Searcharxiv⌕ Search

arXiv subjects

Hui Xiao

Publications and source records attributed to Hui Xiao.

At least 37 records · Page 2Linked to original sources
arXiv2024

Prior-based Objective Inference Mining Potential Uncertainty for Facial Expression Recognition

Annotation ambiguity caused by the inherent subjectivity of visual judgment has always been a major challenge for Facial Expression Recognition (FER) tasks, particularly for largescale datasets from in-the-wild scenarios. A potential solution is the evaluation of relatively objective emotional distributions to help mitigate the ambiguity of subjective annotations. To this end, this paper proposes a novel Prior-based Objective Inference (POI) network. This network employs prior knowledge to derive a more objective and varied emotional distribution and tackles the issue of subjective annotation ambiguity through dynamic knowledge transfer. POI comprises two key networks: Firstly, the Prior Inference Network (PIN) utilizes the prior knowledge of AUs and emotions to capture intricate motion details. To reduce over-reliance on priors and facilitate objective emotional inference, PIN aggregates inferential knowledge from various key facial subregions, encouraging mutual learning. Secondly, the Target Recognition Network (TRN) integrates subjective emotion annotations and objective inference soft labels provided by the PIN, fostering an understanding of inherent facial expression diversity, thus resolving annotation ambiguity. Moreover, we introduce an uncertainty estimation module to quantify and balance facial expression confidence. This module enables a flexible approach to dealing with the uncertainties of subjective annotations. Extensive experiments show that POI exhibits competitive performance on both synthetic noisy datasets and multiple real-world datasets. All codes and training logs will be publicly available at https://github.com/liuhw01/POI.

cs.CV↗
arXiv2024

A simple model of decision-making in the application process

In decision-making, individuals often rely on intuition, which can occasionally yield suboptimal outcomes. This study examines the impact of intuitive decision-making on individuals who are confronted with limited position information in the job application process. We propose a measure, the mismatch index, that gauges allocation efficiency by comparing the final application rate to the preset admission rate. By simulation and analytical results, we counter-intuitively find that under the intuitive strategy, acquiring more information does not always lead to more efficient allocation. Additionally, a shift from despondency to a bandwagon effect occurs when the initial application rate surpasses the admission rate, which can be observed in our field experiments. Meanwhile, experimental data also unveil variations in individuals' reliance on intuition, indicating the presence of inherent adventurous and conservative inclinations. To account for these effects, we introduce an enhancement factor into our model. The improved results align well with these real data, showing that compared to mediate competitive scenarios, individuals exhibit a stronger conservative tendency in fierce or less competitive scenarios. These findings offer significant insights into resource allocation, especially in the competitive job market context.

physics.soc-ph↗
arXiv2024

Multi-Level Label Correction by Distilling Proximate Patterns for Semi-supervised Semantic Segmentation

Semi-supervised semantic segmentation relieves the reliance on large-scale labeled data by leveraging unlabeled data. Recent semi-supervised semantic segmentation approaches mainly resort to pseudo-labeling methods to exploit unlabeled data. However, unreliable pseudo-labeling can undermine the semi-supervision processes. In this paper, we propose an algorithm called Multi-Level Label Correction (MLLC), which aims to use graph neural networks to capture structural relationships in Semantic-Level Graphs (SLGs) and Class-Level Graphs (CLGs) to rectify erroneous pseudo-labels. Specifically, SLGs represent semantic affinities between pairs of pixel features, and CLGs describe classification consistencies between pairs of pixel labels. With the support of proximate pattern information from graphs, MLLC can rectify incorrectly predicted pseudo-labels and can facilitate discriminative feature representations. We design an end-to-end network to train and perform this effective label corrections mechanism. Experiments demonstrate that MLLC can significantly improve supervised baselines and outperforms state-of-the-art approaches in different scenarios on Cityscapes and PASCAL VOC 2012 datasets. Specifically, MLLC improves the supervised baseline by at least 5% and 2% with DeepLabV2 and DeepLabV3+ respectively under different partition protocols.

cs.CV↗
arXiv2024

Beyond expected values: Making environmental decisions using value of information analysis when measurement outcome matters

