arXiv subjects

Xiyu Wang

Publications and source records attributed to Xiyu Wang.

32 records · Page 2Linked to original sources

arXiv2023

Boosting Diffusion Models with an Adaptive Momentum Sampler

Diffusion probabilistic models (DPMs) have been shown to generate high-quality images without the need for delicate adversarial training. However, the current sampling process in DPMs is prone to violent shaking. In this paper, we present a novel reverse sampler for DPMs inspired by the widely-used Adam optimizer. Our proposed sampler can be readily applied to a pre-trained diffusion model, utilizing momentum mechanisms and adaptive updating to smooth the reverse sampling process and ensure stable generation, resulting in outputs of enhanced quality. By implicitly reusing update directions from early steps, our proposed sampler achieves a better balance between high-level semantics and low-level details. Additionally, this sampler is flexible and can be easily integrated into pre-trained DPMs regardless of the sampler used during training. Our experimental results on multiple benchmarks demonstrate that our proposed reverse sampler yields remarkable improvements over different baselines. We will make the source code available.

cs.CV↗

arXiv2023

Efficient Transfer Learning in Diffusion Models via Adversarial Noise

Diffusion Probabilistic Models (DPMs) have demonstrated substantial promise in image generation tasks but heavily rely on the availability of large amounts of training data. Previous works, like GANs, have tackled the limited data problem by transferring pre-trained models learned with sufficient data. However, those methods are hard to be utilized in DPMs since the distinct differences between DPM-based and GAN-based methods, showing in the unique iterative denoising process integral and the need for many timesteps with no-targeted noise in DPMs. In this paper, we propose a novel DPMs-based transfer learning method, TAN, to address the limited data problem. It includes two strategies: similarity-guided training, which boosts transfer with a classifier, and adversarial noise selection which adaptive chooses targeted noise based on the input image. Extensive experiments in the context of few-shot image generation tasks demonstrate that our method is not only efficient but also excels in terms of image quality and diversity when compared to existing GAN-based and DDPM-based methods.

cs.CV↗

arXiv2023

GujiBERT and GujiGPT: Construction of Intelligent Information Processing Foundation Language Models for Ancient Texts

In the context of the rapid development of large language models, we have meticulously trained and introduced the GujiBERT and GujiGPT language models, which are foundational models specifically designed for intelligent information processing of ancient texts. These models have been trained on an extensive dataset that encompasses both simplified and traditional Chinese characters, allowing them to effectively handle various natural language processing tasks related to ancient books, including but not limited to automatic sentence segmentation, punctuation, word segmentation, part-of-speech tagging, entity recognition, and automatic translation. Notably, these models have exhibited exceptional performance across a range of validation tasks using publicly available datasets. Our research findings highlight the efficacy of employing self-supervised methods to further train the models using classical text corpora, thus enhancing their capability to tackle downstream tasks. Moreover, it is worth emphasizing that the choice of font, the scale of the corpus, and the initial model selection all exert significant influence over the ultimate experimental outcomes. To cater to the diverse text processing preferences of researchers in digital humanities and linguistics, we have developed three distinct categories comprising a total of nine model variations. We believe that by sharing these foundational language models specialized in the domain of ancient texts, we can facilitate the intelligent processing and scholarly exploration of ancient literary works and, consequently, contribute to the global dissemination of China's rich and esteemed traditional culture in this new era.

cs.CL↗

arXiv2023

Learning Structure-Guided Diffusion Model for 2D Human Pose Estimation

One of the mainstream schemes for 2D human pose estimation (HPE) is learning keypoints heatmaps by a neural network. Existing methods typically improve the quality of heatmaps by customized architectures, such as high-resolution representation and vision Transformers. In this paper, we propose \textbf{DiffusionPose}, a new scheme that formulates 2D HPE as a keypoints heatmaps generation problem from noised heatmaps. During training, the keypoints are diffused to random distribution by adding noises and the diffusion model learns to recover ground-truth heatmaps from noised heatmaps with respect to conditions constructed by image feature. During inference, the diffusion model generates heatmaps from initialized heatmaps in a progressive denoising way. Moreover, we further explore improving the performance of DiffusionPose with conditions from human structural information. Extensive experiments show the prowess of our DiffusionPose, with improvements of 1.6, 1.2, and 1.2 mAP on widely-used COCO, CrowdPose, and AI Challenge datasets, respectively.

cs.CV↗

arXiv2023

Ambient FSK Backscatter Communications using LTE Cell Specific Reference Signals

Long Term Evolution (LTE) signal is ubiquitously present in electromagnetic (EM) background environment, which make it an attractive signal source for the ambient backscatter communications (AmBC). In this paper, we propose a system, in which a backscatter device (BD) introduces artificial Doppler shift to the channel which is larger than the natural Doppler but still small enough such that it can be tracked by the channel estimator at the User Equipment (UE). Channel estimation is done using the downlink cell specific reference signals (CRS) that are present regardless the UE being attached to the network or not. FSK was selected due to its robust operation in a fading channel. We describe the whole AmBC system, use two receivers. Finally, numerical simulations and measurements are provided to validate the proposed FSK AmBC performance.

