arXiv subjects

Chun Liu

Publications and source records attributed to Chun Liu.

At least 55 records · Page 3Linked to original sources

arXiv2024

Uniqueness to inverse acoustic and elastic medium scattering problems with hyper-singular source method

This paper is concerned with inverse scattering problems of determining the support of an isotropic and homogeneous penetrable body from knowledge of multi-static far-field patterns in acoustics and in linear elasticity. The normal derivative of the total fields admits no jump on the interface of the scatterer in the trace sense. If the contrast function of the refractive index function or the density function has a positive lower bound near the boundary, we propose a hyper-singular source method to prove uniqueness of inverse scattering with all incoming plane waves at a fixed energy. It is based on subtle analysis on the leading part of the scattered field when hyper-singular sources caused by the first derivative of the fundamental solution approach to a boundary point. As a by-product, we show that this hyper-singular method can be also used to determine the boundary value of a Holder continuous refractive index function in acoustics or a Holder continuous density function in linear elasticity.

math.AP↗

arXiv2024

Energetic Variational Gaussian Process Regression for Computer Experiments

The Gaussian process (GP) regression model is a widely employed surrogate modeling technique for computer experiments, offering precise predictions and statistical inference for the computer simulators that generate experimental data. Estimation and inference for GP can be performed in both frequentist and Bayesian frameworks. In this chapter, we construct the GP model through variational inference, particularly employing the recently introduced energetic variational inference method by Wang et al. (2021). Adhering to the GP model assumptions, we derive posterior distributions for its parameters. The energetic variational inference approach bridges the Bayesian sampling and optimization and enables approximation of the posterior distributions and identification of the posterior mode. By incorporating a normal prior on the mean component of the GP model, we also apply shrinkage estimation to the parameters, facilitating mean function variable selection. To showcase the effectiveness of our proposed GP model, we present results from three benchmark examples.

stat.ME↗

arXiv2024

E4C: Enhance Editability for Text-Based Image Editing by Harnessing Efficient CLIP Guidance

Diffusion-based image editing is a composite process of preserving the source image content and generating new content or applying modifications. While current editing approaches have made improvements under text guidance, most of them have only focused on preserving the information of the input image, disregarding the importance of editability and alignment to the target prompt. In this paper, we prioritize the editability by proposing a zero-shot image editing method, named \textbf{E}nhance \textbf{E}ditability for text-based image \textbf{E}diting via \textbf{E}fficient \textbf{C}LIP guidance (\textbf{E4C}), which only requires inference-stage optimization to explicitly enhance the edibility and text alignment. Specifically, we develop a unified dual-branch feature-sharing pipeline that enables the preservation of the structure or texture of the source image while allowing the other to be adapted based on the editing task. We further integrate CLIP guidance into our pipeline by utilizing our novel random-gateway optimization mechanism to efficiently enhance the semantic alignment with the target prompt. Comprehensive quantitative and qualitative experiments demonstrate that our method effectively resolves the text alignment issues prevalent in existing methods while maintaining the fidelity to the source image, and performs well across a wide range of editing tasks.

cs.CV↗

arXiv2024

Increasing stability for inverse acoustic source problems in the time domain

This paper is concerned with inverse source problems for the acoustic wave equation in the full space R^3, where the source term is compactly supported in both time and spatial variables. The main goal is to investigate increasing stability for the wave equation in terms of the interval length of given parameters (e.g., bandwith of the temporal component of the source function). We establish increasing stability estimates of the L^2 -norm of the source function by using only the Dirichlet boundary data. Our method relies on the Huygens principle, the Fourier transform and explicit bounds for the continuation of analytic functions.

math.AP↗

arXiv2024

BotanicGarden: A High-Quality Dataset for Robot Navigation in Unstructured Natural Environments

The rapid developments of mobile robotics and autonomous navigation over the years are largely empowered by public datasets for testing and upgrading, such as sensor odometry and SLAM tasks. Impressive demos and benchmark scores have arisen, which may suggest the maturity of existing navigation techniques. However, these results are primarily based on moderate structured scenario testing. When transitioning to challenging unstructured environments, especially in GNSS-denied, texture-monotonous, and dense-vegetated natural fields, their performance can hardly sustain at a high level and requires further validation and improvement. To bridge this gap, we build a novel robot navigation dataset in a luxuriant botanic garden of more than 48000m2. Comprehensive sensors are used, including Gray and RGB stereo cameras, spinning and MEMS 3D LiDARs, and low-cost and industrial-grade IMUs, all of which are well calibrated and hardware-synchronized. An all-terrain wheeled robot is employed for data collection, traversing through thick woods, riversides, narrow trails, bridges, and grasslands, which are scarce in previous resources. This yields 33 short and long sequences, forming 17.1km trajectories in total. Excitedly, both highly-accurate ego-motions and 3D map ground truth are provided, along with fine-annotated vision semantics. We firmly believe that our dataset can advance robot navigation and sensor fusion research to a higher level.

