arXiv subjects

Bing Li

Publications and source records attributed to Bing Li.

At least 253 records · Page 14Linked to original sources

arXiv2024

NARUTO: Neural Active Reconstruction from Uncertain Target Observations

We present NARUTO, a neural active reconstruction system that combines a hybrid neural representation with uncertainty learning, enabling high-fidelity surface reconstruction. Our approach leverages a multi-resolution hash-grid as the mapping backbone, chosen for its exceptional convergence speed and capacity to capture high-frequency local features.The centerpiece of our work is the incorporation of an uncertainty learning module that dynamically quantifies reconstruction uncertainty while actively reconstructing the environment. By harnessing learned uncertainty, we propose a novel uncertainty aggregation strategy for goal searching and efficient path planning. Our system autonomously explores by targeting uncertain observations and reconstructs environments with remarkable completeness and fidelity. We also demonstrate the utility of this uncertainty-aware approach by enhancing SOTA neural SLAM systems through an active ray sampling strategy. Extensive evaluations of NARUTO in various environments, using an indoor scene simulator, confirm its superior performance and state-of-the-art status in active reconstruction, as evidenced by its impressive results on benchmark datasets like Replica and MP3D.

cs.CV↗

arXiv2024

Finite time/Infinite time blow-up behaviors for the inhomogeneous nonlinear Schrödinger equation

In this work, we consider the following focusing inhomogeneous nonlinear Schrödinger equation \begin{align*} i\partial_t u+Δu +|x|^{-b}|u|^p u=0,\quad (t, x)\in\mathbb{R}\times\mathbb{R}^N \end{align*} with $0 0. \end{equation*} To our knowledge, the statement (1) establishes the first finite time blow-up result for this equation in the intercritical case when the initial data $u_0$ doesn't have finite variance and is non-radial. The statement (2) gives the first result for the infinite time blow-up rate for this equation.

math.AP↗

arXiv2024

Location-guided Head Pose Estimation for Fisheye Image

Camera with a fisheye or ultra-wide lens covers a wide field of view that cannot be modeled by the perspective projection. Serious fisheye lens distortion in the peripheral region of the image leads to degraded performance of the existing head pose estimation models trained on undistorted images. This paper presents a new approach for head pose estimation that uses the knowledge of head location in the image to reduce the negative effect of fisheye distortion. We develop an end-to-end convolutional neural network to estimate the head pose with the multi-task learning of head pose and head location. Our proposed network estimates the head pose directly from the fisheye image without the operation of rectification or calibration. We also created a fisheye-distorted version of the three popular head pose estimation datasets, BIWI, 300W-LP, and AFLW2000 for our experiments. Experiments results show that our network remarkably improves the accuracy of head pose estimation compared with other state-of-the-art one-stage and two-stage methods.

cs.CV↗

arXiv2024

A Copula Graphical Model for Multi-Attribute Data using Optimal Transport

Motivated by modern data forms such as images and multi-view data, the multi-attribute graphical model aims to explore the conditional independence structure among vectors. Under the Gaussian assumption, the conditional independence between vectors is characterized by blockwise zeros in the precision matrix. To relax the restrictive Gaussian assumption, in this paper, we introduce a novel semiparametric multi-attribute graphical model based on a new copula named Cyclically Monotone Copula. This new copula treats the distribution of the node vectors as multivariate marginals and transforms them into Gaussian distributions based on the optimal transport theory. Since the model allows the node vectors to have arbitrary continuous distributions, it is more flexible than the classical Gaussian copula method that performs coordinatewise Gaussianization. We establish the concentration inequalities of the estimated covariance matrices and provide sufficient conditions for selection consistency of the group graphical lasso estimator. For the setting with high-dimensional attributes, a {Projected Cyclically Monotone Copula} model is proposed to address the curse of dimensionality issue that arises from solving high-dimensional optimal transport problems. Numerical results based on synthetic and real data show the efficiency and flexibility of our methods.