In ecological and environmental contexts, management actions must sometimes be chosen urgently. Value of information (VoI) analysis provides a quantitative toolkit for projecting the improved management outcomes expected after making additional measurements. However, traditional VoI analysis reports metrics as expected values (i.e. risk-neutral). This can be problematic because expected values hide uncertainties in projections. The true value of a measurement will only be known after the measurement's outcome is known, leaving large uncertainty in the measurement's value before it is performed. As a result, the expected value metrics produced in traditional VoI analysis may not align with the priorities of a risk-averse decision-maker who wants to avoid low-value measurement outcomes. In the present work, we introduce four new VoI metrics that can address a decision-maker's risk-aversion to different measurement outcomes. We demonstrate the benefits of the new metrics with two ecological case studies for which traditional VoI analysis has been previously applied. Using the new metrics, we also demonstrate a clear mathematical link between the often-separated environmental decision-making disciplines of VoI and optimal design of experiments. This mathematical link has the potential to catalyse future collaborations between ecologists and statisticians to work together to quantitatively address environmental decision-making questions of fundamental importance. Overall, the introduced VoI metrics complement existing metrics to provide decision-makers with a comprehensive view of the value of, and risks associated with, a proposed monitoring or measurement activity. This is critical for improved environmental outcomes when decisions must be urgently made.

stat.AP↗
arXiv2023

JFinder: A Novel Architecture for Java Vulnerability Identification Based Quad Self-Attention and Pre-training Mechanism

Software vulnerabilities pose significant risks to computer systems, impacting our daily lives, productivity, and even our health. Identifying and addressing security vulnerabilities in a timely manner is crucial to prevent hacking and data breaches. Unfortunately, current vulnerability identification methods, including classical and deep learning-based approaches, exhibit critical drawbacks that prevent them from meeting the demands of the contemporary software industry. To tackle these issues, we present JFinder, a novel architecture for Java vulnerability identification that leverages quad self-attention and pre-training mechanisms to combine structural information and semantic representations. Experimental results demonstrate that JFinder outperforms all baseline methods, achieving an accuracy of 0.97 on the CWE dataset and an F1 score of 0.84 on the PROMISE dataset. Furthermore, a case study reveals that JFinder can accurately identify four cases of vulnerabilities after patching.

cs.CR↗
arXiv2023

Efficient Dynamic Allocation Policy for Robust Ranking and Selection under Stochastic Control Framework

This research considers the ranking and selection with input uncertainty. The objective is to maximize the posterior probability of correctly selecting the best alternative under a fixed simulation budget, where each alternative is measured by its worst-case performance. We formulate the dynamic simulation budget allocation decision problem as a stochastic control problem under a Bayesian framework. Following the approximate dynamic programming theory, we derive a one-step-ahead dynamic optimal budget allocation policy and prove that this policy achieves consistency and asymptotic optimality. Numerical experiments demonstrate that the proposed procedure can significantly improve performance.

math.OC↗
arXiv2023

Semi-Supervised Learning with Pseudo-Negative Labels for Image Classification

Semi-supervised learning frameworks usually adopt mutual learning approaches with multiple submodels to learn from different perspectives. To avoid transferring erroneous pseudo labels between these submodels, a high threshold is usually used to filter out a large number of low-confidence predictions for unlabeled data. However, such filtering can not fully exploit unlabeled data with low prediction confidence. To overcome this problem, in this work, we propose a mutual learning framework based on pseudo-negative labels. Negative labels are those that a corresponding data item does not belong. In each iteration, one submodel generates pseudo-negative labels for each data item, and the other submodel learns from these labels. The role of the two submodels exchanges after each iteration until convergence. By reducing the prediction probability on pseudo-negative labels, the dual model can improve its prediction ability. We also propose a mechanism to select a few pseudo-negative labels to feed into submodels. In the experiments, our framework achieves state-of-the-art results on several main benchmarks. Specifically, with our framework, the error rates of the 13-layer CNN model are 9.35% and 7.94% for CIFAR-10 with 1000 and 4000 labels, respectively. In addition, for the non-augmented MNIST with only 20 labels, the error rate is 0.81% by our framework, which is much smaller than that of other approaches. Our approach also demonstrates a significant performance improvement in domain adaptation.

cs.CV↗
arXiv2022

DeepVulSeeker: A Novel Vulnerability Identification Framework via Code Graph Structure and Pre-training Mechanism

Software vulnerabilities can pose severe harms to a computing system. They can lead to system crash, privacy leakage, or even physical damage. Correctly identifying vulnerabilities among enormous software codes in a timely manner is so far the essential prerequisite to patch them. Unfortantely, the current vulnerability identification methods, either the classic ones or the deep-learning-based ones, have several critical drawbacks, making them unable to meet the present-day demands put forward by the software industry. To overcome the drawbacks, in this paper, we propose DeepVulSeeker, a novel fully automated vulnerability identification framework, which leverages both code graph structures and the semantic features with the help of the recently advanced Graph Representation Self-Attention and pre-training mechanisms. Our experiments show that DeepVulSeeker not only reaches an accuracy as high as 0.99 on traditional CWE datasets, but also outperforms all other exisiting methods on two highly-complicated datasets. We also testified DeepVulSeeker based on three case studies, and found that DeepVulSeeker is able to understand the implications of the vulnerbilities. We have fully implemented DeepVulSeeker and open-sourced it for future follow-up research.

