arXiv subjects

Lei Wang

Publications and source records attributed to Lei Wang.

At least 631 records · Page 35Linked to original sources

arXiv2024

AUEditNet: Dual-Branch Facial Action Unit Intensity Manipulation with Implicit Disentanglement

Facial action unit (AU) intensity plays a pivotal role in quantifying fine-grained expression behaviors, which is an effective condition for facial expression manipulation. However, publicly available datasets containing intensity annotations for multiple AUs remain severely limited, often featuring a restricted number of subjects. This limitation places challenges to the AU intensity manipulation in images due to disentanglement issues, leading researchers to resort to other large datasets with pretrained AU intensity estimators for pseudo labels. In addressing this constraint and fully leveraging manual annotations of AU intensities for precise manipulation, we introduce AUEditNet. Our proposed model achieves impressive intensity manipulation across 12 AUs, trained effectively with only 18 subjects. Utilizing a dual-branch architecture, our approach achieves comprehensive disentanglement of facial attributes and identity without necessitating additional loss functions or implementing with large batch sizes. This approach offers a potential solution to achieve desired facial attribute editing despite the dataset's limited subject count. Our experiments demonstrate AUEditNet's superior accuracy in editing AU intensities, affirming its capability in disentangling facial attributes and identity within a limited subject pool. AUEditNet allows conditioning by either intensity values or target images, eliminating the need for constructing AU combinations for specific facial expression synthesis. Moreover, AU intensity estimation, as a downstream task, validates the consistency between real and edited images, confirming the effectiveness of our proposed AU intensity manipulation method.

cs.CV↗

arXiv2024

ONNXPruner: ONNX-Based General Model Pruning Adapter

Recent advancements in model pruning have focused on developing new algorithms and improving upon benchmarks. However, the practical application of these algorithms across various models and platforms remains a significant challenge. To address this challenge, we propose ONNXPruner, a versatile pruning adapter designed for the ONNX format models. ONNXPruner streamlines the adaptation process across diverse deep learning frameworks and hardware platforms. A novel aspect of ONNXPruner is its use of node association trees, which automatically adapt to various model architectures. These trees clarify the structural relationships between nodes, guiding the pruning process, particularly highlighting the impact on interconnected nodes. Furthermore, we introduce a tree-level evaluation method. By leveraging node association trees, this method allows for a comprehensive analysis beyond traditional single-node evaluations, enhancing pruning performance without the need for extra operations. Experiments across multiple models and datasets confirm ONNXPruner's strong adaptability and increased efficacy. Our work aims to advance the practical application of model pruning.

cs.LG↗

arXiv2024

Large Eddy Simulations of Turbulent Pipe Flows At Moderate-To-High Reynolds Numbers

Wall-bounded turbulence is relevant for many engineering and natural science applications, yet there are still aspects of its underlying physics that are not fully understood, particularly at high Reynolds numbers. In this study, we investigate fully-developed turbulent pipe flows at moderate-to-high friction velocity Reynolds numbers ($361 \leq Re_τ \leq 2,000$), corresponding to bulk velocity-based Reynolds numbers of $11,700 \leq Re_{b} \leq 82,500$, using wall-modeled Large Eddy Simulations (LES) in OpenFOAM. A grid convergence study is performed for $Re_τ = 361$, followed by an investigation of the accuracy of various subgrid-scale stress models for the same Reynolds number. Results show that the Wall-Adapting Local Eddy (WALE) model performs well compared to experiments and Direct Numerical Simulations (DNS), while One-Equation Eddy-Viscosity Model (OEEVM) and Smagorinsky (SMG) are too dissipative. LES utilizing WALE are then performed for four different Reynolds numbers with gradually refined grids, revealing excellent agreement with DNS data in the outer region. However, a significant deviation from DNS data is observed in the sub-viscous layer region, indicating the need for further mesh refinement in the wall-normal direction to accurately capture the smallest-scale motions' behavior. Additional mesh sensitivity analysis uncovered that, as the $Re_τ$ value rises, it becomes crucial for a grid to adhere to the condition of $Δx^{+} \leq 20 - 25$ and $Δz^{+} \leq 10$ in order to precisely capture substantial large and small scale fluctuations. Overall, the WALE model enables accurate numerical simulations of high-Reynolds-number, wall-bounded flows at a fraction of the computational cost required for temporal and spatial resolution of the inner layer.