stat.ML↗

arXiv2024

Two bifurcation sets of expansive Lorenz maps with a hole at the critical point

Let $f$ be an expansive Lorenz map on $[0,1]$ and $c$ be the critical point. The survivor set we are discussing here is denoted as $S^+_{f}(a,b):=\{x\in[0,1]:f(b)\leq f^{n}(x) \leq f(a)\ \forall n\geq0\}$, where the hole $(a,b)\subseteq [0,1]$ satisfies $a\leq c \leq b$ and $a\neq b$. Let $a\in[0,c]$ be fixed, we mainly focus on the following two bifurcation sets: $$ E_{f}(a):=\{b\in[c,1]:S^{+}_{f}(a,ε)\neq S^{+}_{f}(a,b) \ \forall \ ε>b\}, \ \ {\rm and} $$ $$ B_{f}(a):=\{b\in[c,1]:h_{top}(S^+_{f}(a,ε))\neq h_{top}(S^+_{f}(a,b)) \ \forall \ ε>b\}. $$ By combinatorial renormalization tools, we give a complete characterization of the maximal plateau $P(b)$ such that for all $ε\in P(b)$, $h_{top}(S^+_{f}(a,ε))=h_{top}(S^+_{f}(a,b))$. Moreover, we obtain a sufficient and necessary condition for $E_{f}(a)=B_{f}(a)$, which partially extends the results in \cite{allaart2023} and \cite{baker2020}.

math.DS↗

arXiv2024

A nonparametric test for elliptical distribution based on kernel embedding of probabilities

Elliptical distribution is a basic assumption underlying many multivariate statistical methods. For example, in sufficient dimension reduction and statistical graphical models, this assumption is routinely imposed to simplify the data dependence structure. Before applying such methods, we need to decide whether the data are elliptically distributed. Currently existing tests either focus exclusively on spherical distributions, or rely on bootstrap to determine the null distribution, or require specific forms of the alternative distribution. In this paper, we introduce a general nonparametric test for elliptical distribution based on kernel embedding of the probability measure that embodies the two properties that characterize an elliptical distribution: namely, after centering and rescaling, (1) the direction and length of the random vector are independent, and (2) the directional vector is uniformly distributed on the unit sphere. We derive the asymptotic distributions of the test statistic via von-Mises expansion, develop the sample-level procedure to determine the rejection region, and establish the consistency and validity of the proposed test. We also develop the concentration bounds of the test statistic, allowing the dimension to grow with the sample size, and further establish the consistency in this high-dimension setting. We compare our method with several existing methods via simulation studies, and apply our test to a SENIC dataset with and without a transformation aimed to achieve ellipticity.

math.ST↗

arXiv2024

A Survey on Federated Learning in Intelligent Transportation Systems

The development of Intelligent Transportation System (ITS) has brought about comprehensive urban traffic information that not only provides convenience to urban residents in their daily lives but also enhances the efficiency of urban road usage, leading to a more harmonious and sustainable urban life. Typical scenarios in ITS mainly include traffic flow prediction, traffic target recognition, and vehicular edge computing. However, most current ITS applications rely on a centralized training approach where users upload source data to a cloud server with high computing power for management and centralized training. This approach has limitations such as poor real-time performance, data silos, and difficulty in guaranteeing data privacy. To address these limitations, federated learning (FL) has been proposed as a promising solution. In this paper, we present a comprehensive review of the application of FL in ITS, with a particular focus on three key scenarios: traffic flow prediction, traffic target recognition, and vehicular edge computing. For each scenario, we provide an in-depth analysis of its key characteristics, current challenges, and specific manners in which FL is leveraged. Moreover, we discuss the benefits that FL can offer as a potential solution to the limitations of the centralized training approach currently used in ITS applications.

