arXiv subjects

Wei Huang

Publications and source records attributed to Wei Huang.

At least 361 records · Page 20Linked to original sources

arXiv2022

Playing Tic-Tac-Toe Games with Intelligent Single-pixel Imaging

Single-pixel imaging (SPI) is a novel optical imaging technique by replacing a two-dimensional pixelated sensor with a single-pixel detector and pattern illuminations. SPI have been extensively used for various tasks related to image acquisition and processing. In this work, a novel non-image-based task of playing Tic-Tac-Toe games interactively is merged into the framework of SPI. An optoelectronic artificial intelligent (AI) player with minimal digital computation can detect the game states, generate optimal moves and display output results mainly by pattern illumination and single-pixel detection. Simulated and experimental results demonstrate the feasibility of proposed scheme and its unbeatable performance against human players.

cs.CV↗

arXiv2022

Isogeometric analysis of diffusion problems on random surfaces

In this article, we discuss the numerical solution of diffusion equations on random surfaces within the isogeometric framework. We describe in detail, how diffusion problems on random surfaces can be modelled and how quantities of interest may be derived. In particular, we employ a low rank approximation algorithm for the high-dimensional space-time correlation of the random solution based on an online singular value decomposition, cp. [7]. Extensive numerical studies are performed to validate the approach. In particular, we consider complex computational geometries originating from surface triangulations. The latter can be recast into the isogeometric context by transforming them into quadrangulations using the procedure from [41] and a subsequent approximation by NURBS surfaces.

math.NA↗

arXiv2022

Filtering electrons by mode coupling in finite semiconductor superlattices

Electron transmission through semiconductor superlattices is studied with transfer matrix method and resonance theory. The formation of electron band-pass transmission is ascribed to the coupling of different modes in those semiconductor superlattices with the symmetric unit cell. Upon Fabry-Pérot resonance condition, Bloch modes and two other resonant modes are identified to be related to the nature of the superlattice and its unit cell, respectively. The bands related to the unit cell and the superlattice overlap spontaneously in the tunneling region due to the shared wells, and the coupling of perfectly resonances results in the band-pass tunneling. Our findings provide a promising way to study electronic systems with more complicated superlattices or even optical systems with photonic crystals.

cond-mat.mes-hall↗

arXiv2022

Towards Deepening Graph Neural Networks: A GNTK-based Optimization Perspective

Graph convolutional networks (GCNs) and their variants have achieved great success in dealing with graph-structured data. Nevertheless, it is well known that deep GCNs suffer from the over-smoothing problem, where node representations tend to be indistinguishable as more layers are stacked up. The theoretical research to date on deep GCNs has focused primarily on expressive power rather than trainability, an optimization perspective. Compared to expressivity, trainability attempts to address a more fundamental question: Given a sufficiently expressive space of models, can we successfully find a good solution via gradient descent-based optimizers? This work fills this gap by exploiting the Graph Neural Tangent Kernel (GNTK), which governs the optimization trajectory under gradient descent for wide GCNs. We formulate the asymptotic behaviors of GNTK in the large depth, which enables us to reveal the dropping trainability of wide and deep GCNs at an exponential rate in the optimization process. Additionally, we extend our theoretical framework to analyze residual connection-based techniques, which are found to be merely able to mitigate the exponential decay of trainability mildly. Inspired by our theoretical insights on trainability, we propose Critical DropEdge, a connectivity-aware and graph-adaptive sampling method, to alleviate the exponential decay problem more fundamentally. Experimental evaluation consistently confirms using our proposed method can achieve better results compared to relevant counterparts with both infinite-width and finite-width.

cs.LG↗

arXiv2022

Experimental Demonstration of High-Rate Discrete-Modulated Continuous-Variable Quantum Key Distribution System

A high-rate continuous-variable quantum key distribution (CV-QKD) system based on high-order discrete modulation is experimentally investigated. With the help of the novel system scheme, effective digital signal processing algorithms and advanced analytical security proof method, the transmission results of 5 km, 10 km, 25 km, and 50 km are achieved for the 1 GBaud optimized quantum signals. Correspondingly, the asymptotic secret key rate (SKR) is 288.421 Mbps, 159.395 Mbps, 50.004 Mbps and 7.579 Mbps for discrete Gaussian (DG) 64QAM, and 326.708 Mbps, 179.348 Mbps, 50.623 Mbps and 9.212 Mbps for DG 256QAM. Under the same parameters, the achieved SKRs of DG 256QAM is almost same to ideal Gaussian modulation. In this case, the demonstrated high-rate discrete modulated CV-QKD system has the application potential for high speed security communication under tens of kilometers.