physics.flu-dyn↗

arXiv2024

Phase-field based lattice Boltzmann method for containerless freezing

In this paper, a lattice Boltzmann model is proposed to simulate solid-liquid phase change phenomena in multiphase systems. The model couples the thermal properties of the solidification front with the dynamics of the liquid droplet interface, which enables the description of the complex interfacial changes during solid-liquid phase change process. The model treats the interfaces of gas, liquid, and solid phases using the phase field order parameter and the solid fraction. The volume expansion or contraction caused by the change of properties such as density during phase change is represented by adding a mass source term to the continuum equation. The proposed model is first validated by the three-phase Stefan problem and the droplet solidification on a cold surface, and the numerical results are in good agreement with the analytical and experimental results. Then it is used to model the solidification problem with bubbles. The results show that the model is able to accurately capture the effect of bubbles on the solidification process, which is in good agreement with previous work. In addition, a parametric study is carried out to examine the dependence of the sessile droplet solidification on different physical and numerical parameters. The results show that the droplet solidification time increases with increasing droplet volume and contact angle.

physics.flu-dyn↗

arXiv2024

YAYI-UIE: A Chat-Enhanced Instruction Tuning Framework for Universal Information Extraction

The difficulty of the information extraction task lies in dealing with the task-specific label schemas and heterogeneous data structures. Recent work has proposed methods based on large language models to uniformly model different information extraction tasks. However, these existing methods are deficient in their information extraction capabilities for Chinese languages other than English. In this paper, we propose an end-to-end chat-enhanced instruction tuning framework for universal information extraction (YAYI-UIE), which supports both Chinese and English. Specifically, we utilize dialogue data and information extraction data to enhance the information extraction performance jointly. Experimental results show that our proposed framework achieves state-of-the-art performance on Chinese datasets while also achieving comparable performance on English datasets under both supervised settings and zero-shot settings.

cs.CL↗

arXiv2024

All in an Aggregated Image for In-Image Learning

This paper introduces a new in-context learning (ICL) mechanism called In-Image Learning (I$^2$L) that combines demonstration examples, visual cues, and chain-of-thought reasoning into an aggregated image to enhance the capabilities of Large Multimodal Models (e.g., GPT-4V) in multimodal reasoning tasks. Unlike previous approaches that rely on converting images to text or incorporating visual input into language models, I$^2$L consolidates all information into an aggregated image and leverages image processing, understanding, and reasoning abilities. This has several advantages: it reduces inaccurate textual descriptions of complex images, provides flexibility in positioning demonstration examples, and avoids multiple input images and lengthy prompts. We also introduce I$^2$L-Hybrid, a method that combines the strengths of I$^2$L with other ICL methods. Specifically, it uses an automatic strategy to select the most suitable method (I$^2$L or another certain ICL method) for a specific task instance. We conduct extensive experiments to assess the effectiveness of I$^2$L and I$^2$L-Hybrid on MathVista, which covers a variety of complex multimodal reasoning tasks. Additionally, we investigate the influence of image resolution, the number of demonstration examples in a single image, and the positions of these demonstrations in the aggregated image on the effectiveness of I$^2$L. Our code is publicly available at https://github.com/AGI-Edgerunners/IIL.

cs.CV↗

arXiv2024

CSST Strong Lensing Preparation: a Framework for Detecting Strong Lenses in the Multi-color Imaging Survey by the China Survey Space Telescope (CSST)

Strong gravitational lensing is a powerful tool for investigating dark matter and dark energy properties. With the advent of large-scale sky surveys, we can discover strong lensing systems on an unprecedented scale, which requires efficient tools to extract them from billions of astronomical objects. The existing mainstream lens-finding tools are based on machine learning algorithms and applied to cut-out-centered galaxies. However, according to the design and survey strategy of optical surveys by CSST, preparing cutouts with multiple bands requires considerable efforts. To overcome these challenges, we have developed a framework based on a hierarchical visual Transformer with a sliding window technique to search for strong lensing systems within entire images. Moreover, given that multi-color images of strong lensing systems can provide insights into their physical characteristics, our framework is specifically crafted to identify strong lensing systems in images with any number of channels. As evaluated using CSST mock data based on an Semi-Analytic Model named CosmoDC2, our framework achieves precision and recall rates of 0.98 and 0.90, respectively. To evaluate the effectiveness of our method in real observations, we have applied it to a subset of images from the DESI Legacy Imaging Surveys and media images from Euclid Early Release Observations. 61 new strong lensing system candidates are discovered by our method. However, we also identified false positives arising primarily from the simplified galaxy morphology assumptions within the simulation. This underscores the practical limitations of our approach while simultaneously highlighting potential avenues for future improvements.