cs.NI↗

arXiv2024

Uniform Diophantine approximation with restricted denominators

Let $b\geq2$ be an integer and $A=(a_{n})_{n=1}^{\infty}$ be a strictly increasing subsequence of positive integers with $η:=\limsup\limits_{n\to\infty}\frac{a_{n+1}}{a_{n}}<+\infty$. For each irrational real number $ξ$, we denote by $\hat{v}_{b,A}(ξ)$ the supremum of the real numbers $\hat{v}$ for which, for every sufficiently large integer $N$, the equation $\|b^{a_n}ξ\|<(b^{a_N})^{-\hat{v}}$ has a solution $n$ with $1\leq n\leq N$. For every $\hat{v}\in[0,η]$, let $\hat{\mathcal{V}}_{b,A}(\hat{v})$ ($\hat{\mathcal{V}}_{b,A}^{\ast}(\hat{v})$) be the set of all real numbers $ξ$ such that $\hat{v}_{b,A}(ξ)\geq\hat{v}$ ($\hat{v}_{b,A}(ξ)=\hat{v}$) respectively. In this paper, we give some results of the Hausdorfff dimensions of $\hat{\mathcal{V}}_{b,A}(\hat{v})$ and $\hat{\mathcal{V}}_{b,A}^{\ast}(\hat{v})$. When $η=1$, we prove that the Hausdorfff dimensions of $\hat{\mathcal{V}}_{b,A}(\hat{v})$ and $\hat{\mathcal{V}}_{b,A}^{\ast}(\hat{v})$ are equal to $\left(\frac{1-\hat{v}}{1+\hat{v}}\right)^{2}$ for any $\hat{v}\in[0,1]$. When $η>1$ and $\lim_{n\to\infty}\frac{a_{n+1}}{a_{n}}$ exists, we show that the Hausdorfff dimension of $\hat{\mathcal{V}}_{b,A}(\hat{v})$ is strictly less than $\left(\frac{η-\hat{v}}{η+\hat{v}}\right)^{2}$ for some $\hat{v}$, which is different with the case $η=1$, and we give a lower bound of the Hausdorfff dimensions of $\hat{\mathcal{V}}_{b,A}(\hat{v})$ and $\hat{\mathcal{V}}_{b,A}^{\ast}(\hat{v})$ for any $\hat{v}\in[0,η]$. Furthermore, we show that this lower bound can be reached for some $\hat{v}$.

math.NT↗

arXiv2024

Application of Deep Learning Methods for Distinguishing Gamma-Ray Bursts from Fermi/GBM TTE Data

To investigate GRBs in depth, it is crucial to develop an effective method for identifying GRBs accurately. Current criteria, e.g., onboard blind search, ground blind search, and target search, are limited by manually set thresholds and perhaps miss GRBs, especially for sub-threshold events. We propose a novel approach that utilizes convolutional neural networks (CNNs) to distinguish GRBs and non-GRBs directly. We structured three CNN models, plain-CNN, ResNet, and ResNet-CBAM, and endeavored to exercise fusing strategy models. Count maps of NaI detectors onboard Fermi/GBM were employed as the input samples of datasets and models were implemented to evaluate their performance on different time scale data. The ResNet-CBAM model trained on 64 ms dataset achieves high accuracy overall, which includes residual and attention mechanism modules. The visualization methods of Grad-CAM and t-SNE explicitly displayed that the optimal model focuses on the key features of GRBs precisely. The model was applied to analyze one-year data, accurately identifying approximately 98% of GRBs listed in the Fermi burst catalog, 8 out of 9 sub-threshold GRBs, and 5 GRBs triggered by other satellites, which demonstrated the deep learning methods could effectively distinguish GRBs from observational data. Besides, thousands of unknown candidates were retrieved and compared with the bursts of SGR J1935+2154 for instance, which exemplified the potential scientific value of these candidates indeed. Detailed studies on integrating our model into real-time analysis pipelines thus may improve their accuracy of inspection, and provide valuable guidance for rapid follow-up observations of multi-band telescopes.

astro-ph.HE↗

arXiv2024

Benchmarking Segmentation Models with Mask-Preserved Attribute Editing

When deploying segmentation models in practice, it is critical to evaluate their behaviors in varied and complex scenes. Different from the previous evaluation paradigms only in consideration of global attribute variations (e.g. adverse weather), we investigate both local and global attribute variations for robustness evaluation. To achieve this, we construct a mask-preserved attribute editing pipeline to edit visual attributes of real images with precise control of structural information. Therefore, the original segmentation labels can be reused for the edited images. Using our pipeline, we construct a benchmark covering both object and image attributes (e.g. color, material, pattern, style). We evaluate a broad variety of semantic segmentation models, spanning from conventional close-set models to recent open-vocabulary large models on their robustness to different types of variations. We find that both local and global attribute variations affect segmentation performances, and the sensitivity of models diverges across different variation types. We argue that local attributes have the same importance as global attributes, and should be considered in the robustness evaluation of segmentation models. Code: https://github.com/PRIS-CV/Pascal-EA.