eess.SP↗

arXiv2023

Async-fork: Mitigating Query Latency Spikes Incurred by the Fork-based Snapshot Mechanism from the OS Level

In-memory key-value stores (IMKVSes) serve many online applications because of their efficiency. To support data backup, popular industrial IMKVSes periodically take a point-in-time snapshot of the in-memory data with the system call fork. However, this mechanism can result in latency spikes for queries arriving during the snapshot period because fork leads the engine into the kernel mode in which the engine is out-of-service for queries. In contrast to existing research focusing on optimizing snapshot algorithms, we optimize the fork operation to address the latency spikes problem from the operating system (OS) level, while keeping the data persistent mechanism in IMKVSes unchanged. Specifically, we first conduct an in-depth study to reveal the impact of the fork operation as well as the optimization techniques on query latency. Based on findings in the study, we propose Async-fork to offload the work of copying the page table from the engine (the parent process) to the child process as copying the page table dominates the execution time of fork. To keep data consistent between the parent and the child, we design the proactive synchronization strategy. Async-fork is implemented in the Linux kernel and deployed into the online Redis database in public clouds. Our experiment results show that compared with the default fork method in OS, Async-fork reduces the tail latency of queries arriving during the snapshot period by 81.76% on an 8GB instance and 99.84% on a 64GB instance.

cs.DB↗

arXiv2022

Domain Adaptation via Bidirectional Cross-Attention Transformer

Domain Adaptation (DA) aims to leverage the knowledge learned from a source domain with ample labeled data to a target domain with unlabeled data only. Most existing studies on DA contribute to learning domain-invariant feature representations for both domains by minimizing the domain gap based on convolution-based neural networks. Recently, vision transformers significantly improved performance in multiple vision tasks. Built on vision transformers, in this paper we propose a Bidirectional Cross-Attention Transformer (BCAT) for DA with the aim to improve the performance. In the proposed BCAT, the attention mechanism can extract implicit source and target mixup feature representations to narrow the domain discrepancy. Specifically, in BCAT, we design a weight-sharing quadruple-branch transformer with a bidirectional cross-attention mechanism to learn domain-invariant feature representations. Extensive experiments demonstrate that the proposed BCAT model achieves superior performance on four benchmark datasets over existing state-of-the-art DA methods that are based on convolutions or transformers.

cs.CV↗

arXiv2022

Ambient backscatter communications using LTE cell specific reference signals

Long Term Evolution (LTE) systems provide ubiquitous coverage for mobile communications, which makes it a promising candidate to be used as a signal source in the ambient backscatter communications. In this paper, we propose a system in which a backscatter device modulates the ambient LTE signal by changing its reflection coefficient and the receiver uses the LTE Cell Specific Reference Signals (CRS) to estimate the channel and demodulates the backscattered signal from the obtained channel impulse response estimates. We first outline the overall system, discuss the receiver operation, and then provide experimental evidence on the practicality of the proposed system.

eess.SP↗

arXiv2022

Calibrating Class Weights with Multi-Modal Information for Partial Video Domain Adaptation

Assuming the source label space subsumes the target one, Partial Video Domain Adaptation (PVDA) is a more general and practical scenario for cross-domain video classification problems. The key challenge of PVDA is to mitigate the negative transfer caused by the source-only outlier classes. To tackle this challenge, a crucial step is to aggregate target predictions to assign class weights by up-weighing target classes and down-weighing outlier classes. However, the incorrect predictions of class weights can mislead the network and lead to negative transfer. Previous works improve the class weight accuracy by utilizing temporal features and attention mechanisms, but these methods may fall short when trying to generate accurate class weight when domain shifts are significant, as in most real-world scenarios. To deal with these challenges, we propose the Multi-modality Cluster-calibrated partial Adversarial Network (MCAN). MCAN enhances video feature extraction with multi-modal features from multiple temporal scales to form more robust overall features. It utilizes a novel class weight calibration method to alleviate the negative transfer caused by incorrect class weights. The calibration method tries to identify and weigh correct and incorrect predictions using distributional information implied by unsupervised clustering. Extensive experiments are conducted on prevailing PVDA benchmarks, and the proposed MCAN achieves significant improvements when compared to state-of-the-art PVDA methods.