astro-ph.IM↗

arXiv2024

Constructing Cross-lingual Consumer Health Vocabulary with Word-Embedding from Comparable User Generated Content

The online health community (OHC) is the primary channel for laypeople to share health information. To analyze the health consumer-generated content (HCGC) from the OHCs, identifying the colloquial medical expressions used by laypeople is a critical challenge. The open-access and collaborative consumer health vocabulary (OAC CHV) is the controlled vocabulary for addressing such a challenge. Nevertheless, OAC CHV is only available in English, limiting its applicability to other languages. This research proposes a cross-lingual automatic term recognition framework for extending the English CHV into a cross-lingual one. Our framework requires an English HCGC corpus and a non-English (i.e., Chinese in this study) HCGC corpus as inputs. Two monolingual word vector spaces are determined using the skip-gram algorithm so that each space encodes common word associations from laypeople within a language. Based on the isometry assumption, the framework aligns two monolingual spaces into a bilingual word vector space, where we employ cosine similarity as a metric for identifying semantically similar words across languages. The experimental results demonstrate that our framework outperforms the other two large language models in identifying CHV across languages. Our framework only requires raw HCGC corpora and a limited size of medical translations, reducing human efforts in compiling cross-lingual CHV.

cs.CL↗

arXiv2024

Exploiting Inter-sample and Inter-feature Relations in Dataset Distillation

Dataset distillation has emerged as a promising approach in deep learning, enabling efficient training with small synthetic datasets derived from larger real ones. Particularly, distribution matching-based distillation methods attract attention thanks to its effectiveness and low computational cost. However, these methods face two primary limitations: the dispersed feature distribution within the same class in synthetic datasets, reducing class discrimination, and an exclusive focus on mean feature consistency, lacking precision and comprehensiveness. To address these challenges, we introduce two novel constraints: a class centralization constraint and a covariance matching constraint. The class centralization constraint aims to enhance class discrimination by more closely clustering samples within classes. The covariance matching constraint seeks to achieve more accurate feature distribution matching between real and synthetic datasets through local feature covariance matrices, particularly beneficial when sample sizes are much smaller than the number of features. Experiments demonstrate notable improvements with these constraints, yielding performance boosts of up to 6.6% on CIFAR10, 2.9% on SVHN, 2.5% on CIFAR100, and 2.5% on TinyImageNet, compared to the state-of-the-art relevant methods. In addition, our method maintains robust performance in cross-architecture settings, with a maximum performance drop of 1.7% on four architectures. Code is available at https://github.com/VincenDen/IID.

cs.CV↗

arXiv2024

PCToolkit: A Unified Plug-and-Play Prompt Compression Toolkit of Large Language Models

Prompt compression is an innovative method for efficiently condensing input prompts while preserving essential information. To facilitate quick-start services, user-friendly interfaces, and compatibility with common datasets and metrics, we present the Prompt Compression Toolkit (PCToolkit). This toolkit is a unified plug-and-play solution for compressing prompts in Large Language Models (LLMs), featuring cutting-edge prompt compressors, diverse datasets, and metrics for comprehensive performance evaluation. PCToolkit boasts a modular design, allowing for easy integration of new datasets and metrics through portable and user-friendly interfaces. In this paper, we outline the key components and functionalities of PCToolkit. We conducted evaluations of the compressors within PCToolkit across various natural language tasks, including reconstruction, summarization, mathematical problem-solving, question answering, few-shot learning, synthetic tasks, code completion, boolean expressions, multiple choice questions, and lies recognition.

cs.CL↗

arXiv2024

Meet JEANIE: a Similarity Measure for 3D Skeleton Sequences via Temporal-Viewpoint Alignment

Video sequences exhibit significant nuisance variations (undesired effects) of speed of actions, temporal locations, and subjects' poses, leading to temporal-viewpoint misalignment when comparing two sets of frames or evaluating the similarity of two sequences. Thus, we propose Joint tEmporal and cAmera viewpoiNt alIgnmEnt (JEANIE) for sequence pairs. In particular, we focus on 3D skeleton sequences whose camera and subjects' poses can be easily manipulated in 3D. We evaluate JEANIE on skeletal Few-shot Action Recognition (FSAR), where matching well temporal blocks (temporal chunks that make up a sequence) of support-query sequence pairs (by factoring out nuisance variations) is essential due to limited samples of novel classes. Given a query sequence, we create its several views by simulating several camera locations. For a support sequence, we match it with view-simulated query sequences, as in the popular Dynamic Time Warping (DTW). Specifically, each support temporal block can be matched to the query temporal block with the same or adjacent (next) temporal index, and adjacent camera views to achieve joint local temporal-viewpoint warping. JEANIE selects the smallest distance among matching paths with different temporal-viewpoint warping patterns, an advantage over DTW which only performs temporal alignment. We also propose an unsupervised FSAR akin to clustering of sequences with JEANIE as a distance measure. JEANIE achieves state-of-the-art results on NTU-60, NTU-120, Kinetics-skeleton and UWA3D Multiview Activity II on supervised and unsupervised FSAR, and their meta-learning inspired fusion.