cs.CV↗

arXiv2024

PromptIQA: Boosting the Performance and Generalization for No-Reference Image Quality Assessment via Prompts

Due to the diversity of assessment requirements in various application scenarios for the IQA task, existing IQA methods struggle to directly adapt to these varied requirements after training. Thus, when facing new requirements, a typical approach is fine-tuning these models on datasets specifically created for those requirements. However, it is time-consuming to establish IQA datasets. In this work, we propose a Prompt-based IQA (PromptIQA) that can directly adapt to new requirements without fine-tuning after training. On one hand, it utilizes a short sequence of Image-Score Pairs (ISP) as prompts for targeted predictions, which significantly reduces the dependency on the data requirements. On the other hand, PromptIQA is trained on a mixed dataset with two proposed data augmentation strategies to learn diverse requirements, thus enabling it to effectively adapt to new requirements. Experiments indicate that the PromptIQA outperforms SOTA methods with higher performance and better generalization. The code will be available.

cs.CV↗

arXiv2024

Semantics-enhanced Cross-modal Masked Image Modeling for Vision-Language Pre-training

In vision-language pre-training (VLP), masked image modeling (MIM) has recently been introduced for fine-grained cross-modal alignment. However, in most existing methods, the reconstruction targets for MIM lack high-level semantics, and text is not sufficiently involved in masked modeling. These two drawbacks limit the effect of MIM in facilitating cross-modal semantic alignment. In this work, we propose a semantics-enhanced cross-modal MIM framework (SemMIM) for vision-language representation learning. Specifically, to provide more semantically meaningful supervision for MIM, we propose a local semantics enhancing approach, which harvest high-level semantics from global image features via self-supervised agreement learning and transfer them to local patch encodings by sharing the encoding space. Moreover, to achieve deep involvement of text during the entire MIM process, we propose a text-guided masking strategy and devise an efficient way of injecting textual information in both masked modeling and reconstruction target acquisition. Experimental results validate that our method improves the effectiveness of the MIM task in facilitating cross-modal semantic alignment. Compared to previous VLP models with similar model size and data scale, our SemMIM model achieves state-of-the-art or competitive performance on multiple downstream vision-language tasks.

cs.CV↗

arXiv2024

Unifying Latent and Lexicon Representations for Effective Video-Text Retrieval

In video-text retrieval, most existing methods adopt the dual-encoder architecture for fast retrieval, which employs two individual encoders to extract global latent representations for videos and texts. However, they face challenges in capturing fine-grained semantic concepts. In this work, we propose the UNIFY framework, which learns lexicon representations to capture fine-grained semantics and combines the strengths of latent and lexicon representations for video-text retrieval. Specifically, we map videos and texts into a pre-defined lexicon space, where each dimension corresponds to a semantic concept. A two-stage semantics grounding approach is proposed to activate semantically relevant dimensions and suppress irrelevant dimensions. The learned lexicon representations can thus reflect fine-grained semantics of videos and texts. Furthermore, to leverage the complementarity between latent and lexicon representations, we propose a unified learning scheme to facilitate mutual learning via structure sharing and self-distillation. Experimental results show our UNIFY framework largely outperforms previous video-text retrieval methods, with 4.8% and 8.2% Recall@1 improvement on MSR-VTT and DiDeMo respectively.

cs.CV↗

arXiv2024

Repeating fast radio bursts produced by a strange star interacting with its planet in an eccentric orbit

FRB 180916 is an important repeating fast radio burst (FRB) source. Interestingly, the activity of FRB 180916 shows a well-regulated behavior, with a period of 16.35 days. The bursts are found to occur in a duty circle of about 5 days in each period. In this study, we suggest that the bursts of FRB 180916 are produced by a strange star interacting with its planet. The planet moves in a highly eccentric orbit around its compact host, with the periastron only slightly beyond the tidal disruption radius. As a result, the planet will be partially disrupted every time it passes through the periastron. The stripped material from the planet will be accreted by the strange star, falling to the polar cap region along the magnetic field lines and accumulated there. It will finally lead to a local collapse when the crust at the polar region is overloaded, triggering an FRB. The observed 16.35 day period corresponds to the orbital motion of the planet, and the 5 day duty circle is explained as the duration of the partial disruption near the periastron. The energy released in each local collapse event can be as high as $\sim 10^{42}~\rm {erg}$, which is large enough to account for typical FRBs even if the radiation efficiency is extremely low.