cs.CV↗

arXiv2022

Parametric Euler Sums of Harmonic Numbers

We define a parametric variant of generalized Euler sums and construct contour integration to give some explicit evaluations of these parametric Euler sums. In particular, we establish several explicit formulas of (Hurwitz) zeta functions, linear and quadratic parametric Euler sums. Furthermore, we also give an explicit evaluation of alternating double zeta values $\ze(\overline{2j},2m+1)$ in terms of a combination of alternating Riemann zeta values by using the parametric Euler sums.

math.NT↗

arXiv2020

Coherent Multi-antenna Receiver for BPSK-modulated Ambient Backscatter Tags

Ambient Backscatter Communication (AmBC) is an emerging communication technology that can enable green Internet-of-Things deployments. The widespread acceptance of this paradigm is limited by low Signal-to-Interference-Plus-Noise Ratio (SINR) of the signal impinging on the receiver antenna due to the strong direct path interference and unknown ambient signal. The adverse impact of these two factors can be mitigated by using non-coherent multi-antenna receivers, which is known to require higher SINR to reach Bit-Error-Rate (BER) performance of coherent receivers. However, in literature, coherent receivers for AmBC systems are little-studied because of unknown ambient signal, unknown location of AmBC tags, and varying channel conditions. In this paper, a coherent multi-antenna receiver, which does not require a prior information of the ambient signal, for decoding Binary-Phase-shift-Keying (BPSK) modulated signal is presented. The performance of the proposed receiver is compared with the ideal coherent receiver that has a perfect phase information, and also with the performance of non-coherent receiver, which assumes distributions for ambient signal and phase offset caused by excess length of the backscatter path. Comparative simulation results show the designed receiver can achieve the same BER-performance of the ideal coherent receiver with 1-dB more SINR, which corresponds to 5-dB or more gain with respect to non-coherent reception of On-Off-Keying modulated signals. Variation of the detection performance with the tag location shows that the coverage area is in the close vicinity of the transmitter and a larger region around the receiver, which is consistent with the theoretical results.

eess.SP↗

arXiv2020

Optimum Multi-Antenna Ambient Backscatter Receiver for General Binary-Modulated Signal

Ambient backscatter communication (AmBC) is becoming increasingly popular for enabling green communication amidst the continual development of the Internet-of-things paradigm. Efforts have been put into backscatter signal detection as the detection performance is limited by the low signal-to-interference-plus-noise ratio (SINR) of the signal at the receiver. The low SINR can be improved by adopting a multi-antenna receiver. In this paper, the optimum multi-antenna receiver that does not impose any constraints on the types of binary modulation performed by the backscatter device and the waveform used by the ambient source system is studied. The proposed receiver owns a simple structure formed by two beamformers. Bit error rate (BER) performances of the optimum receiver are derived under constant-amplitude ambient signal and Gaussian-distributed ambient signal. Moreover, to facilitate the implementation of the optimum receiver, a simplified receiver is proposed and practical approximations to required beamformers are provided. The derived optimum receiver avoids the complex direct path interference cancellation and coherent reception, but exploits the fact that backscatter signal changes the composite channel impinging at the receiver and the directivity of receiver antenna array. Comparative simulation results show that the performance of the optimum receiver achieves the same performance as the coherent receiver even though it realizes non-coherent reception. The studied receivers provide high flexibility for implementing simple and low-cost receivers in different AmBC systems.

eess.SP↗

arXiv2018

An Unsupervised Deep Learning Approach for Scenario Forecasts

In this paper, we propose a novel scenario forecasts approach which can be applied to a broad range of power system operations (e.g., wind, solar, load) over various forecasts horizons and prediction intervals. This approach is model-free and data-driven, producing a set of scenarios that represent possible future behaviors based only on historical observations and point forecasts. It first applies a newly-developed unsupervised deep learning framework, the generative adversarial networks, to learn the intrinsic patterns in historical renewable generation data. Then by solving an optimization problem, we are able to quickly generate large number of realistic future scenarios. The proposed method has been applied to a wind power generation and forecasting dataset from national renewable energy laboratory. Simulation results indicate our method is able to generate scenarios that capture spatial and temporal correlations. Our code and simulation datasets are freely available online.

math.OC↗

arXiv2017

Handover Analysis on High Speed Train with Doppler Frequency Spread

This paper investigates the handover performance on high speed train (HST) via different speed under three scenarios, which are viaduct environment, cutting environment and urban area. To provide stable wireless service, we adopt Long Term Evolution (LTE) for high speed railway (HST) system. Moreover, we consider the effect of speed on handover procedure. Interchannel interference (ICI) caused by the Doppler frequency spread is related to the speed of HST, which is considered into the proposed system to evaluate the system handover performance including handover starting time and handover delay. Numerical results show the parameters in the system including SNR, throughput, handover starting time and handover delay. The proposed system provides some insights for practical railway system.

cs.NI↗