SearcharxivSearch

arXiv subjects

Zewei Xu

Publications and source records attributed to Zewei Xu.

10 recordsLinked to original sources

Optimal dimension-dependent $\ell^p$ and $\ell^{1,\infty}$ estimates of the second-order discrete Riesz transforms

In this paper we investigate the optimal dimension-dependent estimates of the second-order discrete Riesz transforms \[ R_{\mathrm{dis}}^{(jk)}f(n) = c_d\sum_{m\in\mathbb Z^d\setminus\{0\}} \frac{m_jm_k}{|m|^{d+2}}f(n-m), \qquad c_d=\frac{\Gamma\left(\frac{d+2}{2}\right)}{\pi^{d/2}}. \] For $j\neq k$ and every fixed $1<p<\infty$, we prove that \[ \|R_{\mathrm{dis}}^{(jk)}\|_{\ell^p\to\ell^p} = c_d\left[ \frac{2}{2^{d/2}} + \left(\frac83+o(1)\right)\frac{d}{3^{d/2}} \right] \] and \[ \frac{2c_d}{2^{d/2}} \leq \|R_{\mathrm{dis}}^{(jk)}\|_{\ell^1\to\ell^{1,\infty}} \leq c_d\left[ \frac{2}{2^{d/2}} + \left(\frac83+o(1)\right)\frac{d}{3^{d/2}} \right]. \] Since $ c_d\sim \sqrt{\pi d}\left(\frac{d}{2\pi e}\right)^{d/2} $ by Stirling's formula, thl $\ell^p$ estimates give a negative answer to the conjecture proposed by Ba\~nuelos and Kim in \cite{BK2}. The diagonal case exhibits quite a different phenomenon: for every $j$ and every $1<p<\infty$, $R_{\mathrm{dis}}^{(jj)}$ is neither bounded from $\ell^p(\mathbb Z^d)$ to $\ell^p(\mathbb Z^d)$ nor of weak type $(1,1)$. Cancellation is restored for the operators $R_{\mathrm{dis}}^{(jj-kk)} =R_{\mathrm{dis}}^{(jj)}-R_{\mathrm{dis}}^{(kk)}$. For every fixed $1<p<\infty$, \[ \|R_{\mathrm{dis}}^{(jj-kk)}\|_{\ell^p\to\ell^p} = 4c_d\left[ 1+(1+o(1))\frac{d}{2^{d/2}} \right], \] and \[ 4c_d \leq \|R_{\mathrm{dis}}^{(jj-kk)}\|_{\ell^1\to\ell^{1,\infty}} \leq 4c_d\left[ 1+(1+o(1))\frac{d}{2^{d/2}} \right]. \]

math.CA

Optimal dimension-dependent $\ell^p$ and $\ell^{1,\infty}$ estimates of the discrete Riesz Transforms

In this paper, we are concerned with the optimal dimension-dependent $\ell^p$ norm of the discrete Riesz Transforms $R_{\text{dis}}^{(k)}$ on $\mathbb{Z}^d$ given by the singular convolution kernel $K_k(m)=c_d m_k/|m|^{d+1}$, where $c_d=\Gamma(\frac{d+1}{2})/\pi^{(d+1)/2}$ . We show that for fixed $1<p<\infty$, when $d\to \infty$ $$\|R_{dis}^{\left( k \right)}\|_{\ell ^p\left( \mathbb{Z}^d \right) \rightarrow \ell ^p\left( \mathbb{Z}^d \right)}=2c_d\left( 1+\frac{\left( \sqrt{2}+o\left( 1 \right) \right) d}{2^{\frac{d}{2}}} \right) .$$ The operator norm of $R_{\text{dis}}^{(k)}$ grows super-exponentially as $d\to\infty$ since $c_d\sim(\frac{d-1}{2e\pi})^{\frac{d-1}{2}}\sqrt{\frac{d-1}{\pi}}$ by Stirling's formula, which gives a negative answer to the conjecture proposed by Ba\~{n}uelos, Kim and Kwa\'{s}nicki in \cite{BKK}. The optimal dimension-dependent $\ell^{1,\infty}$ estimate of $R_{\text{dis}}^{(k)}$ is also established.

