arXiv subjects

Wei Sun

Publications and source records attributed to Wei Sun.

At least 181 records · Page 10Linked to original sources

arXiv2024

Addition is All You Need for Energy-efficient Language Models

Large neural networks spend most computation on floating point tensor multiplications. In this work, we find that a floating point multiplier can be approximated by one integer adder with high precision. We propose the linear-complexity multiplication L-Mul algorithm that approximates floating point number multiplication with integer addition operations. The new algorithm costs significantly less computation resource than 8-bit floating point multiplication but achieves higher precision. Compared to 8-bit floating point multiplications, the proposed method achieves higher precision but consumes significantly less bit-level computation. Since multiplying floating point numbers requires substantially higher energy compared to integer addition operations, applying the L-Mul operation in tensor processing hardware can potentially reduce 95% energy cost by element-wise floating point tensor multiplications and 80% energy cost of dot products. We calculated the theoretical error expectation of L-Mul, and evaluated the algorithm on a wide range of textual, visual, and symbolic tasks, including natural language understanding, structural reasoning, mathematics, and commonsense question answering. Our numerical analysis experiments agree with the theoretical error estimation, which indicates that L-Mul with 4-bit mantissa achieves comparable precision as float8_e4m3 multiplications, and L-Mul with 3-bit mantissa outperforms float8_e5m2. Evaluation results on popular benchmarks show that directly applying L-Mul to the attention mechanism is almost lossless. We further show that replacing all floating point multiplications with 3-bit mantissa L-Mul in a transformer model achieves equivalent precision as using float8_e4m3 as accumulation precision in both fine-tuning and inference.

cs.CL↗

arXiv2024

Deep Learning Based 3D Segmentation: A Survey

3D segmentation is a fundamental and challenging problem in computer vision with applications in autonomous driving and robotics. It has received significant attention from the computer vision, graphics and machine learning communities. Conventional methods for 3D segmentation, based on hand-crafted features and machine learning classifiers, lack generalization ability. Driven by their success in 2D computer vision, deep learning techniques have recently become the tool of choice for 3D segmentation tasks. This has led to an influx of many methods in the literature that have been evaluated on different benchmark datasets. Whereas survey papers on RGB-D and point cloud segmentation exist, there is a lack of a recent in-depth survey that covers all 3D data modalities and application domains. This paper fills the gap and comprehensively surveys the recent progress in deep learning-based 3D segmentation techniques. We cover over 220 works from the last six years, analyze their strengths and limitations, and discuss their competitive results on benchmark datasets. The survey provides a summary of the most commonly used pipelines and finally highlights promising research directions for the future.

cs.CV↗

arXiv2024

Bilateral boundary finite-time stabilization of 2x2 linear first-order hyperbolic systems with spatially varying coefficients

This paper presents bilateral control laws for one-dimensional(1-D) linear 2x2 hyperbolic first-order systems (with spatially varying coefficients). Bilateral control means there are two actuators at each end of the domain. This situation becomes more complex as the transport velocities are no longer constant, and this extension is nontrivial. By selecting the appropriate backstepping transformation and target system, the infinite-dimensional backstepping method is extended and a full-state feedback control law is given that ensures the closed-loop system converges to its zero equilibrium in finite time. The design of bilateral controllers enables a potential for fault-tolerant designs.

math.OC↗

arXiv2024

Assessing UHD Image Quality from Aesthetics, Distortions, and Saliency

UHD images, typically with resolutions equal to or higher than 4K, pose a significant challenge for efficient image quality assessment (IQA) algorithms, as adopting full-resolution images as inputs leads to overwhelming computational complexity and commonly used pre-processing methods like resizing or cropping may cause substantial loss of detail. To address this problem, we design a multi-branch deep neural network (DNN) to assess the quality of UHD images from three perspectives: global aesthetic characteristics, local technical distortions, and salient content perception. Specifically, aesthetic features are extracted from low-resolution images downsampled from the UHD ones, which lose high-frequency texture information but still preserve the global aesthetics characteristics. Technical distortions are measured using a fragment image composed of mini-patches cropped from UHD images based on the grid mini-patch sampling strategy. The salient content of UHD images is detected and cropped to extract quality-aware features from the salient regions. We adopt the Swin Transformer Tiny as the backbone networks to extract features from these three perspectives. The extracted features are concatenated and regressed into quality scores by a two-layer multi-layer perceptron (MLP) network. We employ the mean square error (MSE) loss to optimize prediction accuracy and the fidelity loss to optimize prediction monotonicity. Experimental results show that the proposed model achieves the best performance on the UHD-IQA dataset while maintaining the lowest computational complexity, demonstrating its effectiveness and efficiency. Moreover, the proposed model won first prize in ECCV AIM 2024 UHD-IQA Challenge. The code is available at https://github.com/sunwei925/UIQA.

