arXiv subjects

Rui Zhang

Publications and source records attributed to Rui Zhang.

At least 487 records · Page 27Linked to original sources

arXiv2024

Vision Mamba Distillation for Low-resolution Fine-grained Image Classification

Low-resolution fine-grained image classification has recently made significant progress, largely thanks to the super-resolution techniques and knowledge distillation methods. However, these approaches lead to an exponential increase in the number of parameters and computational complexity of models. In order to solve this problem, in this letter, we propose a Vision Mamba Distillation (ViMD) approach to enhance the effectiveness and efficiency of low-resolution fine-grained image classification. Concretely, a lightweight super-resolution vision Mamba classification network (SRVM-Net) is proposed to improve its capability for extracting visual features by redesigning the classification sub-network with Mamba modeling. Moreover, we design a novel multi-level Mamba knowledge distillation loss boosting the performance, which can transfer prior knowledge obtained from a High-resolution Vision Mamba classification Network (HRVM-Net) as a teacher into the proposed SRVM-Net as a student. Extensive experiments on seven public fine-grained classification datasets related to benchmarks confirm our ViMD achieves a new state-of-the-art performance. While having higher accuracy, ViMD outperforms similar methods with fewer parameters and FLOPs, which is more suitable for embedded device applications. Code is available at https://github.com/boa2004plaust/ViMD.

cs.CV↗

arXiv2024

A Condensed Transition Graph Framework for Zero-shot Link Prediction with Large Language Models

Zero-shot link prediction (ZSLP) on knowledge graphs aims at automatically identifying relations between given entities. Existing methods primarily employ auxiliary information to predict tail entity given head entity and its relation, yet face challenges due to the occasional unavailability of such detailed information and the inherent simplicity of predicting tail entities based on semantic similarities. Even though Large Language Models (LLMs) offer a promising solution to predict unobserved relations between the head and tail entity in a zero-shot manner, their performance is still restricted due to the inability to leverage all the (exponentially many) paths' information between two entities, which are critical in collectively indicating their relation types. To address this, in this work, we introduce a Condensed Transition Graph Framework for Zero-Shot Link Prediction (CTLP), which encodes all the paths' information in linear time complexity to predict unseen relations between entities, attaining both efficiency and information preservation. Specifically, we design a condensed transition graph encoder with theoretical guarantees on its coverage, expressiveness, and efficiency. It is learned by a transition graph contrastive learning strategy. Subsequently, we design a soft instruction tuning to learn and map the all-path embedding to the input of LLMs. Experimental results show that our proposed CTLP method achieves state-of-the-art performance on three standard ZSLP datasets

cs.CL↗

arXiv2024

RAMIE: Retrieval-Augmented Multi-task Information Extraction with Large Language Models on Dietary Supplements

\textbf{Objective:} We aimed to develop an advanced multi-task large language model (LLM) framework to extract multiple types of information about dietary supplements (DS) from clinical records. \textbf{Methods:} We used four core DS information extraction tasks - namely, named entity recognition (NER: 2,949 clinical sentences), relation extraction (RE: 4,892 sentences), triple extraction (TE: 2,949 sentences), and usage classification (UC: 2,460 sentences) as our multitasks. We introduced a novel Retrieval-Augmented Multi-task Information Extraction (RAMIE) Framework, including: 1) employed instruction fine-tuning techniques with task-specific prompts, 2) trained LLMs for multiple tasks with improved storage efficiency and lower training costs, and 3) incorporated retrieval augmentation generation (RAG) techniques by retrieving similar examples from the training set. We compared RAMIE's performance to LLMs with instruction fine-tuning alone and conducted an ablation study to assess the contributions of multi-task learning and RAG to improved multitasking performance. \textbf{Results:} With the aid of the RAMIE framework, Llama2-13B achieved an F1 score of 87.39 (3.51\% improvement) on the NER task and demonstrated outstanding performance on the RE task with an F1 score of 93.74 (1.15\% improvement). For the TE task, Llama2-7B scored 79.45 (14.26\% improvement), and MedAlpaca-7B achieved the highest F1 score of 93.45 (0.94\% improvement) on the UC task. The ablation study revealed that while MTL increased efficiency with a slight trade-off in performance, RAG significantly boosted overall accuracy. \textbf{Conclusion:} This study presents a novel RAMIE framework that demonstrates substantial improvements in multi-task information extraction for DS-related data from clinical records. Our framework can potentially be applied to other domains.