cs.CR↗
arXiv2022

Moderate deviations and local limit theorems for the coefficients of random walks on the general linear group

Consider the random walk $G_n : = g_n \ldots g_1$, $n \geq 1$, where $(g_n)_{n\geq 1}$ is a sequence of independent and identically distributed random elements with law $μ$ on the general linear group ${\rm GL}(V)$ with $V=\mathbb R^d$. Under suitable conditions on $μ$, we establish Cramér type moderate deviation expansions and local limit theorems with moderate deviations for the coefficients $\langle f, G_n v \rangle$, where $v \in V$ and $f \in V^*$. Our approach is based on the Hölder regularity of the invariant measure of the Markov chain $G_n \!\cdot \! x = \mathbb R G_n v$ on the projective space of $V$ with the starting point $x = \mathbb R v$, under the changed measure.

math.PR↗
arXiv2022

Edgeworth expansion for the coefficients of random walks on the general linear group

Let $(g_n)_{n\geq 1}$ be a sequence of independent and identically distributed random elements with law $μ$ on the general linear group $\textup{GL}(V)$, where $V=\mathbb R^d$. Consider the random walk $G_n : = g_n \ldots g_1$, $n \geq 1$. Under suitable conditions on $μ$, we establish the first-order Edgeworth expansion for the coefficients $\langle f, G_n v \rangle$ with $v \in V$ and $f \in V^*$, in which a new additional term appears compared to the case of vector norm $\|G_n v\|$.

math.PR↗
arXiv2022

Semi-Supervised Semantic Segmentation with Cross Teacher Training

Convolutional neural networks can achieve remarkable performance in semantic segmentation tasks. However, such neural network approaches heavily rely on costly pixel-level annotation. Semi-supervised learning is a promising resolution to tackle this issue, but its performance still far falls behind the fully supervised counterpart. This work proposes a cross-teacher training framework with three modules that significantly improves traditional semi-supervised learning approaches. The core is a cross-teacher module, which could simultaneously reduce the coupling among peer networks and the error accumulation between teacher and student networks. In addition, we propose two complementary contrastive learning modules. The high-level module can transfer high-quality knowledge from labeled data to unlabeled ones and promote separation between classes in feature space. The low-level module can encourage low-quality features learning from the high-quality features among peer networks. In experiments, the cross-teacher module significantly improves the performance of traditional student-teacher approaches, and our framework outperforms stateof-the-art methods on benchmark datasets. Our source code of CTT will be released.

cs.CV↗
arXiv2021

Limit theorems for the coefficients of random walks on the general linear group

Let $(g_n)_{n\geq 1}$ be a sequence of independent and identically distributed random elements with law $μ$ on the general linear group $\textrm{GL}(V)$, where $V=\mathbb R^d$. Consider the random walk $G_n : = g_n \ldots g_1$, $n \geq 1$, and the coefficients $\langle f, G_n v \rangle$, where $v \in V$ and $f \in V^*$. Under suitable moment assumptions on $μ$, we prove the strong and weak laws of large numbers and the central limit theorem for $\langle f, G_n v \rangle$, which improve the previous results established under the exponential moment condition on $μ$. We further demonstrate the Berry-Esseen bound, the Edgeworth expansion, the Cramér type moderate deviation expansion and the local limit theorem with moderate deviations for $\langle f, G_n v \rangle$ under the exponential moment condition. Under a subexponential moment condition on $μ$, we also show a Berry-Esseen type bound and the moderate deviation principle for $\langle f, G_n v \rangle$. Our approach is based on various versions of the Hölder regularity of the invariant measure of the Markov chain $G_n \!\cdot \! x = \mathbb R G_n v$ on the projective space of $V$ with the starting point $x = \mathbb R v$.