cs.CV↗

arXiv2024

Forklens: Accurate weak-lensing shear measurement with deep learning

Weak gravitational lensing is one of the most important probes of the nature of dark matter and dark energy. In order to extract cosmological information from next-generation weak lensing surveys (e.g., Euclid, Roman, LSST, and CSST) as much as possible, accurate measurements of weak lensing shear are required. There are existing algorithms to measure the weak lensing shear on imaging data, which have been successfully applied in previous surveys. In the meantime, machine learning (ML) has been widely recognized in various astrophysics applications in modeling and observations. In this work, we present a fully deep-learning-based approach to measuring weak lensing shear accurately. Our approach comprises two modules. The first one contains a convolutional neural network (CNN) with two branches for taking galaxy images and point spread function (PSF) simultaneously, and the output of this module includes the galaxy's magnitude, size, and shape. The second module includes a multiple-layer neural network (NN) to calibrate weak-lensing shear measurements. We name the program Forklens and make it publicly available online. Applying Forklens to CSST-like mock images, we achieve consistent accuracy with traditional approaches (such as moment-based measurement and forward model fitting) on the sources with high signal-to-noise ratios (S/N, > 20). For the sources with S/N < 10, Forklens exhibits an $\sim 36\%$ higher Pearson coefficient on galaxy ellipticity measurements. After adopting galaxy weighting, the shear measurements with Forklens deliver accuracy levels to $0.2\%$. The whole procedure of Forklens is automated and costs about $0.7$ milliseconds per galaxy, which is appropriate for adequately taking advantage of the sky coverage and depth of the upcoming weak lensing surveys.

astro-ph.CO↗

arXiv2024

Measurement of the earth tides with a diamagnetic-levitated micro-oscillator at room temperature

The precise measurement of the gravity of the earth plays a pivotal role in various fundamental research and application fields. Although a few gravimeters have been reported to achieve this goal, miniaturization of high-precision gravimetry remains a challenge. In this work, we have proposed and demonstrated a miniaturized gravimetry operating at room temperature based on a diamagnetic levitated micro-oscillator with a proof mass of only 215 mg. Compared with the latest reported miniaturized gravimeters based on Micro-Electro-Mechanical Systems, the performance of our gravimetry has substantial improvements in that an acceleration sensitivity of 15 $μGal/\sqrt{Hz}$ and a drift as low as 61 $μGal$ per day have been reached. Based on this diamagnetic levitation gravimetry, we observed the earth tides, and the correlation coefficient between the experimental data and theoretical data reached 0.97. Some moderate foreseeable improvements can develop this diamagnetic levitation gravimetry into chip size device, making it suitable for mobile platforms such as drones. Our advancement in gravimetry is expected to facilitate a multitude of applications, including underground density surveying and the forecasting of natural hazards.

physics.app-ph↗

arXiv2024

View-decoupled Transformer for Person Re-identification under Aerial-ground Camera Network

Existing person re-identification methods have achieved remarkable advances in appearance-based identity association across homogeneous cameras, such as ground-ground matching. However, as a more practical scenario, aerial-ground person re-identification (AGPReID) among heterogeneous cameras has received minimal attention. To alleviate the disruption of discriminative identity representation by dramatic view discrepancy as the most significant challenge in AGPReID, the view-decoupled transformer (VDT) is proposed as a simple yet effective framework. Two major components are designed in VDT to decouple view-related and view-unrelated features, namely hierarchical subtractive separation and orthogonal loss, where the former separates these two features inside the VDT, and the latter constrains these two to be independent. In addition, we contribute a large-scale AGPReID dataset called CARGO, consisting of five/eight aerial/ground cameras, 5,000 identities, and 108,563 images. Experiments on two datasets show that VDT is a feasible and effective solution for AGPReID, surpassing the previous method on mAP/Rank1 by up to 5.0%/2.7% on CARGO and 3.7%/5.2% on AG-ReID, keeping the same magnitude of computational complexity. Our project is available at https://github.com/LinlyAC/VDT-AGPReID