cs.CV↗

arXiv2024

LMM-VQA: Advancing Video Quality Assessment with Large Multimodal Models

The explosive growth of videos on streaming media platforms has underscored the urgent need for effective video quality assessment (VQA) algorithms to monitor and perceptually optimize the quality of streaming videos. However, VQA remains an extremely challenging task due to the diverse video content and the complex spatial and temporal distortions, thus necessitating more advanced methods to address these issues. Nowadays, large multimodal models (LMMs), such as GPT-4V, have exhibited strong capabilities for various visual understanding tasks, motivating us to leverage the powerful multimodal representation ability of LMMs to solve the VQA task. Therefore, we propose the first Large Multi-Modal Video Quality Assessment (LMM-VQA) model, which introduces a novel spatiotemporal visual modeling strategy for quality-aware feature extraction. Specifically, we first reformulate the quality regression problem into a question and answering (Q&A) task and construct Q&A prompts for VQA instruction tuning. Then, we design a spatiotemporal vision encoder to extract spatial and temporal features to represent the quality characteristics of videos, which are subsequently mapped into the language space by the spatiotemporal projector for modality alignment. Finally, the aligned visual tokens and the quality-inquired text tokens are aggregated as inputs for the large language model (LLM) to generate the quality score and level. Extensive experiments demonstrate that LMM-VQA achieves state-of-the-art performance across five VQA benchmarks, exhibiting an average improvement of $5\%$ in generalization ability over existing methods. Furthermore, due to the advanced design of the spatiotemporal encoder and projector, LMM-VQA also performs exceptionally well on general video understanding tasks, further validating its effectiveness. Our code will be released at https://github.com/Sueqk/LMM-VQA.

cs.CV↗

arXiv2024

$X(3872)$ Relevant $D\bar{D}^*$ Scattering in $N_f=2$ Lattice QCD

We study the $S$-wave $D\bar{D}^*(I=0)$ scattering at four different pion masses $m_π$ ranging from 250 MeV to 417 MeV from $N_f=2$ lattice QCD. Three energy levels $E_{2,3,4}$ are extracted at each $m_π$. The analysis of $E_{2,3}$ using the effective range expansion (ERE) comes out with a shallow bound state below the $D\bar{D}^*$ threshold, and the phase shifts at $E_{3,4}$ indicate the possible existence of a resonance near 4.0 GeV. We also perform a joint analysis to $E_{2,3,4}$ through the $K$-matrix parameterization of the scattering amplitude. In this way, we observe a $D\bar{D}^*$ bound state whose properties are almost the same as that from the ERE analysis. At each $m_π$, this joint analysis also results in a resonance pole with a mass slightly above 4.0 GeV and a width around 40-60 MeV, which are compatible with the properties of the newly observed $χ_{c1}(4010)$ by LHCb. More scrutinized lattice QCD calculations are desired to check the existence of this resonance.

hep-lat↗

arXiv2024

Depth-guided Texture Diffusion for Image Semantic Segmentation

Depth information provides valuable insights into the 3D structure especially the outline of objects, which can be utilized to improve the semantic segmentation tasks. However, a naive fusion of depth information can disrupt feature and compromise accuracy due to the modality gap between the depth and the vision. In this work, we introduce a Depth-guided Texture Diffusion approach that effectively tackles the outlined challenge. Our method extracts low-level features from edges and textures to create a texture image. This image is then selectively diffused across the depth map, enhancing structural information vital for precisely extracting object outlines. By integrating this enriched depth map with the original RGB image into a joint feature embedding, our method effectively bridges the disparity between the depth map and the image, enabling more accurate semantic segmentation. We conduct comprehensive experiments across diverse, commonly-used datasets spanning a wide range of semantic segmentation tasks, including Camouflaged Object Detection (COD), Salient Object Detection (SOD), and indoor semantic segmentation. With source-free estimated depth or depth captured by depth cameras, our method consistently outperforms existing baselines and achieves new state-of-theart results, demonstrating the effectiveness of our Depth-guided Texture Diffusion for image semantic segmentation.