math.PR↗
arXiv2021

Conditioned limit theorems for hyperbolic dynamical systems

Let $(\mathbb X, T)$ be a subshift of finite type equipped with the Gibbs measure $ν$ and let $f$ be a real-valued Hölder continuous function on $\mathbb X$ such that $ν(f) = 0$. Consider the Birkhoff sums $S_n f = \sum_{k=0}^{n-1} f \circ T^{k}$, $n\geq 1$. For any $t \in \mathbb R$, denote by $τ_t^f$ the first time when the sum $t+ S_n f$ leaves the positive half-line for some $n\geq 1$. By analogy with the case of random walks with independent identically distributed increments, we study the asymptotic as $n\to\infty$ of the probabilities $ ν(x\in \mathbb X: τ_t^f(x)>n) $ and $ ν(x\in \mathbb X: τ_t^f(x)=n) $. We also establish integral and local type limit theorems for the sum $t+ S_n f(x)$ conditioned on the set $\{ x \in \mathbb X: τ_t^f(x)>n \}$.

math.DS↗
arXiv2021

Conditioned local limit theorems for random walks on the real line

Consider a random walk $S_n=\sum_{i=1}^n X_i$ with independent and identically distributed real-valued increments $X_i$ of zero mean and finite variance. Assume that $X_i$ is non-lattice and has a moment of order $2+δ$. For any $x\geq 0$, let $τ_x = \inf \left\{ k\geq 1: x+S_{k} < 0 \right\}$ be the first time when the random walk $x+S_n$ leaves the half-line $[0,\infty)$. We study the asymptotic behavior of the probability $\bb P (τ_x >n)$ and that of the expectation $\mathbb{E} \left( f(x + S_n ), τ_x > n \right)$ for a large class of target function $f$ and various values of $x$, $y$ possibly depending on $n$. This general setting implies limit theorems for the joint distribution $\mathbb{P} \left( x + S_n \in y+ [0, Δ], τ_x > n \right)$ where $Δ>0$ may also depend on $n$. In particular, the case of moderate deviations $y=σ\sqrt{q n\log n}$ is considered. We also deduce some new asymptotics for random walks with drift and give explicit constants in the asymptotic of the probability $\bb P (τ_x =n)$. For the proofs we establish new conditioned integral limit theorems with precise error terms.

math.PR↗
arXiv2020

Large deviation expansions for the coefficients of random walks on the general linear group

Let $(g_n)_{n\geq 1}$ be a sequence of independent and identically distributed elements of the general linear group $GL(d, \mathbb R)$. Consider the random walk $G_n: = g_n \ldots g_1$. Under suitable conditions, we establish Bahadur-Rao-Petrov type large deviation expansion for the coefficients $\langle f, G_n v \rangle$, where $f \in (\mathbb R^d)^*$ and $v \in \mathbb R^d$. In particular, our result implies the large deviation principle with an explicit rate function, thus improving significantly the large deviation bounds established earlier. Moreover, we establish Bahadur-Rao-Petrov type large deviation expansion for the coefficients $\langle f, G_n v \rangle$ under the changed measure. Toward this end we prove the Hölder regularity of the stationary measure corresponding to the Markov chain $G_n v /|G_n v|$ under the changed measure, which is of independent interest. In addition, we also prove local limit theorems with large deviations for the coefficients of $G_n$.

math.PR↗
arXiv2020

Berry-Esseen bounds and moderate deviations for the norm, entries and spectral radius of products of positive random matrices

Let $(g_{n})_{n\geq 1}$ be a sequence of independent and identically distributed positive random $d\times d$ matrices and consider the matrix product $G_n: = g_n \ldots g_1$. Under suitable conditions, we establish the Berry-Esseen bounds on the rate of convergence in the central limit theorem and moderate deviation expansions of Cramér type, for the matrix norm $\| G_n \|$ of $G_n$, for its $(i,j)$-th entry $G_n^{i,j}$, and the and for its spectral radius $ρ(G_n)$.

math.PR↗
arXiv2019

Precise large deviation asymptotics for products of random matrices

Let $(g_{n})_{n\geq 1}$ be a sequence of independent identically distributed $d\times d$ real random matrices with Lyapunov exponent $γ$. For any starting point $x$ on the unit sphere in $\mathbb R^d$, we deal with the norm $ | G_n x | $, where $G_{n}:=g_{n} \ldots g_{1}$. The goal of this paper is to establish precise asymptotics for large deviation probabilities $\mathbb P(\log | G_n x | \geq n(q+l))$, where $q>γ$ is fixed and $l$ is vanishing as $n\to \infty$. We study both invertible matrices and positive matrices and give analogous results for the couple $(X_n^x,\log | G_n x |)$ with target functions, where $X_n^x= G_n x /| G_n x |$. As applications we improve previous results on the large deviation principle for the matrix norm $\|G_n\|$ and obtain a precise local limit theorem with large deviations.

math.PR↗