math.CA

Nanometer-scale pre-bunched electron beams generated from all-optical plasma-based acceleration

High-quality and prebunched electron beams can produce coherent x-rays with high intensity and narrow bandwidth, which is essential for modern light sources. An all-optical scheme based on plasma-based acceleration to produce bright electron beams that are pre-bunched on nanometer-scales is proposed. By using a density modulation created by two low intensity counter-propagating lasers, the phase velocity of the plasma wake excited by an intense driver laser in a uniform plasma can be modulated at a frequency twice that of the colliding lasers and thus turn the injection on and off. The injected electrons are micro-bunched at the Doppler shifted wavelength of the modulated wavelength using the corresponding phase velocity of the gradual expansion of the wakefield. It is demonstrated that by controlling the properties of the drive and colliding lasers, that beams with exotic pre-bunched structures can be produced, which may have critical applications in ultrafast high power x-rays. This extremely compact, all-optical scheme to produce ultra-bright pre-bunched electron beams may therefore enable novel applications for ultrafast x-ray users and arouse general interest in various fields.

physics.acc-ph

Towards A Comprehensive Visual Saliency Explanation Framework for AI-based Face Recognition Systems

Over recent years, deep convolutional neural networks have significantly advanced the field of face recognition techniques for both verification and identification purposes. Despite the impressive accuracy, these neural networks are often criticized for lacking explainability. There is a growing demand for understanding the decision-making process of AI-based face recognition systems. Some studies have investigated the use of visual saliency maps as explanations, but they have predominantly focused on the specific face verification case. The discussion on more general face recognition scenarios and the corresponding evaluation methodology for these explanations have long been absent in current research. Therefore, this manuscript conceives a comprehensive explanation framework for face recognition tasks. Firstly, an exhaustive definition of visual saliency map-based explanations for AI-based face recognition systems is provided, taking into account the two most common recognition situations individually, i.e., face verification and identification. Secondly, a new model-agnostic explanation method named CorrRISE is proposed to produce saliency maps, which reveal both the similar and dissimilar regions between any given face images. Subsequently, the explanation framework conceives a new evaluation methodology that offers quantitative measurement and comparison of the performance of general visual saliency explanation methods in face recognition. Consequently, extensive experiments are carried out on multiple verification and identification scenarios. The results showcase that CorrRISE generates insightful saliency maps and demonstrates superior performance, particularly in similarity maps in comparison with the state-of-the-art explanation approaches.

cs.CV

Explainable Face Verification via Feature-Guided Gradient Backpropagation

Recent years have witnessed significant advancement in face recognition (FR) techniques, with their applications widely spread in people's lives and security-sensitive areas. There is a growing need for reliable interpretations of decisions of such systems. Existing studies relying on various mechanisms have investigated the usage of saliency maps as an explanation approach, but suffer from different limitations. This paper first explores the spatial relationship between face image and its deep representation via gradient backpropagation. Then a new explanation approach FGGB has been conceived, which provides precise and insightful similarity and dissimilarity saliency maps to explain the "Accept" and "Reject" decision of an FR system. Extensive visual presentation and quantitative measurement have shown that FGGB achieves superior performance in both similarity and dissimilarity maps when compared to current state-of-the-art explainable face verification approaches.

cs.CV

Discriminative Deep Feature Visualization for Explainable Face Recognition

Despite the huge success of deep convolutional neural networks in face recognition (FR) tasks, current methods lack explainability for their predictions because of their "black-box" nature. In recent years, studies have been carried out to give an interpretation of the decision of a deep FR system. However, the affinity between the input facial image and the extracted deep features has not been explored. This paper contributes to the problem of explainable face recognition by first conceiving a face reconstruction-based explanation module, which reveals the correspondence between the deep feature and the facial regions. To further interpret the decision of an FR model, a novel visual saliency explanation algorithm has been proposed. It provides insightful explanation by producing visual saliency maps that represent similar and dissimilar regions between input faces. A detailed analysis has been presented for the generated visual explanation to show the effectiveness of the proposed method.