cs.CV↗

arXiv2024

Correspondence-Guided SfM-Free 3D Gaussian Splatting for NVS

Novel View Synthesis (NVS) without Structure-from-Motion (SfM) pre-processed camera poses--referred to as SfM-free methods--is crucial for promoting rapid response capabilities and enhancing robustness against variable operating conditions. Recent SfM-free methods have integrated pose optimization, designing end-to-end frameworks for joint camera pose estimation and NVS. However, most existing works rely on per-pixel image loss functions, such as L2 loss. In SfM-free methods, inaccurate initial poses lead to misalignment issue, which, under the constraints of per-pixel image loss functions, results in excessive gradients, causing unstable optimization and poor convergence for NVS. In this study, we propose a correspondence-guided SfM-free 3D Gaussian splatting for NVS. We use correspondences between the target and the rendered result to achieve better pixel alignment, facilitating the optimization of relative poses between frames. We then apply the learned poses to optimize the entire scene. Each 2D screen-space pixel is associated with its corresponding 3D Gaussians through approximated surface rendering to facilitate gradient back propagation. Experimental results underline the superior performance and time efficiency of the proposed approach compared to the state-of-the-art baselines.

cs.CV↗

arXiv2024

Nanometric dual-comb ranging using photon-level microcavity solitons

Absolute distance measurement with low return power, fast measurement speed, high precision, and immunity to intensity fluctuations is highly demanded in nanotechnology. However, achieving all these objectives simultaneously remains a significant challenge for miniaturized systems. Here, we demonstrate dual-comb ranging (DCR) that encompasses all these capabilities by using counter-propagating (CP) solitons generated in an integrated Si$_3$N$_4$ microresonator. We derive equations linking the DCR precision with comb line powers, revealing the advantage of microcomb's large line spacing in precise ranging. Leveraging the advantage, our system reaches 1-nm-precision and measures nm-scale vibration at frequencies up to 0.9 MHz. We also show that precise DCR is possible even in the presence of strong intensity noise and loss, using a mean received photon number as low as 5.5$\times$10$^{-4}$ per pulse. Our work establishes an optimization principle for dual-comb systems and bridges high performance ranging with foundry-manufactured photonic chips.

physics.optics↗

arXiv2024

SG-JND: Semantic-Guided Just Noticeable Distortion Predictor For Image Compression

Just noticeable distortion (JND), representing the threshold of distortion in an image that is minimally perceptible to the human visual system (HVS), is crucial for image compression algorithms to achieve a trade-off between transmission bit rate and image quality. However, traditional JND prediction methods only rely on pixel-level or sub-band level features, lacking the ability to capture the impact of image content on JND. To bridge this gap, we propose a Semantic-Guided JND (SG-JND) network to leverage semantic information for JND prediction. In particular, SG-JND consists of three essential modules: the image preprocessing module extracts semantic-level patches from images, the feature extraction module extracts multi-layer features by utilizing the cross-scale attention layers, and the JND prediction module regresses the extracted features into the final JND value. Experimental results show that SG-JND achieves the state-of-the-art performance on two publicly available JND datasets, which demonstrates the effectiveness of SG-JND and highlight the significance of incorporating semantic information in JND assessment.

eess.IV↗

arXiv2024

LMM-PCQA: Assisting Point Cloud Quality Assessment with LMM

Although large multi-modality models (LMMs) have seen extensive exploration and application in various quality assessment studies, their integration into Point Cloud Quality Assessment (PCQA) remains unexplored. Given LMMs' exceptional performance and robustness in low-level vision and quality assessment tasks, this study aims to investigate the feasibility of imparting PCQA knowledge to LMMs through text supervision. To achieve this, we transform quality labels into textual descriptions during the fine-tuning phase, enabling LMMs to derive quality rating logits from 2D projections of point clouds. To compensate for the loss of perception in the 3D domain, structural features are extracted as well. These quality logits and structural features are then combined and regressed into quality scores. Our experimental results affirm the effectiveness of our approach, showcasing a novel integration of LMMs into PCQA that enhances model understanding and assessment accuracy. We hope our contributions can inspire subsequent investigations into the fusion of LMMs with PCQA, fostering advancements in 3D visual quality analysis and beyond. The code is available at https://github.com/zzc-1998/LMM-PCQA.