quant-ph↗

arXiv2022

Enhancing Adversarial Training with Second-Order Statistics of Weights

Adversarial training has been shown to be one of the most effective approaches to improve the robustness of deep neural networks. It is formalized as a min-max optimization over model weights and adversarial perturbations, where the weights can be optimized through gradient descent methods like SGD. In this paper, we show that treating model weights as random variables allows for enhancing adversarial training through \textbf{S}econd-Order \textbf{S}tatistics \textbf{O}ptimization (S$^2$O) with respect to the weights. By relaxing a common (but unrealistic) assumption of previous PAC-Bayesian frameworks that all weights are statistically independent, we derive an improved PAC-Bayesian adversarial generalization bound, which suggests that optimizing second-order statistics of weights can effectively tighten the bound. In addition to this theoretical insight, we conduct an extensive set of experiments, which show that S$^2$O not only improves the robustness and generalization of the trained neural networks when used in isolation, but also integrates easily in state-of-the-art adversarial training techniques like TRADES, AWP, MART, and AVMixup, leading to a measurable improvement of these techniques. The code is available at \url{https://github.com/Alexkael/S2O}.

cs.LG↗

arXiv2022

An Audio-Visual Attention Based Multimodal Network for Fake Talking Face Videos Detection

DeepFake based digital facial forgery is threatening the public media security, especially when lip manipulation has been used in talking face generation, the difficulty of fake video detection is further improved. By only changing lip shape to match the given speech, the facial features of identity is hard to be discriminated in such fake talking face videos. Together with the lack of attention on audio stream as the prior knowledge, the detection failure of fake talking face generation also becomes inevitable. Inspired by the decision-making mechanism of human multisensory perception system, which enables the auditory information to enhance post-sensory visual evidence for informed decisions output, in this study, a fake talking face detection framework FTFDNet is proposed by incorporating audio and visual representation to achieve more accurate fake talking face videos detection. Furthermore, an audio-visual attention mechanism (AVAM) is proposed to discover more informative features, which can be seamlessly integrated into any audio-visual CNN architectures by modularization. With the additional AVAM, the proposed FTFDNet is able to achieve a better detection performance on the established dataset (FTFDD). The evaluation of the proposed work has shown an excellent performance on the detection of fake talking face videos, which is able to arrive at a detection rate above 97%.

cs.CV↗

arXiv2022

Secure two-way fiber-optic time transfer against sub-ns asymmetric delay attack

Two-way fiber-optic time transfer is a promising precise time synchronization technique with sub-nanosecond accuracy. However, asymmetric delay attack is a serious threat which cannot be prevent by any encryption method. In this paper, a dynamic model based scheme is proposed to defense the sub-nanosecond asymmetric delay attack. A threshold is set according to the estimated time difference by a two-state clock model where the fixed frequency difference is excluded from the time difference to detect the asymmetric delay attack which is smaller than the time difference induced by the fixed frequency difference. Theoretical simulation and experimental demonstration are implemented to prove the feasibility of the scheme. A two-way fiber-optic time transfer system with time stability with 24.5ps, 3.98ps, and 2.95ps at 1s, 10s, and 100s averaging time is shown under sub-ns asymmetric time delay attack experimentally. The proposed method provides a promising secure sub-ns precise time synchronization technique against asymmetric delay attack.

quant-ph↗

arXiv2022

Attention-Based Lip Audio-Visual Synthesis for Talking Face Generation in the Wild

Talking face generation with great practical significance has attracted more attention in recent audio-visual studies. How to achieve accurate lip synchronization is a long-standing challenge to be further investigated. Motivated by xxx, in this paper, an AttnWav2Lip model is proposed by incorporating spatial attention module and channel attention module into lip-syncing strategy. Rather than focusing on the unimportant regions of the face image, the proposed AttnWav2Lip model is able to pay more attention on the lip region reconstruction. To our limited knowledge, this is the first attempt to introduce attention mechanism to the scheme of talking face generation. An extensive experiments have been conducted to evaluate the effectiveness of the proposed model. Compared to the baseline measured by LSE-D and LSE-C metrics, a superior performance has been demonstrated on the benchmark lip synthesis datasets, including LRW, LRS2 and LRS3.

cs.CV↗

arXiv2022

Audio-visual speech separation based on joint feature representation with cross-modal attention

Multi-modal based speech separation has exhibited a specific advantage on isolating the target character in multi-talker noisy environments. Unfortunately, most of current separation strategies prefer a straightforward fusion based on feature learning of each single modality, which is far from sufficient consideration of inter-relationships between modalites. Inspired by learning joint feature representations from audio and visual streams with attention mechanism, in this study, a novel cross-modal fusion strategy is proposed to benefit the whole framework with semantic correlations between different modalities. To further improve audio-visual speech separation, the dense optical flow of lip motion is incorporated to strengthen the robustness of visual representation. The evaluation of the proposed work is performed on two public audio-visual speech separation benchmark datasets. The overall improvement of the performance has demonstrated that the additional motion network effectively enhances the visual representation of the combined lip images and audio signal, as well as outperforming the baseline in terms of all metrics with the proposed cross-modal fusion.