cs.RO↗

arXiv2024

On a positive-preserving, energy-stable numerical scheme to mass-action kinetics with detailed balance

In this paper, we provide a detailed theoretical analysis of the numerical scheme introduced in J. Comput. Phys. 436 (2021) 110253 for the reaction kinetics of a class of chemical reaction networks that satisfies detailed balance condition. In contrast to conventional numerical approximations, which are typically constructed based on ordinary differential equations (ODEs) for the concentrations of all involved species, the scheme is developed using the equations of reaction trajectories, which can be viewed as a generalized gradient flow of physically relevant free energy. The unique solvability, positivity-preserving, and energy-stable properties are proved for the general case involving multiple reactions, under a mild condition on the stoichiometric matrix.

math.NA↗

arXiv2024

Augmenting Prototype Network with TransMix for Few-shot Hyperspectral Image Classification

Few-shot hyperspectral image classification aims to identify the classes of each pixel in the images by only marking few of these pixels. And in order to obtain the spatial-spectral joint features of each pixel, the fixed-size patches centering around each pixel are often used for classification. However, observing the classification results of existing methods, we found that boundary patches corresponding to the pixels which are located at the boundary of the objects in the hyperspectral images, are hard to classify. These boundary patchs are mixed with multi-class spectral information. Inspired by this, we propose to augment the prototype network with TransMix for few-shot hyperspectrial image classification(APNT). While taking the prototype network as the backbone, it adopts the transformer as feature extractor to learn the pixel-to-pixel relation and pay different attentions to different pixels. At the same time, instead of directly using the patches which are cut from the hyperspectral images for training, it randomly mixs up two patches to imitate the boundary patches and uses the synthetic patches to train the model, with the aim to enlarge the number of hard training samples and enhance their diversity. And by following the data agumentation technique TransMix, the attention returned by the transformer is also used to mix up the labels of two patches to generate better labels for synthetic patches. Compared with existing methods, the proposed method has demonstrated sate of the art performance and better robustness for few-shot hyperspectral image classification in our experiments.

cs.CV↗

arXiv2023

Multi-level Relation Learning for Cross-domain Few-shot Hyperspectral Image Classification

Cross-domain few-shot hyperspectral image classification focuses on learning prior knowledge from a large number of labeled samples from source domains and then transferring the knowledge to the tasks which contain few labeled samples in target domains. Following the metric-based manner, many current methods first extract the features of the query and support samples, and then directly predict the classes of query samples according to their distance to the support samples or prototypes. The relations between samples have not been fully explored and utilized. Different from current works, this paper proposes to learn sample relations on different levels and take them into the model learning process, to improve the cross-domain few-shot hyperspectral image classification. Building on current method of "Deep Cross-Domain Few-Shot Learning for Hyperspectral Image Classification" which adopts a domain discriminator to deal with domain-level distribution difference, the proposed method applies contrastive learning to learn the class-level sample relations to obtain more discriminable sample features. In addition, it adopts a transformer based cross-attention learning module to learn the set-level sample relations and acquire the attention from query samples to support samples. Our experimental results have demonstrated the contribution of the multi-level relation learning mechanism for few-shot hyperspectral image classification when compared with the state of the art methods.

cs.CV↗

arXiv2023

Iterative missing value imputation based on feature importance

Many datasets suffer from missing values due to various reasons,which not only increases the processing difficulty of related tasks but also reduces the accuracy of classification. To address this problem, the mainstream approach is to use missing value imputation to complete the dataset. Existing imputation methods estimate the missing parts based on the observed values in the original feature space, and they treat all features as equally important during data completion, while in fact different features have different importance. Therefore, we have designed an imputation method that considers feature importance. This algorithm iteratively performs matrix completion and feature importance learning, and specifically, matrix completion is based on a filling loss that incorporates feature importance. Our experimental analysis involves three types of datasets: synthetic datasets with different noisy features and missing values, real-world datasets with artificially generated missing values, and real-world datasets originally containing missing values. The results on these datasets consistently show that the proposed method outperforms the existing five imputation algorithms.To the best of our knowledge, this is the first work that considers feature importance in the imputation model.