cs.CV↗

arXiv2024

Large Multi-modality Model Assisted AI-Generated Image Quality Assessment

Traditional deep neural network (DNN)-based image quality assessment (IQA) models leverage convolutional neural networks (CNN) or Transformer to learn the quality-aware feature representation, achieving commendable performance on natural scene images. However, when applied to AI-Generated images (AGIs), these DNN-based IQA models exhibit subpar performance. This situation is largely due to the semantic inaccuracies inherent in certain AGIs caused by uncontrollable nature of the generation process. Thus, the capability to discern semantic content becomes crucial for assessing the quality of AGIs. Traditional DNN-based IQA models, constrained by limited parameter complexity and training data, struggle to capture complex fine-grained semantic features, making it challenging to grasp the existence and coherence of semantic content of the entire image. To address the shortfall in semantic content perception of current IQA models, we introduce a large Multi-modality model Assisted AI-Generated Image Quality Assessment (MA-AGIQA) model, which utilizes semantically informed guidance to sense semantic information and extract semantic vectors through carefully designed text prompts. Moreover, it employs a mixture of experts (MoE) structure to dynamically integrate the semantic information with the quality-aware features extracted by traditional DNN-based IQA models. Comprehensive experiments conducted on two AI-generated content datasets, AIGCQA-20k and AGIQA-3k show that MA-AGIQA achieves state-of-the-art performance, and demonstrate its superior generalization capabilities on assessing the quality of AGIs. Code is available at https://github.com/wangpuyi/MA-AGIQA.

cs.CV↗

arXiv2024

A microcomb-empowered Fourier domain mode-locked LiDAR

Light detection and ranging (LiDAR) has emerged as an indispensable tool in autonomous technology. Among its various techniques, frequency modulated continuous wave (FMCW) LiDAR stands out due to its capability to operate with ultralow return power, immunity to unwanted light, and simultaneous acquisition of distance and velocity. However, achieving a rapid update rate with sub-micron precision remains a challenge for FMCW LiDARs. Here, we present such a LiDAR with a sub-10 nm precision and a 24.6 kHz update rate by combining a broadband Fourier domain mode-locked (FDML) laser with a silicon nitride soliton microcomb. An ultrahigh frequency chirp rate up to 320 PHz/s is linearized by a 50 GHz microcomb to reach this performance. Our theoretical analysis also contributes to resolving the challenge of FMCW velocity measurements with nonlinear frequency sweeps and enables us to realize velocity measurement with an uncertainty below 0.4 mm/s. Our work shows how nanophotonic microcombs can unlock the potential of ultrafast frequency sweeping lasers for applications including LiDAR, optical coherence tomography and sensing.

physics.optics↗

arXiv2024

UNQA: Unified No-Reference Quality Assessment for Audio, Image, Video, and Audio-Visual Content

As multimedia data flourishes on the Internet, quality assessment (QA) of multimedia data becomes paramount for digital media applications. Since multimedia data includes multiple modalities including audio, image, video, and audio-visual (A/V) content, researchers have developed a range of QA methods to evaluate the quality of different modality data. While they exclusively focus on addressing the single modality QA issues, a unified QA model that can handle diverse media across multiple modalities is still missing, whereas the latter can better resemble human perception behaviour and also have a wider range of applications. In this paper, we propose the Unified No-reference Quality Assessment model (UNQA) for audio, image, video, and A/V content, which tries to train a single QA model across different media modalities. To tackle the issue of inconsistent quality scales among different QA databases, we develop a multi-modality strategy to jointly train UNQA on multiple QA databases. Based on the input modality, UNQA selectively extracts the spatial features, motion features, and audio features, and calculates a final quality score via the four corresponding modality regression modules. Compared with existing QA methods, UNQA has two advantages: 1) the multi-modality training strategy makes the QA model learn more general and robust quality-aware feature representation as evidenced by the superior performance of UNQA compared to state-of-the-art QA methods. 2) UNQA reduces the number of models required to assess multimedia data across different modalities. and is friendly to deploy to practical applications.