cs.CV↗

arXiv2024

Evaluatology: The Science and Engineering of Evaluation

Evaluation is a crucial aspect of human existence and plays a vital role in various fields. However, it is often approached in an empirical and ad-hoc manner, lacking consensus on universal concepts, terminologies, theories, and methodologies. This lack of agreement has significant repercussions. This article aims to formally introduce the discipline of evaluatology, which encompasses the science and engineering of evaluation. We propose a universal framework for evaluation, encompassing concepts, terminologies, theories, and methodologies that can be applied across various disciplines. Our research reveals that the essence of evaluation lies in conducting experiments that intentionally apply a well-defined evaluation condition to diverse subjects and infer the impact of different subjects by measuring and/or testing. Derived from the essence of evaluation, we propose five axioms focusing on key aspects of evaluation outcomes as the foundational evaluation theory. These axioms serve as the bedrock upon which we build universal evaluation theories and methodologies. When evaluating a single subject, it is crucial to create evaluation conditions with different levels of equivalency. By applying these conditions to diverse subjects, we can establish reference evaluation models. These models allow us to alter a single independent variable at a time while keeping all other variables as controls. When evaluating complex scenarios, the key lies in establishing a series of evaluation models that maintain transitivity. Building upon the science of evaluation, we propose a formal definition of a benchmark as a simplified and sampled evaluation condition that guarantees different levels of equivalency. This concept serves as the cornerstone for a universal benchmark-based engineering approach to evaluation across various disciplines, which we refer to as benchmarkology.

cs.HC↗

arXiv2024

The Whole is Better than the Sum: Using Aggregated Demonstrations in In-Context Learning for Sequential Recommendation

Large language models (LLMs) have shown excellent performance on various NLP tasks. To use LLMs as strong sequential recommenders, we explore the in-context learning approach to sequential recommendation. We investigate the effects of instruction format, task consistency, demonstration selection, and number of demonstrations. As increasing the number of demonstrations in ICL does not improve accuracy despite using a long prompt, we propose a novel method called LLMSRec-Syn that incorporates multiple demonstration users into one aggregated demonstration. Our experiments on three recommendation datasets show that LLMSRec-Syn outperforms state-of-the-art LLM-based sequential recommendation methods. In some cases, LLMSRec-Syn can perform on par with or even better than supervised learning methods. Our code is publicly available at https://github.com/demoleiwang/LLMSRec_Syn.

cs.IR↗

arXiv2024

Gradient-Aware Logit Adjustment Loss for Long-tailed Classifier

In the real-world setting, data often follows a long-tailed distribution, where head classes contain significantly more training samples than tail classes. Consequently, models trained on such data tend to be biased toward head classes. The medium of this bias is imbalanced gradients, which include not only the ratio of scale between positive and negative gradients but also imbalanced gradients from different negative classes. Therefore, we propose the Gradient-Aware Logit Adjustment (GALA) loss, which adjusts the logits based on accumulated gradients to balance the optimization process. Additionally, We find that most of the solutions to long-tailed problems are still biased towards head classes in the end, and we propose a simple and post hoc prediction re-balancing strategy to further mitigate the basis toward head class. Extensive experiments are conducted on multiple popular long-tailed recognition benchmark datasets to evaluate the effectiveness of these two designs. Our approach achieves top-1 accuracy of 48.5\%, 41.4\%, and 73.3\% on CIFAR100-LT, Places-LT, and iNaturalist, outperforming the state-of-the-art method GCL by a significant margin of 3.62\%, 0.76\% and 1.2\%, respectively. Code is available at https://github.com/lt-project-repository/lt-project.

cs.CV↗

arXiv2024

Chaotic Masking Protocol for Secure Communication and Attack Detection in Remote Estimation of Cyber-Physical Systems

In remote estimation of cyber-physical systems (CPSs), sensor measurements transmitted through network may be attacked by adversaries, leading to leakage risk of privacy (e.g., the system state), and/or failure of the remote estimator. To deal with this problem, a chaotic masking protocol is proposed in this paper to secure the sensor measurements transmission. In detail, at the plant side, a chaotic dynamic system is deployed to encode the sensor measurement, and at the estimator side, an estimator estimates both states of the physical plant and the chaotic system. With this protocol, no additional secure communication links is needed for synchronization, and the masking effect can be perfectly removed when the estimator is in steady state. Furthermore, this masking protocol can deal with multiple types of attacks, i.e., eavesdropping attack, replay attack, and stealthy false data injection attack.

eess.SY↗