cs.SD↗

arXiv2022

Auto-scaling Vision Transformers without Training

This work targets automated designing and scaling of Vision Transformers (ViTs). The motivation comes from two pain spots: 1) the lack of efficient and principled methods for designing and scaling ViTs; 2) the tremendous computational cost of training ViT that is much heavier than its convolution counterpart. To tackle these issues, we propose As-ViT, an auto-scaling framework for ViTs without training, which automatically discovers and scales up ViTs in an efficient and principled manner. Specifically, we first design a "seed" ViT topology by leveraging a training-free search process. This extremely fast search is fulfilled by a comprehensive study of ViT's network complexity, yielding a strong Kendall-tau correlation with ground-truth accuracies. Second, starting from the "seed" topology, we automate the scaling rule for ViTs by growing widths/depths to different ViT layers. This results in a series of architectures with different numbers of parameters in a single run. Finally, based on the observation that ViTs can tolerate coarse tokenization in early training stages, we propose a progressive tokenization strategy to train ViTs faster and cheaper. As a unified framework, As-ViT achieves strong performance on classification (83.5% top1 on ImageNet-1k) and detection (52.7% mAP on COCO) without any manual crafting nor scaling of ViT architectures: the end-to-end model design and scaling process cost only 12 hours on one V100 GPU. Our code is available at https://github.com/VITA-Group/AsViT.

cs.LG↗

arXiv2022

Achieving Efficient Distributed Machine Learning Using a Novel Non-Linear Class of Aggregation Functions

Distributed machine learning (DML) over time-varying networks can be an enabler for emerging decentralized ML applications such as autonomous driving and drone fleeting. However, the commonly used weighted arithmetic mean model aggregation function in existing DML systems can result in high model loss, low model accuracy, and slow convergence speed over time-varying networks. To address this issue, in this paper, we propose a novel non-linear class of model aggregation functions to achieve efficient DML over time-varying networks. Instead of taking a linear aggregation of neighboring models as most existing studies do, our mechanism uses a nonlinear aggregation, a weighted power-p mean (WPM), as the aggregation function of local models from neighbors. The subsequent optimizing steps are taken using mirror descent defined by a Bregman divergence that maintains convergence to optimality. In this paper, we analyze properties of the WPM and rigorously prove convergence properties of our aggregation mechanism. Additionally, through extensive experiments, we show that when p > 1, our design significantly improves the convergence speed of the model and the scalability of DML under time-varying networks compared with arithmetic mean aggregation functions, with little additional computation overhead.

cs.LG↗

arXiv2022

Demystify Optimization and Generalization of Over-parameterized PAC-Bayesian Learning

PAC-Bayesian is an analysis framework where the training error can be expressed as the weighted average of the hypotheses in the posterior distribution whilst incorporating the prior knowledge. In addition to being a pure generalization bound analysis tool, PAC-Bayesian bound can also be incorporated into an objective function to train a probabilistic neural network, making them a powerful and relevant framework that can numerically provide a tight generalization bound for supervised learning. For simplicity, we call probabilistic neural network learned using training objectives derived from PAC-Bayesian bounds as {\it PAC-Bayesian learning}. Despite their empirical success, the theoretical analysis of PAC-Bayesian learning for neural networks is rarely explored. This paper proposes a new class of convergence and generalization analysis for PAC-Bayes learning when it is used to train the over-parameterized neural networks by the gradient descent method. For a wide probabilistic neural network, we show that when PAC-Bayes learning is applied, the convergence result corresponds to solving a kernel ridge regression when the probabilistic neural tangent kernel (PNTK) is used as its kernel. Based on this finding, we further characterize the uniform PAC-Bayesian generalization bound which improves over the Rademacher complexity-based bound for non-probabilistic neural network. Finally, drawing the insight from our theoretical results, we propose a proxy measure for efficient hyperparameters selection, which is proven to be time-saving.

cs.LG↗

arXiv2022

Knowledge Graph Based Waveform Recommendation: A New Communication Waveform Design Paradigm