cs.CL↗

arXiv2024

SEP: Self-Enhanced Prompt Tuning for Visual-Language Model

Prompt tuning based on Context Optimization (CoOp) effectively adapts visual-language models (VLMs) to downstream tasks by inferring additional learnable prompt tokens. However, these tokens are less discriminative as they are independent of the pre-trained tokens and fail to capture input-specific knowledge, such as class-aware textual or instance-aware visual knowledge. Leveraging the discriminative and generalization capabilities inherent in pre-trained tokens, we introduce a novel approach named Self-Enhanced Prompt Tuning (SEP). The core principle of SEP involves adapting the learnable prompt tokens at each encoder layer from the corresponding self-pretrained tokens, thereby explicitly incorporating discriminative prior knowledge to enhance both textual-level and visual-level embeddings. Furthermore, SEP's self-enhanced tokens not only boost discrimination but also mitigate domain shifts in unseen domains, enhancing generalization. In practice, SEP selects several representative tokens from all pre-trained tokens for each input data at every layer of the text/visual encoders. Subsequently, a Token Fusion Module (TFM) is introduced to generate a self-enhanced token by merging these representative tokens with the learnable tokens using a cross-attention mechanism. This self-enhanced token is then concatenated with all pre-trained tokens, serving as input for subsequent encoder layers to produce the relevant embeddings. Comprehensive evaluations across various benchmarks and tasks confirm SEP's efficacy in prompt tuning. Code: \href{Code}{https://github.com/htyao89/SEP}.

cs.CV↗

arXiv2024

Paying more attention to local contrast: improving infrared small target detection performance via prior knowledge

The data-driven method for infrared small target detection (IRSTD) has achieved promising results. However, due to the small scale of infrared small target datasets and the limited number of pixels occupied by the targets themselves, it is a challenging task for deep learning methods to directly learn from these samples. Utilizing human expert knowledge to assist deep learning methods in better learning is worthy of exploration. To effectively guide the model to focus on targets' spatial features, this paper proposes the Local Contrast Attention Enhanced infrared small target detection Network (LCAE-Net), combining prior knowledge with data-driven deep learning methods. LCAE-Net is a U-shaped neural network model which consists of two developed modules: a Local Contrast Enhancement (LCE) module and a Channel Attention Enhancement (CAE) module. The LCE module takes advantages of prior knowledge, leveraging handcrafted convolution operator to acquire Local Contrast Attention (LCA), which could realize background suppression while enhance the potential target region, thus guiding the neural network to pay more attention to potential infrared small targets' location information. To effectively utilize the response information throughout downsampling progresses, the CAE module is proposed to achieve the information fusion among feature maps' different channels. Experimental results indicate that our LCAE-Net outperforms existing state-of-the-art methods on the three public datasets NUDT-SIRST, NUAA-SIRST, and IRSTD-1K, and its detection speed could reach up to 70 fps. Meanwhile, our model has a parameter count and Floating-Point Operations (FLOPs) of 1.945M and 4.862G respectively, which is suitable for deployment on edge devices.

cs.CV↗

arXiv2024

Integrating Base Station with Intelligent Surface for 6G Wireless Networks: Architectures, Design Issues, and Future Directions

Intelligent surface (IS) is envisioned as a promising technology for the sixth-generation (6G) wireless networks, which can effectively reconfigure the wireless propagation environment via dynamically controllable signal reflection/transmission. In particular, integrating passive intelligent surface (IS) into the base station (BS) is a novel solution to enhance the wireless network throughput and coverage both cost-effectively and energyefficiently. In this article, we provide an overview of IS-integrated BSs for wireless networks, including their motivations, practical architectures, and main design issues. Moreover, numerical results are presented to compare the performance of different IS-integrated BS architectures as well as the conventional BS without IS. Finally, promising directions are pointed out to stimulate future research on IS-BS/terminal integration in wireless networks.

eess.SP↗

arXiv2024

Relational Contrastive Learning and Masked Image Modeling for Scene Text Recognition