cs.CV

Towards Visual Saliency Explanations of Face Verification

In the past years, deep convolutional neural networks have been pushing the frontier of face recognition (FR) techniques in both verification and identification scenarios. Despite the high accuracy, they are often criticized for lacking explainability. There has been an increasing demand for understanding the decision-making process of deep face recognition systems. Recent studies have investigated the usage of visual saliency maps as an explanation, but they often lack a discussion and analysis in the context of face recognition. This paper concentrates on explainable face verification tasks and conceives a new explanation framework. Firstly, a definition of the saliency-based explanation method is provided, which focuses on the decisions made by the deep FR model. Secondly, a new model-agnostic explanation method named CorrRISE is proposed to produce saliency maps, which reveal both the similar and dissimilar regions of any given pair of face images. Then, an evaluation methodology is designed to measure the performance of general visual saliency explanation methods in face verification. Finally, substantial visual and quantitative results have shown that the proposed CorrRISE method demonstrates promising results in comparison with other state-of-the-art explainable face verification approaches.

cs.CV

Wise-IoU: Bounding Box Regression Loss with Dynamic Focusing Mechanism

The loss function for bounding box regression (BBR) is essential to object detection. Its good definition will bring significant performance improvement to the model. Most existing works assume that the examples in the training data are high-quality and focus on strengthening the fitting ability of BBR loss. If we blindly strengthen BBR on low-quality examples, it will jeopardize localization performance. Focal-EIoU v1 was proposed to solve this problem, but due to its static focusing mechanism (FM), the potential of non-monotonic FM was not fully exploited. Based on this idea, we propose an IoU-based loss with a dynamic non-monotonic FM named Wise-IoU (WIoU). The dynamic non-monotonic FM uses the outlier degree instead of IoU to evaluate the quality of anchor boxes and provides a wise gradient gain allocation strategy. This strategy reduces the competitiveness of high-quality anchor boxes while also reducing the harmful gradient generated by low-quality examples. This allows WIoU to focus on ordinary-quality anchor boxes and improve the detector's overall performance. When WIoU is applied to the state-of-the-art real-time detector YOLOv7, the AP-75 on the MS-COCO dataset is improved from 53.03% to 54.50%. Code is available at https://github.com/Instinct323/wiou.

cs.CV

Explainable Sentence-Level Sentiment Analysis for Amazon Product Reviews

In this paper, we conduct a sentence level sentiment analysis on the product reviews from Amazon and thorough analysis on the model interpretability. For the sentiment analysis task, we use the BiLSTM model with attention mechanism. For the study of interpretability, we consider the attention weights distribution of single sentence and the attention weights of main aspect terms. The model has an accuracy of up to 0.96. And we find that the aspect terms have the same or even more attention weights than the sentimental words in sentences.

cs.CL

DAPnet: A Double Self-attention Convolutional Network for Point Cloud Semantic Labeling

Airborne Laser Scanning (ALS) point clouds have complex structures, and their 3D semantic labeling has been a challenging task. It has three problems: (1) the difficulty of classifying point clouds around boundaries of objects from different classes, (2) the diversity of shapes within the same class, and (3) the scale differences between classes. In this study, we propose a novel double self-attention convolutional network called the DAPnet. The double self-attention includes the point attention module (PAM) and the group attention module (GAM). For problem (1), the PAM can effectively assign different weights based on the relevance of point clouds in adjacent areas. Meanwhile, for the problem (2), the GAM enhances the correlation between groups, i.e., grouped features within the same classes. To solve the problem (3), we adopt a multiscale radius to construct the groups and concatenate extracted hierarchical features with the output of the corresponding upsampling process. Under the ISPRS 3D Semantic Labeling Contest dataset, the DAPnet outperforms the benchmark by 85.2\% with an overall accuracy of 90.7\%. By conducting ablation comparisons, we find that the PAM effectively improves the model than the GAM. The incorporation of the double self-attention module has an average of 7\% improvement on the pre-class accuracy. Plus, the DAPnet consumes a similar training time to those without the attention modules for model convergence. The DAPnet can assign different weights to features based on the relevance between point clouds and their neighbors, which effectively improves classification performance. The source codes are available at: https://github.com/RayleighChen/point-attention.

cs.CV