADI-QSC-$L1^+$ scheme, which has the same unconditionally stability and convergence orders. In addition, a fast implementation for the ADI-QSC-$L1^+$ scheme based on the exponential-sum-approximation (ESA) technique is proposed. Moreover, we also introduce the optimal QSC method to improve the spatial convergence to fourth-order. Numerical experiments are attached to support the theoretical analysis, and to demonstrate the effectiveness of the proposed schemes.

math.NA↗
arXiv2023

Revisiting Cephalometric Landmark Detection from the view of Human Pose Estimation with Lightweight Super-Resolution Head

Accurate localization of cephalometric landmarks holds great importance in the fields of orthodontics and orthognathics due to its potential for automating key point labeling. In the context of landmark detection, particularly in cephalometrics, it has been observed that existing methods often lack standardized pipelines and well-designed bias reduction processes, which significantly impact their performance. In this paper, we revisit a related task, human pose estimation (HPE), which shares numerous similarities with cephalometric landmark detection (CLD), and emphasize the potential for transferring techniques from the former field to benefit the latter. Motivated by this insight, we have developed a robust and adaptable benchmark based on the well-established HPE codebase known as MMPose. This benchmark can serve as a dependable baseline for achieving exceptional CLD performance. Furthermore, we introduce an upscaling design within the framework to further enhance performance. This enhancement involves the incorporation of a lightweight and efficient super-resolution module, which generates heatmap predictions on high-resolution features and leads to further performance refinement, benefiting from its ability to reduce quantization bias. In the MICCAI CLDetection2023 challenge, our method achieves 1st place ranking on three metrics and 3rd place on the remaining one. The code for our method is available at https://github.com/5k5000/CLdetection2023.

cs.CV↗
arXiv2023

CloudBrain-NMR: An Intelligent Cloud Computing Platform for NMR Spectroscopy Processing, Reconstruction and Analysis

Nuclear Magnetic Resonance (NMR) spectroscopy has served as a powerful analytical tool for studying molecular structure and dynamics in chemistry and biology. However, the processing of raw data acquired from NMR spectrometers and subsequent quantitative analysis involves various specialized tools, which necessitates comprehensive knowledge in programming and NMR. Particularly, the emerging deep learning tools is hard to be widely used in NMR due to the sophisticated setup of computation. Thus, NMR processing is not an easy task for chemist and biologists. In this work, we present CloudBrain-NMR, an intelligent online cloud computing platform designed for NMR data reading, processing, reconstruction, and quantitative analysis. The platform is conveniently accessed through a web browser, eliminating the need for any program installation on the user side. CloudBrain-NMR uses parallel computing with graphics processing units and central processing units, resulting in significantly shortened computation time. Furthermore, it incorporates state-of-the-art deep learning-based algorithms offering comprehensive functionalities that allow users to complete the entire processing procedure without relying on additional software. This platform has empowered NMR applications with advanced artificial intelligence processing. CloudBrain-NMR is openly accessible for free usage at https://csrc.xmu.edu.cn/CloudBrain.html

q-bio.QM↗
arXiv2023

Self-compression of ultrahigh-peak-power lasers

Pulse self-compression is a simple and economical method for improving the peak power of ultra-intense laser pulses. By solving a modified nonlinear Schrodinger equation considering the fifth-order susceptibility, we found that self-compression appeared even in normally dispersive medium owing to the negative fifth-order susceptibility inducing a mass of negative frequency chirp. Furthermore, negatively pre-chirped pulses allow for self-compression at lower intensity, avoiding medium damage. We numerically analyze the optimal choice of pre-chirp, input intensity, and medium length. A proof-of-principle experiment successfully proves the above theoretical findings. It is expected that petawatt or even exawatt laser pulses with 25 fs/15 fs transform limited pulse duration can be self-compressed to about 9.9 fs/7.6 fs in normally dispersive medium, such as fused silica glass plate.

physics.optics↗
arXiv2023

Deep Learning Overloaded Vehicle Identification for Long Span Bridges Based on Structural Health Monitoring Data

Overloaded vehicles bring great harm to transportation infrastructures. BWIM (bridge weigh-in-motion) method for overloaded vehicle identification is getting more popular because it can be implemented without interruption to the traffic. However, its application is still limited because its effectiveness largely depends on professional knowledge and extra information, and is susceptible to occurrence of multiple vehicles. In this paper, a deep learning based overloaded vehicle identification approach (DOVI) is proposed, with the purpose of overloaded vehicle identification for long-span bridges by the use of structural health monitoring data. The proposed DOVI model uses temporal convolutional architectures to extract the spatial and temporal features of the input sequence data, thus provides an end-to-end overloaded vehicle identification solution which neither needs the influence line nor needs to obtain velocity and wheelbase information in advance and can be applied under the occurrence of multiple vehicles. Model evaluations are conducted on a simply supported beam and a long-span cable-stayed bridge under random traffic flow. Results demonstrate that the proposed deep-learning overloaded vehicle identification approach has better effectiveness and robustness, compared with other machine learning and deep learning approaches.