Context-aware methods have achieved remarkable advancements in supervised scene text recognition by leveraging semantic priors from words. Considering the heterogeneity of text and background in STR, we propose that such contextual priors can be reinterpreted as the relations between textual elements, serving as effective self-supervised labels for representation learning. However, textual relations are restricted to the finite size of the dataset due to lexical dependencies, which causes over-fitting problem, thus compromising the representation quality. To address this, our work introduces a unified framework of Relational Contrastive Learning and Masked Image Modeling for STR (RCMSTR), which explicitly models the enriched textual relations. For the RCL branch, we first introduce the relational rearrangement module to cultivate new relations on the fly. Based on this, we further conduct relational contrastive learning to model the intra- and inter-hierarchical relations for frames, sub-words and words. On the other hand, MIM can naturally boost the context information via masking, where we find that the block masking strategy is more effective for STR. For the effective integration of RCL and MIM, we also introduce a novel decoupling design aimed at mitigating the impact of masked images on contrastive learning. Additionally, to enhance the compatibility of MIM with CNNs, we propose the adoption of sparse convolutions and directly sharing the weights with dense convolutions in training. The proposed RCMSTR demonstrates superior performance in various evaluation protocols for different STR-related downstream tasks, outperforming the existing state-of-the-art self-supervised STR techniques. Ablation studies and qualitative experimental results further validate the effectiveness of our method. The code and pre-trained models will be available at https://github.com/ThunderVVV/RCMSTR .

cs.CV↗

arXiv2024

RSRP Measurement Based Channel Autocorrelation Estimation for IRS-Aided Wideband Communication

The passive and frequency-flat reflection of IRS, as well as the high-dimensional IRS-reflected channels, have posed significant challenges for efficient IRS channel estimation, especially in wideband communication systems with significant multi-path channel delay spread. To address these challenges, we propose a novel neural network (NN)-empowered framework for IRS channel autocorrelation matrix estimation in wideband orthogonal frequency division multiplexing (OFDM) systems. This framework relies only on the easily accessible reference signal received power (RSRP) measurements at users in existing wideband communication systems, without requiring additional pilot transmission. Based on the estimates of channel autocorrelation matrix, the passive reflection of IRS is optimized to maximize the average user received signal-to-noise ratio (SNR) over all subcarriers in the OFDM system. Numerical results verify that the proposed algorithm significantly outperforms existing powermeasurement-based IRS reflection designs in wideband channels.

cs.IT↗

arXiv2024

OFDM Reference Signal Pattern Design Criteria for Integrated Communication and Sensing

Extended ambiguity performance (EAP), which includes all grating lobes and side peaks, indicates the maximum detectable region without undesired peaks for target parameter estimation and is critical to radar sensor design. Driven by EAP requirements of bi-static sensing, we propose design criteria for orthogonal frequency division multiplexing (OFDM) reference signal (RS) patterns. The design not only improves EAP in both time delay and Doppler shift domains under different types of sensing algorithms, but also reduces resource overhead for integrated communication and sensing. With minimal modifications of post-FFT processing for current RS patterns, guard interval is extended beyond conventional cyclic prefix (CP), while maintaining inter-symbol-interference-(ISI)-free delay estimation. For standard-resolution sensing algorithms, a staggering offset of a linear slope that is relatively prime to the RS comb size is suggested. As for super-resolution sensing algorithms, necessary and sufficient conditions of comb RS staggering offsets, plus new patterns synthesized therefrom, are derived for the corresponding achievable EAP. Furthermore, we generalize the RS pattern design criterion for super-resolution sensing algorithms to irregular forms, which minimizes number of resource elements (REs) for associated algorithms to eliminate all side peaks. Starting from staggered comb pattern in current positioning RS, our generalized design eventually removes any regular form for ultimate flexibility. Overall, the proposed techniques are promising to extend the ISI- and ambiguity-free range of distance and speed estimates for radar sensing.

eess.SP↗

arXiv2024

Sum Rate Maximization for Movable Antenna Enhanced Multiuser Covert Communications

In this letter, we propose to employ movable antenna (MA) to enhance covert communications with noise uncertainty, where the confidential data is transmitted from an MA-aided access point (AP) to multiple users with a warden attempting to detect the existence of the legal transmission. To maximize the sum rate of users under covertness constraint, we formulate an optimization problem to jointly design the transmit beamforming and the positions of MAs at the AP. To solve the formulated non-convex optimization problem, we develop a block successive upper-bound minimization (BSUM) based algorithm, where the proximal distance algorithm (PDA) and the successive convex approximation (SCA) are employed to optimize the transmit beamforming and the MAs' positions, respectively. Simulation results show that the proposed MAs-aided system can significantly increase the covert sum rate via antenna position optimization as compared to conventional systems with fixed-position antennas (FPAs).

eess.SP↗

arXiv2024

An Overview on IRS-Enabled Sensing and Communications for 6G: Architectures, Fundamental Limits, and Joint Beamforming Designs