Traditionally, a communication waveform is designed by experts based on communication theory and their experiences on a case-by-case basis, which is usually laborious and time-consuming. In this paper, we investigate the waveform design from a novel perspective and propose a new waveform design paradigm with the knowledge graph (KG)-based intelligent recommendation system. The proposed paradigm aims to improve the design efficiency by structural characterization and representations of existing waveforms and intelligently utilizing the knowledge learned from them. To achieve this goal, we first build a communication waveform knowledge graph (CWKG) with a first-order neighbor node, for which both structured semantic knowledge and numerical parameters of a waveform are integrated by representation learning. Based on the developed CWKG, we further propose an intelligent communication waveform recommendation system (CWRS) to generate waveform candidates. In the CWRS, an improved involution1D operator, which is channel-agnostic and space-specific, is introduced according to the characteristics of KG-based waveform representation for feature extraction, and the multi-head self-attention is adopted to weigh the influence of various components for feature fusion. Meanwhile, multilayer perceptron-based collaborative filtering is used to evaluate the matching degree between the requirement and the waveform candidate. Simulation results show that the proposed CWKG-based CWRS can automatically recommend waveform candidates with high reliability.

eess.SP↗

arXiv2021

Coupling-assisted quasi-bound states in the continuum in heterogeneous metasurfaces

In this paper, we present a Bound states in the continuum (BIC) metamaterial in heterogeneous structures based on the universal coupled mode theory. We find the more general physical parameters to represent BIC, which are the resonant frequencies and corresponding phases of metamaterial structures. Therefore, BIC metamaterial comes from the equal value of the resonant frequencies and phases of metamaterial structures which are not only for homogeneous structures. Meanwhile if slightly vary one of metamaterial structure's resonant frequency and phase by varying geometry, we can obtain the quasi-BIC instead of broken symmetry of homogeneous structures. In this paper, we provide the BIC and quasi-BIC with one example of two heterogeneous structures which are cut wire (CW) and Split-Ring Resonator (SRR), to widely extends the metamaterial BIC beyond common sense. Furthermore, we demonstrate the simulation results and experimental results to proof our idea.

physics.optics↗

arXiv2021

Semantic-Aware Generation for Self-Supervised Visual Representation Learning

In this paper, we propose a self-supervised visual representation learning approach which involves both generative and discriminative proxies, where we focus on the former part by requiring the target network to recover the original image based on the mid-level features. Different from prior work that mostly focuses on pixel-level similarity between the original and generated images, we advocate for Semantic-aware Generation (SaGe) to facilitate richer semantics rather than details to be preserved in the generated image. The core idea of implementing SaGe is to use an evaluator, a deep network that is pre-trained without labels, for extracting semantic-aware features. SaGe complements the target network with view-specific features and thus alleviates the semantic degradation brought by intensive data augmentations. We execute SaGe on ImageNet-1K and evaluate the pre-trained models on five downstream tasks including nearest neighbor test, linear classification, and fine-scaled image recognition, demonstrating its ability to learn stronger visual representations.

cs.CV↗

arXiv2021

Sub-Gbps key rate four-state continuous-variable quantum key distribution within metropolitan area

Continuous-variable quantum key distribution (CVQKD) has potential advantages of high secret key rate, which is very suitable for high-speed metropolitan network application. However, the reported highest secret key rates of the CVQKD systems up to now are limited in a few Mbps. Here, we address the fundamental experimental problems and demonstrate a single-carrier four-state CVQKD with sub-Gbps key rate within metropolitan area. In the demonstrated four-state CVQKD using local local oscillator, an ultra-low level of excess noise is obtained and a high efficient post-processing setup is designed for practically extracting the final secure keys. Thus, the achieved secure key rates are 190.54 Mbps and 137.76 Mbps and 52.48 Mbps using linear channel assuming security analysis method and 233.87 Mbps, 133.6 Mbps and 21.53 Mbps using semidefinite programming security analysis method over transmission distances of 5 km, 10 km and 25 km, respectively. This record-breaking result increases the previous secret key rate record by an order of magnitude, which is sufficient to achieve the one-time pad cryptographic task. Our work shows the road for future high-rate and large-scale CVQKD deployment in secure broadband metropolitan and access networks.

quant-ph↗

arXiv2021

Phase-reference intensity attack on continuous-variable quantum key distribution with a real local oscillator

In practical continuous-variable quantum key distribution system using local local oscillator (LLO CV-QKD), the phase noise related to coherent detection and phase-reference pulse intensity that can be locally calibrated at the receiver side is considered to be trusted noise to improve the performance. However, if the intensity of the phase-reference pulse is not monitored precisely in real-time, a security loophole will be opened for the eavesdropper to launch attacks. To this end, we propose two practical phase-reference pulse intensity attack strategies, where Eve can reduce the trusted phase noise by manipulating the intensity of the phase-reference pulse, thereby hiding her attack on the signal pulse if the total excess noise remains unchanged. The performance of the LLO CV-QKD system under these attacks has been analyzed. We show that precisely monitoring the intensity of the phase-reference pulse in real-time is an essential countermeasure to prevent the proposed attacks. Moreover, an intensity-monitoring scheme for the phase-reference pulse is proposed to strengthen the security of the practical LLO CV-QKD system and make the trusted phase noise model more robust.

quant-ph↗