cs.LG↗
arXiv2023

Radiology-Llama2: Best-in-Class Large Language Model for Radiology

This paper introduces Radiology-Llama2, a large language model specialized for radiology through a process known as instruction tuning. Radiology-Llama2 is based on the Llama2 architecture and further trained on a large dataset of radiology reports to generate coherent and clinically useful impressions from radiological findings. Quantitative evaluations using ROUGE metrics on the MIMIC-CXR and OpenI datasets demonstrate that Radiology-Llama2 achieves state-of-the-art performance compared to other generative language models, with a Rouge-1 score of 0.4834 on MIMIC-CXR and 0.4185 on OpenI. Additional assessments by radiology experts highlight the model's strengths in understandability, coherence, relevance, conciseness, and clinical utility. The work illustrates the potential of localized language models designed and tuned for specialized domains like radiology. When properly evaluated and deployed, such models can transform fields like radiology by automating rote tasks and enhancing human expertise.

cs.CL↗
arXiv2023

Unsupervised Domain Adaptation via Domain-Adaptive Diffusion

Unsupervised Domain Adaptation (UDA) is quite challenging due to the large distribution discrepancy between the source domain and the target domain. Inspired by diffusion models which have strong capability to gradually convert data distributions across a large gap, we consider to explore the diffusion technique to handle the challenging UDA task. However, using diffusion models to convert data distribution across different domains is a non-trivial problem as the standard diffusion models generally perform conversion from the Gaussian distribution instead of from a specific domain distribution. Besides, during the conversion, the semantics of the source-domain data needs to be preserved for classification in the target domain. To tackle these problems, we propose a novel Domain-Adaptive Diffusion (DAD) module accompanied by a Mutual Learning Strategy (MLS), which can gradually convert data distribution from the source domain to the target domain while enabling the classification model to learn along the domain transition process. Consequently, our method successfully eases the challenge of UDA by decomposing the large domain gap into small ones and gradually enhancing the capacity of classification model to finally adapt to the target domain. Our method outperforms the current state-of-the-arts by a large margin on three widely used UDA datasets.

cs.CV↗
arXiv2023

DISGO: Automatic End-to-End Evaluation for Scene Text OCR

This paper discusses the challenges of optical character recognition (OCR) on natural scenes, which is harder than OCR on documents due to the wild content and various image backgrounds. We propose to uniformly use word error rates (WER) as a new measurement for evaluating scene-text OCR, both end-to-end (e2e) performance and individual system component performances. Particularly for the e2e metric, we name it DISGO WER as it considers Deletion, Insertion, Substitution, and Grouping/Ordering errors. Finally we propose to utilize the concept of super blocks to automatically compute BLEU scores for e2e OCR machine translation. The small SCUT public test set is used to demonstrate WER performance by a modularized OCR system.

cs.CV↗
arXiv2023

Diffusion-based Image Translation with Label Guidance for Domain Adaptive Semantic Segmentation

Translating images from a source domain to a target domain for learning target models is one of the most common strategies in domain adaptive semantic segmentation (DASS). However, existing methods still struggle to preserve semantically-consistent local details between the original and translated images. In this work, we present an innovative approach that addresses this challenge by using source-domain labels as explicit guidance during image translation. Concretely, we formulate cross-domain image translation as a denoising diffusion process and utilize a novel Semantic Gradient Guidance (SGG) method to constrain the translation process, conditioning it on the pixel-wise source labels. Additionally, a Progressive Translation Learning (PTL) strategy is devised to enable the SGG method to work reliably across domains with large gaps. Extensive experiments demonstrate the superiority of our approach over state-of-the-art methods.

cs.CV↗
arXiv2023

Localized High-Concentration Electrolytes Get More Localized Through Micelle-Like Structures

Liquid electrolytes in batteries are typically treated as macroscopically homogeneous ionic transport media despite having complex chemical composition and atomistic solvation structures, leaving a knowledge gap of microstructural characteristics. Here, we reveal a unique micelle-like structure in a localized high-concentration electrolyte (LHCE), in which the solvent acts as a surfactant between an insoluble salt in diluent. The miscibility of the solvent with the diluent and simultaneous solubility of the salt results in a micelle-like structure with a smeared interface and an increased salt concentration at the centre of the salt-solvent clusters that extends the salt solubility. These intermingling miscibility effects have temperature dependencies, wherein an exemplified LHCE peaks in localized cluster salt concentration near room temperature and is utilized to form a stable solid-electrolyte interphase (SEI) on Li-metal anode. These findings serve as a guide to predicting a stable ternary phase diagram and connecting the electrolyte microstructure with electrolyte formulation and formation protocols to form stable SEI for enhanced battery cyclability.