This paper presents an overview on intelligent reflecting surface (IRS)-enabled sensing and communication for the forthcoming sixth-generation (6G) wireless networks, in which IRSs are strategically deployed to proactively reconfigure wireless environments to improve both sensing and communication (S&C) performance. First, we exploit a single IRS to enable wireless sensing in the base station's (BS's) non-line-of-sight (NLoS) area. In particular, we present three IRS-enabled NLoS target sensing architectures with fully-passive, semi-passive, and active IRSs, respectively. We compare their pros and cons by analyzing the fundamental sensing performance limits for target detection and parameter estimation. Next, we consider a single IRS to facilitate integrated sensing and communication (ISAC), in which the transmit signals at the BS are used for achieving both S&C functionalities, aided by the IRS through reflective beamforming. We present joint transmit signal and receiver processing designs for realizing efficient ISAC, and jointly optimize the transmit beamforming at the BS and reflective beamforming at the IRS to balance the fundamental performance tradeoff between S&C. Furthermore, we discuss multi-IRS networked ISAC, by particularly focusing on multi-IRS-enabled multi-link ISAC, multi-region ISAC, and ISAC signal routing, respectively. Finally, we highlight various promising research topics in this area to motivate future work.

eess.SP↗

arXiv2024

Radio-Based Passive Target Tracking by a Mobile Receiver with Unknown Transmitter Position

In this paper, we propose a radio-based passive target tracking algorithm using multipath measurements, including the angle of arrival and relative distance. We focus on a scenario in which a mobile receiver continuously receives radio signals from a transmitter located at an unknown position. The receiver utilizes multipath measurements extracted from the received signal to jointly localize the transmitter and the scatterers over time, with scatterers comprising a moving target and stationary objects that can reflect signals within the environment. We develop a comprehensive probabilistic model for the target tracking problem, incorporating the localization of the transmitter and scatterers, the identification of false alarms and missed detections in the measurements, and the association between scatterers and measurements. We employ a belief propagation approach to compute the posterior distributions of the positions of the scatterers and the transmitter. Additionally, we introduce a particle implementation for the belief propagation method. Simulation results demonstrate that our proposed algorithm outperforms existing benchmark methods in terms of target tracking accuracy.

eess.SP↗

arXiv2024

Near-Field Multiuser Communications Aided by Movable Antennas

This letter investigates movable antenna (MA)-aided downlink (DL) multiuser communication systems under the near-field channel condition, where both the base station (BS) and the users are equipped with MAs to fully exploit the degrees of freedom (DoFs) in antenna position optimization. We develop a general channel model to accurately describe the channel characteristics in the near-field region and formulate an MA-position optimization problem to minimize the BS's transmit power subject to users' individual rate constraints. To solve this problem, we propose a two-loop dynamic neighborhood pruning particle swarm optimization (DNPPSO) algorithm that significantly reduces the computational complexity as compared to the standard particle swarm optimization (PSO) algorithm while achieving similar performance. Simulation results validate the effectiveness and advantages of the proposed scheme in power-saving for near-field multiuser communications.

eess.SP↗

arXiv2024

Interpretable Differential Diagnosis with Dual-Inference Large Language Models

Automatic differential diagnosis (DDx) is an essential medical task that generates a list of potential diseases as differentials based on patient symptom descriptions. In practice, interpreting these differential diagnoses yields significant value but remains under-explored. Given the powerful capabilities of large language models (LLMs), we investigated using LLMs for interpretable DDx. Specifically, we curated the first DDx dataset with expert-derived interpretation on 570 clinical notes. Besides, we proposed Dual-Inf, a novel framework that enabled LLMs to conduct bidirectional inference (i.e., from symptoms to diagnoses and vice versa) for DDx interpretation. Both human and automated evaluation validated its efficacy in predicting and elucidating differentials across four base LLMs. In addition, Dual-Inf could reduce interpretation errors and hold promise for rare disease explanations. To the best of our knowledge, it is the first work that customizes LLMs for DDx explanation and comprehensively evaluates their interpretation performance. Overall, our study bridges a critical gap in DDx interpretation and enhances clinical decision-making.

cs.CL↗

arXiv2024

Multi-Layer Perceptron for Predicting Galaxy Parameters (MLP-GaP): stellar masses and star formation rates