cs.LG↗

arXiv2023

The Cumulative Distribution Function Based Method for Random Drift Model

In this paper, we propose a numerical method to uniformly handle the random genetic drift model for pure drift with or without natural selection and mutation. For pure drift and natural selection case, the Dirac $δ$ singularity will develop at two boundary ends and the mass lumped at the two ends stands for the fixation probability. For the one-way mutation case, known as Muller's ratchet, the accumulation of deleterious mutations leads to the loss of the fittest gene, the Dirac $δ$ singularity will spike only at one boundary end, which stands for the fixation of the deleterious gene and loss of the fittest one. For two-way mutation case, the singularity with negative power law may emerge near boundary points. We first rewrite the original model on the probability density function (PDF) to one with respect to the cumulative distribution function (CDF). Dirac $δ$ singularity of the PDF becomes the discontinuity of the CDF. Then we establish a upwind scheme, which keeps the total probability, is positivity preserving and unconditionally stable. For pure drift, the scheme also keeps the conservation of expectation. It can catch the discontinuous jump of the CDF, then predicts accurately the fixation probability for pure drift with or without natural selection and one-way mutation. For two-way mutation case, it can catch the power law of the singularity. %Moreover, some artificial algorithms or additional boundary criteria is not needed in the numerical simulation. The numerical results show the effectiveness of the scheme.

math.NA↗

arXiv2023

VisionFM: a Multi-Modal Multi-Task Vision Foundation Model for Generalist Ophthalmic Artificial Intelligence

We present VisionFM, a foundation model pre-trained with 3.4 million ophthalmic images from 560,457 individuals, covering a broad range of ophthalmic diseases, modalities, imaging devices, and demography. After pre-training, VisionFM provides a foundation to foster multiple ophthalmic artificial intelligence (AI) applications, such as disease screening and diagnosis, disease prognosis, subclassification of disease phenotype, and systemic biomarker and disease prediction, with each application enhanced with expert-level intelligence and accuracy. The generalist intelligence of VisionFM outperformed ophthalmologists with basic and intermediate levels in jointly diagnosing 12 common ophthalmic diseases. Evaluated on a new large-scale ophthalmic disease diagnosis benchmark database, as well as a new large-scale segmentation and detection benchmark database, VisionFM outperformed strong baseline deep neural networks. The ophthalmic image representations learned by VisionFM exhibited noteworthy explainability, and demonstrated strong generalizability to new ophthalmic modalities, disease spectrum, and imaging devices. As a foundation model, VisionFM has a large capacity to learn from diverse ophthalmic imaging data and disparate datasets. To be commensurate with this capacity, in addition to the real data used for pre-training, we also generated and leveraged synthetic ophthalmic imaging data. Experimental results revealed that synthetic data that passed visual Turing tests, can also enhance the representation learning capability of VisionFM, leading to substantial performance gains on downstream ophthalmic AI tasks. Beyond the ophthalmic AI applications developed, validated, and demonstrated in this work, substantial further applications can be achieved in an efficient and cost-effective manner using VisionFM as the foundation.

eess.IV↗

arXiv2023

Multi-level Cross-modal Feature Alignment via Contrastive Learning towards Zero-shot Classification of Remote Sensing Image Scenes

Zero-shot classification of image scenes which can recognize the image scenes that are not seen in the training stage holds great promise of lowering the dependence on large numbers of labeled samples. To address the zero-shot image scene classification, the cross-modal feature alignment methods have been proposed in recent years. These methods mainly focus on matching the visual features of each image scene with their corresponding semantic descriptors in the latent space. Less attention has been paid to the contrastive relationships between different image scenes and different semantic descriptors. In light of the challenge of large intra-class difference and inter-class similarity among image scenes and the potential noisy samples, these methods are susceptible to the influence of the instances which are far from these of the same classes and close to these of other classes. In this work, we propose a multi-level cross-modal feature alignment method via contrastive learning for zero-shot classification of remote sensing image scenes. While promoting the single-instance level positive alignment between each image scene with their corresponding semantic descriptors, the proposed method takes the cross-instance contrastive relationships into consideration,and learns to keep the visual and semantic features of different classes in the latent space apart from each other. Extensive experiments have been done to evaluate the performance of the proposed method. The results show that our proposed method outperforms state of the art methods for zero-shot remote sensing image scene classification. All the code and data are available at github https://github.com/masuqiang/MCFA-Pytorch

cs.CV↗

arXiv2023

CoT-MISR:Marrying Convolution and Transformer for Multi-Image Super-Resolution

As a method of image restoration, image super-resolution has been extensively studied at first. How to transform a low-resolution image to restore its high-resolution image information is a problem that researchers have been exploring. In the early physical transformation methods, the high-resolution pictures generated by these methods always have a serious problem of missing information, and the edges and details can not be well recovered. With the development of hardware technology and mathematics, people begin to use in-depth learning methods for image super-resolution tasks, from direct in-depth learning models, residual channel attention networks, bi-directional suppression networks, to tr networks with transformer network modules, which have gradually achieved good results. In the research of multi-graph super-resolution, thanks to the establishment of multi-graph super-resolution dataset, we have experienced the evolution from convolution model to transformer model, and the quality of super-resolution has been continuously improved. However, we find that neither pure convolution nor pure tr network can make good use of low-resolution image information. Based on this, we propose a new end-to-end CoT-MISR network. CoT-MISR network makes up for local and global information by using the advantages of convolution and tr. The validation of dataset under equal parameters shows that our CoT-MISR network has reached the optimal score index.