cond-mat.mtrl-sci↗
arXiv2023

Learning Gabor Texture Features for Fine-Grained Recognition

Extracting and using class-discriminative features is critical for fine-grained recognition. Existing works have demonstrated the possibility of applying deep CNNs to exploit features that distinguish similar classes. However, CNNs suffer from problems including frequency bias and loss of detailed local information, which restricts the performance of recognizing fine-grained categories. To address the challenge, we propose a novel texture branch as complimentary to the CNN branch for feature extraction. We innovatively utilize Gabor filters as a powerful extractor to exploit texture features, motivated by the capability of Gabor filters in effectively capturing multi-frequency features and detailed local information. We implement several designs to enhance the effectiveness of Gabor filters, including imposing constraints on parameter values and developing a learning method to determine the optimal parameters. Moreover, we introduce a statistical feature extractor to utilize informative statistical information from the signals captured by Gabor filters, and a gate selection mechanism to enable efficient computation by only considering qualified regions as input for texture extraction. Through the integration of features from the Gabor-filter-based texture branch and CNN-based semantic branch, we achieve comprehensive information extraction. We demonstrate the efficacy of our method on multiple datasets, including CUB-200-2011, NA-bird, Stanford Dogs, and GTOS-mobile. State-of-the-art performance is achieved using our approach.

cs.CV↗
arXiv2023

MixPro: Data Augmentation with MaskMix and Progressive Attention Labeling for Vision Transformer

The recently proposed data augmentation TransMix employs attention labels to help visual transformers (ViT) achieve better robustness and performance. However, TransMix is deficient in two aspects: 1) The image cropping method of TransMix may not be suitable for ViTs. 2) At the early stage of training, the model produces unreliable attention maps. TransMix uses unreliable attention maps to compute mixed attention labels that can affect the model. To address the aforementioned issues, we propose MaskMix and Progressive Attention Labeling (PAL) in image and label space, respectively. In detail, from the perspective of image space, we design MaskMix, which mixes two images based on a patch-like grid mask. In particular, the size of each mask patch is adjustable and is a multiple of the image patch size, which ensures each image patch comes from only one image and contains more global contents. From the perspective of label space, we design PAL, which utilizes a progressive factor to dynamically re-weight the attention weights of the mixed attention label. Finally, we combine MaskMix and Progressive Attention Labeling as our new data augmentation method, named MixPro. The experimental results show that our method can improve various ViT-based models at scales on ImageNet classification (73.8\% top-1 accuracy based on DeiT-T for 300 epochs). After being pre-trained with MixPro on ImageNet, the ViT-based models also demonstrate better transferability to semantic segmentation, object detection, and instance segmentation. Furthermore, compared to TransMix, MixPro also shows stronger robustness on several benchmarks. The code is available at https://github.com/fistyee/MixPro.

cs.CV↗
arXiv2023

M$^3$Net: Multi-view Encoding, Matching, and Fusion for Few-shot Fine-grained Action Recognition

Due to the scarcity of manually annotated data required for fine-grained video understanding, few-shot fine-grained (FS-FG) action recognition has gained significant attention, with the aim of classifying novel fine-grained action categories with only a few labeled instances. Despite the progress made in FS coarse-grained action recognition, current approaches encounter two challenges when dealing with the fine-grained action categories: the inability to capture subtle action details and the insufficiency of learning from limited data that exhibit high intra-class variance and inter-class similarity. To address these limitations, we propose M$^3$Net, a matching-based framework for FS-FG action recognition, which incorporates \textit{multi-view encoding}, \textit{multi-view matching}, and \textit{multi-view fusion} to facilitate embedding encoding, similarity matching, and decision making across multiple viewpoints. \textit{Multi-view encoding} captures rich contextual details from the intra-frame, intra-video, and intra-episode perspectives, generating customized higher-order embeddings for fine-grained data. \textit{Multi-view matching} integrates various matching functions enabling flexible relation modeling within limited samples to handle multi-scale spatio-temporal variations by leveraging the instance-specific, category-specific, and task-specific perspectives. \textit{Multi-view fusion} consists of matching-predictions fusion and matching-losses fusion over the above views, where the former promotes mutual complementarity and the latter enhances embedding generalizability by employing multi-task collaborative learning. Explainable visualizations and experimental results on three challenging benchmarks demonstrate the superiority of M$^3$Net in capturing fine-grained action details and achieving state-of-the-art performance for FS-FG action recognition.