eess.IV↗

arXiv2024

Domain Adaptable Prescriptive AI Agent for Enterprise

Despite advancements in causal inference and prescriptive AI, its adoption in enterprise settings remains hindered primarily due to its technical complexity. Many users lack the necessary knowledge and appropriate tools to effectively leverage these technologies. This work at the MIT-IBM Watson AI Lab focuses on developing the proof-of-concept agent, PrecAIse, a domain-adaptable conversational agent equipped with a suite of causal and prescriptive tools to help enterprise users make better business decisions. The objective is to make advanced, novel causal inference and prescriptive tools widely accessible through natural language interactions. The presented Natural Language User Interface (NLUI) enables users with limited expertise in machine learning and data science to harness prescriptive analytics in their decision-making processes without requiring intensive computing resources. We present an agent capable of function calling, maintaining faithful, interactive, and dynamic conversations, and supporting new domains.

cs.AI↗

arXiv2024

DOLOS: Tricking the Wi-Fi APs with Incorrect User Locations

Wi-Fi-based indoor localization has been extensively studied for context-aware services. As a result, the accurate Wi-Fi-based indoor localization introduces a great location privacy threat. However, the existing solutions for location privacy protection are hard to implement on current devices. They require extra hardware deployment in the environment or hardware modifications at the transmitter or receiver side. To this end, we propose DOLOS, a system that can protect the location privacy of the Wi-Fi user with a novel signal obfuscation approach. DOLOSis a software-only solution that can be deployed on existing protocol-compliant Wi-Fi user devices. We provide this obfuscation by invalidating a simple assumption made by most localization systems -- "direct path signal arrives earlier than all the reflections to distinguish this direct path prior to estimating the location". However, DOLOS creates a novel software fix that allows the user to transmit the signal wherein this direct path arrives later, creating ambiguity in the location estimates. Our experimental results demonstrate DOLOS can degrade the localization accuracy of state-of-art systems by 6x for a single AP and 2.5x for multiple AP scenarios, thereby protecting the Wi-Fi user's location privacy without compromising the Wi-Fi communication performance.

cs.NI↗

arXiv2024

DiffStega: Towards Universal Training-Free Coverless Image Steganography with Diffusion Models

Traditional image steganography focuses on concealing one image within another, aiming to avoid steganalysis by unauthorized entities. Coverless image steganography (CIS) enhances imperceptibility by not using any cover image. Recent works have utilized text prompts as keys in CIS through diffusion models. However, this approach faces three challenges: invalidated when private prompt is guessed, crafting public prompts for semantic diversity, and the risk of prompt leakage during frequent transmission. To address these issues, we propose DiffStega, an innovative training-free diffusion-based CIS strategy for universal application. DiffStega uses a password-dependent reference image as an image prompt alongside the text, ensuring that only authorized parties can retrieve the hidden information. Furthermore, we develop Noise Flip technique to further secure the steganography against unauthorized decryption. To comprehensively assess our method across general CIS tasks, we create a dataset comprising various image steganography instances. Experiments indicate substantial improvements in our method over existing ones, particularly in aspects of versatility, password sensitivity, and recovery quality. Codes are available at \url{https://github.com/evtricks/DiffStega}.

cs.CV↗

arXiv2024

Unveiling mussel plaque core ductility: the role of pore distribution and hierarchical structure

The mussel thread-plaque system exhibits strong adhesion and high ductility, allowing it to adhere to various surfaces. While the microstructure of plaques has been thoroughly studied, the effect of their unique porous structure on ductility remains unclear. This study firstly investigated the porous structure of mussel plaque cores using scanning electron microscopy (SEM). Two-dimensional (2D) porous representative volume elements (RVEs) with scaled distribution parameters were generated, and the calibrated phase-field modelling method was applied to analyse the effect of the pore distribution and multi-scale porous structure on the failure mechanism of porous RVEs. The SEM analysis revealed that large-scale pores exhibited a lognormal size distribution and a uniform spatial distribution. Simulations showed that increasing the normalised mean radius value of the large-scale pore distribution can statistically lead to a decreasing trend in ductility, strength and strain energy, but cannot solely determine their values. The interaction between pores can lead to two different failure modes under the same pore distribution: progressive failure mode and sudden failure mode. Additionally, the hierarchical structure of multi-scale porous RVEs can further increase ductility by 40%-60% compared to single-scale porous RVEs by reducing stiffness, highlighting the hierarchical structure could be another key factor contributing to the high ductility. These findings deepen our understanding of how the pore distribution and multi-scale porous structure in mussel plaques contribute to their high ductility and affect other mechanical properties, providing valuable insights for the future design of highly ductile biomimetic materials.

physics.app-ph↗