cs.CV↗

arXiv2023

Faster Learning of Temporal Action Proposal via Sparse Multilevel Boundary Generator

Temporal action localization in videos presents significant challenges in the field of computer vision. While the boundary-sensitive method has been widely adopted, its limitations include incomplete use of intermediate and global information, as well as an inefficient proposal feature generator. To address these challenges, we propose a novel framework, Sparse Multilevel Boundary Generator (SMBG), which enhances the boundary-sensitive method with boundary classification and action completeness regression. SMBG features a multi-level boundary module that enables faster processing by gathering boundary information at different lengths. Additionally, we introduce a sparse extraction confidence head that distinguishes information inside and outside the action, further optimizing the proposal feature generator. To improve the synergy between multiple branches and balance positive and negative samples, we propose a global guidance loss. Our method is evaluated on two popular benchmarks, ActivityNet-1.3 and THUMOS14, and is shown to achieve state-of-the-art performance, with a better inference speed (2.47xBSN++, 2.12xDBG). These results demonstrate that SMBG provides a more efficient and simple solution for generating temporal action proposals. Our proposed framework has the potential to advance the field of computer vision and enhance the accuracy and speed of temporal action localization in video analysis.The code and models are made available at \url{https://github.com/zhouyang-001/SMBG-for-temporal-action-proposal}.

cs.CV↗

arXiv2023

High-order variational Lagrangian schemes for compressible fluids

We present high-order variational Lagrangian finite element methods for compressible fluids using a discrete energetic variational approach. Our spatial discretization is mass/momentum/energy conserving and entropy stable. Fully implicit time stepping is used for the temporal discretization, which allows for a much larger time step size for stability compared to explicit methods, especially for low-Mach number flows and/or on highly distorted meshes. Ample numerical results are presented to showcase the good performance of our proposed scheme.

math.NA↗

arXiv2022

Local well-posedness of a nonlinear Fokker-Planck model

Noise or fluctuations play an important role in the modeling and understanding of the behavior of various complex systems in nature. Fokker-Planck equations are powerful mathematical tool to study behavior of such systems subjected to fluctuations. In this paper we establish local well-posedness result of a new nonlinear Fokker-Planck equation. Such equations appear in the modeling of the grain boundary dynamics during microstructure evolution in the polycrystalline materials and obey special energy laws.

math.AP↗

arXiv2022

UV R-CNN: Stable and Efficient Dense Human Pose Estimation

Dense pose estimation is a dense 3D prediction task for instance-level human analysis, aiming to map human pixels from an RGB image to a 3D surface of the human body. Due to a large amount of surface point regression, the training process appears to be easy to collapse compared to other region-based human instance analyzing tasks. By analyzing the loss formulation of the existing dense pose estimation model, we introduce a novel point regression loss function, named Dense Points} loss to stable the training progress, and a new balanced loss weighting strategy to handle the multi-task losses. With the above novelties, we propose a brand new architecture, named UV R-CNN. Without auxiliary supervision and external knowledge from other tasks, UV R-CNN can handle many complicated issues in dense pose model training progress, achieving 65.0% $AP_{gps}$ and 66.1% $AP_{gpsm}$ on the DensePose-COCO validation subset with ResNet-50-FPN feature extractor, competitive among the state-of-the-art dense human pose estimation methods.

cs.CV↗

arXiv2022

Temperature dependent extensions of the Cahn-Hilliard equation

The Cahn-Hilliard equation is a fundamental model that describes phase separation processes of binary mixtures. In this paper we focus on the dynamics of these binary media, when the underlying temperature is not constant. The aim of this paper is twofold. We first derive two distinct models that extend the classical Cahn-Hilliard equation with an evolutionary equation for the absolute temperature. Secondly, we analyse the local well-posedness of classical solutions for one of these systems. Our modelling introduces the systems of PDEs by means of a general and unified formalism. This formalism couples standard principles of mechanics together with the main laws of thermodynamics. Our work highlights how certain assumptions on the transport of the temperature effect the overall physics of the systems. The variety of these thermodynamically consistent models opens the question of which one should be more appropriate. Our analysis shows that one of the derived models might be more desirable to the well-posedness theory of classical solutions, a property that might be natural as a selection criteria.

math.AP↗