cs.CV↗
arXiv2023

XTQA: Span-Level Explanations of the Textbook Question Answering

Textbook Question Answering (TQA) is a task that one should answer a diagram/non-diagram question given a large multi-modal context consisting of abundant essays and diagrams. We argue that the explainability of this task should place students as a key aspect to be considered. To address this issue, we devise a novel architecture towards span-level eXplanations of the TQA (XTQA) based on our proposed coarse-to-fine grained algorithm, which can provide not only the answers but also the span-level evidences to choose them for students. This algorithm first coarsely chooses top $M$ paragraphs relevant to questions using the TF-IDF method, and then chooses top $K$ evidence spans finely from all candidate spans within these paragraphs by computing the information gain of each span to questions. Experimental results shows that XTQA significantly improves the state-of-the-art performance compared with baselines. The source code is available at https://github.com/keep-smile-001/opentqa

cs.CL↗
arXiv2023

A Theoretically Guaranteed Quaternion Weighted Schatten p-norm Minimization Method for Color Image Restoration

Inspired by the fact that the matrix formulated by nonlocal similar patches in a natural image is of low rank, the rank approximation issue have been extensively investigated over the past decades, among which weighted nuclear norm minimization (WNNM) and weighted Schatten $p$-norm minimization (WSNM) are two prevailing methods have shown great superiority in various image restoration (IR) problems. Due to the physical characteristic of color images, color image restoration (CIR) is often a much more difficult task than its grayscale image counterpart. However, when applied to CIR, the traditional WNNM/WSNM method only processes three color channels individually and fails to consider their cross-channel correlations. Very recently, a quaternion-based WNNM approach (QWNNM) has been developed to mitigate this issue, which is capable of representing the color image as a whole in the quaternion domain and preserving the inherent correlation among the three color channels. Despite its empirical success, unfortunately, the convergence behavior of QWNNM has not been strictly studied yet. In this paper, on the one side, we extend the WSNM into quaternion domain and correspondingly propose a novel quaternion-based WSNM model (QWSNM) for tackling the CIR problems. Extensive experiments on two representative CIR tasks, including color image denoising and deblurring, demonstrate that the proposed QWSNM method performs favorably against many state-of-the-art alternatives, in both quantitative and qualitative evaluations. On the other side, more importantly, we preliminarily provide a theoretical convergence analysis, that is, by modifying the quaternion alternating direction method of multipliers (QADMM) through a simple continuation strategy, we theoretically prove that both the solution sequences generated by the QWNNM and QWSNM have fixed-point convergence guarantees.

cs.CV↗
arXiv2023

FR-LIO: Fast and Robust Lidar-Inertial Odometry by Tightly-Coupled Iterated Kalman Smoother and Robocentric Voxels

This paper presents a fast lidar-inertial odometry (LIO) that is robust to aggressive motion. To achieve robust tracking in aggressive motion scenes, we exploit the continuous scanning property of lidar to adaptively divide the full scan into multiple partial scans (named sub-frames) according to the motion intensity. And to avoid the degradation of sub-frames resulting from insufficient constraints, we propose a robust state estimation method based on a tightly-coupled iterated error state Kalman smoother (ESKS) framework. Furthermore, we propose a robocentric voxel map (RC-Vox) to improve the system's efficiency. The RC-Vox allows efficient maintenance of map points and k nearest neighbor (k-NN) queries by mapping local map points into a fixed-size, two-layer 3D array structure. Extensive experiments are conducted on 27 sequences from 4 public datasets and our own dataset. The results show that our system can achieve stable tracking in aggressive motion scenes (angular velocity up to 21.8 rad/s) that cannot be handled by other state-of-the-art methods, while our system can achieve competitive performance with these methods in general scenes. Furthermore, thanks to the RC-Vox, our system is much faster than the most efficient LIO system currently published.

cs.RO↗
arXiv2023

Euler-Bernoulli beams with contact forces: existence, uniqueness, and numerical solutions

In this paper, we investigate the Euler-Bernoulli fourth-order boundary value problem (BVP) $w^{(4)}=f(x,w)$, $x\in \intcc{a,b}$, with specified values of $w$ and $w''$ at the end points, where the behaviour of the right-hand side $f$ is motivated by biomechanical, electromechanical, and structural applications incorporating contact forces. In particular, we consider the case when $f$ is bounded above and monotonically decreasing with respect to its second argument. First, we prove the existence and uniqueness of solutions to the BVP. We then study numerical solutions to the BVP, where we resort to spatial discretization by means of finite difference. Similar to the original continuous-space problem, the discrete problem always possesses a unique solution. In the case of a piecewise linear instance of $f$, the discrete problem is an example of the absolute value equation. We show that solutions to this absolute value equation can be obtained by means of fixed-point iterations, and that solutions to the absolute value equation converge to solutions of the continuous BVP. We also illustrate the performance of the fixed-point iterations through a numerical example.

math.NA↗