The large-scale imaging survey will produce massive photometric data in multi-bands for billions of galaxies. Defining strategies to quickly and efficiently extract useful physical information from this data is mandatory. Among the stellar population parameters for galaxies, their stellar masses and star formation rates (SFRs) are the most fundamental. We develop a novel tool, \textit{Multi-Layer Perceptron for Predicting Galaxy Parameters} (MLP-GaP), that uses a machine-learning (ML) algorithm to accurately and efficiently derive the stellar masses and SFRs from multi-band catalogs. We first adopt a mock dataset generated by the \textit{Code Investigating GALaxy Emission} (CIGALE) for training and testing datasets. Subsequently, we used a multi-layer perceptron model to build MLP-GaP and effectively trained it with the training dataset. The results of the test performed on the mock dataset show that MLP-GaP can accurately predict the reference values. Besides MLP-GaP has a significantly faster processing speed than CIGALE. To demonstrate the science-readiness of the MLP-GaP, we also apply it to a real data sample and compare the stellar masses and SFRs with CIGALE. Overall, the predicted values of MLP-GaP show a very good consistency with the estimated values derived from SED fitting. Therefore, the capability of MLP-GaP to rapidly and accurately predict stellar masses and SFRs makes it particularly well-suited for analyzing huge amounts of galaxies in the era of large sky surveys.

astro-ph.GA↗

arXiv2024

Deep Graph Neural Networks via Posteriori-Sampling-based Node-Adaptive Residual Module

Graph Neural Networks (GNNs), a type of neural network that can learn from graph-structured data through neighborhood information aggregation, have shown superior performance in various downstream tasks. However, as the number of layers increases, node representations become indistinguishable, which is known as over-smoothing. To address this issue, many residual methods have emerged. In this paper, we focus on the over-smoothing issue and related residual methods. Firstly, we revisit over-smoothing from the perspective of overlapping neighborhood subgraphs, and based on this, we explain how residual methods can alleviate over-smoothing by integrating multiple orders neighborhood subgraphs to avoid the indistinguishability of the single high-order neighborhood subgraphs. Additionally, we reveal the drawbacks of previous residual methods, such as the lack of node adaptability and severe loss of high-order neighborhood subgraph information, and propose a \textbf{Posterior-Sampling-based, Node-Adaptive Residual module (PSNR)}. We theoretically demonstrate that PSNR can alleviate the drawbacks of previous residual methods. Furthermore, extensive experiments verify the superiority of the PSNR module in fully observed node classification and missing feature scenarios. Our code is available at https://github.com/jingbo02/PSNR-GNN.

cs.LG↗

arXiv2024

QCD Predictions for Meson Electromagnetic Form Factors at High Momenta: Testing Factorization in Exclusive Processes

We report the first lattice QCD computation of pion and kaon electromagnetic form factors, $F_M(Q^2)$, at large momentum transfer up to 10 and 28 $\mathrm{GeV}^2$, respectively. Utilizing physical masses and two fine lattices, we achieve good agreement with JLab experimental results at $Q^2 \lesssim 4~\mathrm{GeV}^2$. For $Q^2 \gtrsim 4~\mathrm{GeV}^2$, our results provide $\textit{ab-initio}$ QCD benchmarks for the forthcoming experiments at JLab 12 GeV and future electron-ion colliders. We also test the QCD collinear factorization framework utilizing our high-$Q^2$ form factors at next-to-next-to-leading order in perturbation theory, which relates the form factors to the leading Fock-state meson distribution amplitudes. Comparisons with independent lattice QCD calculations using the same framework demonstrate, within estimated uncertainties, the universality of these nonperturbative quantities.

hep-lat↗

arXiv2024

Multi-IRS Enhanced Wireless Coverage: Deployment Optimization Based on Large-Scale Channel Knowledge

In this paper, we study the intelligent reflecting surface (IRS) deployment problem where a number of IRSs are optimally placed in a target area to improve its signal coverage with the serving base station (BS). To achieve this, we assume that there is a given set of candidate sites in the target area for deploying IRSs and divide the area into multiple grids of identical size. Then, we derive the average channel power gains from the BS to IRS in each candidate site and from this IRS to any grid in the target area in terms of IRS deployment parameters, including its size, position, height, and orientation. Thus, we are able to approximate the average cascaded channel power gain from the BS to each grid via any IRS, assuming an effective IRS reflection gain based on the large-scale channel knowledge only. Next, we formulate a multi-IRS deployment optimization problem to minimize the total deployment cost by selecting a subset of candidate sites for deploying IRSs and jointly optimizing their heights, orientations, and numbers of reflecting elements while satisfying a given coverage rate performance requirement over all grids in the target area. To solve this challenging combinatorial optimization problem, we first reformulate it as an integer linear programming problem and solve it optimally using the branch-and-bound (BB) algorithm. In addition, we propose an efficient successive refinement algorithm to further reduce computational complexity. Simulation results demonstrate that the proposed lower-complexity successive refinement algorithm achieves near-optimal performance but with significantly reduced running time compared to the proposed optimal BB algorithm, as well as superior performance-cost trade-off than other baseline IRS deployment strategies.

eess.SP↗