astro-ph.HE↗

arXiv2024

Early-Exit with Class Exclusion for Efficient Inference of Neural Networks

Deep neural networks (DNNs) have been successfully applied in various fields. In DNNs, a large number of multiply-accumulate (MAC) operations are required to be performed, posing critical challenges in applying them in resource-constrained platforms, e.g., edge devices. To address this challenge, in this paper, we propose a class-based early-exit for dynamic inference. Instead of pushing DNNs to make a dynamic decision at intermediate layers, we take advantage of the learned features in these layers to exclude as many irrelevant classes as possible, so that later layers only have to determine the target class among the remaining classes. When only one class remains at a layer, this class is the corresponding classification result. Experimental results demonstrate the computational cost of DNNs in inference can be reduced significantly with the proposed early-exit technique. The codes can be found at https://github.com/HWAI-TUDa/EarlyClassExclusion.

cs.LG↗

arXiv2024

Learned Image Compression with Gaussian-Laplacian-Logistic Mixture Model and Concatenated Residual Modules

Recently deep learning-based image compression methods have achieved significant achievements and gradually outperformed traditional approaches including the latest standard Versatile Video Coding (VVC) in both PSNR and MS-SSIM metrics. Two key components of learned image compression are the entropy model of the latent representations and the encoding/decoding network architectures. Various models have been proposed, such as autoregressive, softmax, logistic mixture, Gaussian mixture, and Laplacian. Existing schemes only use one of these models. However, due to the vast diversity of images, it is not optimal to use one model for all images, even different regions within one image. In this paper, we propose a more flexible discretized Gaussian-Laplacian-Logistic mixture model (GLLMM) for the latent representations, which can adapt to different contents in different images and different regions of one image more accurately and efficiently, given the same complexity. Besides, in the encoding/decoding network design part, we propose a concatenated residual blocks (CRB), where multiple residual blocks are serially connected with additional shortcut connections. The CRB can improve the learning ability of the network, which can further improve the compression performance. Experimental results using the Kodak, Tecnick-100 and Tecnick-40 datasets show that the proposed scheme outperforms all the leading learning-based methods and existing compression standards including VVC intra coding (4:4:4 and 4:2:0) in terms of the PSNR and MS-SSIM. The source code is available at \url{https://github.com/fengyurenpingsheng}

eess.IV↗

arXiv2024

Hausdorff dimension of recurrence sets for matrix transformations of tori

Let $T\colon\mathbb{T}^d\to \mathbb{T}^d$, defined by $T x=Ax(\bmod 1)$, where $A$ is a $d\times d$ integer matrix with eigenvalues $1<|λ_1|\le|λ_2|\le\dots\le|λ_d|$. We investigate the Hausdorff dimension of the recurrence set \[R(ψ):=\{x\in\mathbb{T}^d\colon T^nx\in B(x,ψ(n)) {\rm ~for~infinitely~ many~}n\}\] for $α\ge\log|λ_d/λ_1|$, where $ψ$ is a positive decreasing function defined on $\mathbb{N}$ and its lower order at infinity is $α=\liminf\limits_{n\to\infty}\frac{-\log ψ(n)}{n}$. In the case that $A$ is diagonalizable over $\mathbb{Q}$ with integral eigenvalues, we obtain the dimension formula.

math.DS↗

arXiv2024

STAR: An Efficient Softmax Engine for Attention Model with RRAM Crossbar

RRAM crossbars have been studied to construct in-memory accelerators for neural network applications due to their in-situ computing capability. However, prior RRAM-based accelerators show efficiency degradation when executing the popular attention models. We observed that the frequent softmax operations arise as the efficiency bottleneck and also are insensitive to computing precision. Thus, we propose STAR, which boosts the computing efficiency with an efficient RRAM-based softmax engine and a fine-grained global pipeline for the attention models. Specifically, STAR exploits the versatility and flexibility of RRAM crossbars to trade off the model accuracy and hardware efficiency. The experimental results evaluated on several datasets show STAR achieves up to 30.63x and 1.31x computing efficiency improvements over the GPU and the state-of-the-art RRAM-based attention accelerators, respectively.

cs.AR↗