arXiv subjects

Guanghui Wang

Publications and source records attributed to Guanghui Wang.

At least 109 records · Page 6Linked to original sources

arXiv2025

PF3Det: A Prompted Foundation Feature Assisted Visual LiDAR 3D Detector

3D object detection is crucial for autonomous driving, leveraging both LiDAR point clouds for precise depth information and camera images for rich semantic information. Therefore, the multi-modal methods that combine both modalities offer more robust detection results. However, efficiently fusing LiDAR points and images remains challenging due to the domain gaps. In addition, the performance of many models is limited by the amount of high quality labeled data, which is expensive to create. The recent advances in foundation models, which use large-scale pre-training on different modalities, enable better multi-modal fusion. Combining the prompt engineering techniques for efficient training, we propose the Prompted Foundational 3D Detector (PF3Det), which integrates foundation model encoders and soft prompts to enhance LiDAR-camera feature fusion. PF3Det achieves the state-of-the-art results under limited training data, improving NDS by 1.19% and mAP by 2.42% on the nuScenes dataset, demonstrating its efficiency in 3D detection.

cs.CV↗

arXiv2025

Federated Class-Incremental Learning: A Hybrid Approach Using Latent Exemplars and Data-Free Techniques to Address Local and Global Forgetting

Federated Class-Incremental Learning (FCIL) refers to a scenario where a dynamically changing number of clients collaboratively learn an ever-increasing number of incoming tasks. FCIL is known to suffer from local forgetting due to class imbalance at each client and global forgetting due to class imbalance across clients. We develop a mathematical framework for FCIL that formulates local and global forgetting. Then, we propose an approach called Hybrid Rehearsal (HR), which utilizes latent exemplars and data-free techniques to address local and global forgetting, respectively. HR employs a customized autoencoder designed for both data classification and the generation of synthetic data. To determine the embeddings of new tasks for all clients in the latent space of the encoder, the server uses the Lennard-Jones Potential formulations. Meanwhile, at the clients, the decoder decodes the stored low-dimensional latent space exemplars back to the high-dimensional input space, used to address local forgetting. To overcome global forgetting, the decoder generates synthetic data. Furthermore, our mathematical framework proves that our proposed approach HR can, in principle, tackle the two local and global forgetting challenges. In practice, extensive experiments demonstrate that while preserving privacy, our proposed approach outperforms the state-of-the-art baselines on multiple FCIL benchmarks with low compute and memory footprints.

cs.LG↗

arXiv2025

Minimum degree conditions for Hamilton $l$-cycles in $ k $-uniform hypergraphs

We show that for $ η>0 $ and sufficiently large $ n $, every 5-graph on $ n $ vertices with $δ_{2}(H)\ge (91/216+η)\binom{n}{3}$ contains a Hamilton 2-cycle. This minimum 2-degree condition is asymptotically best possible. Moreover, we give some related results on Hamilton $ \ell $-cycles with $ d $-degree for $\ell\le d \le k-1$ and $1\le \ell < k/2$.

math.CO↗

arXiv2025

The Impact of the Distance Between Cycles on Elementary Trapping Sets

Elementary trapping sets (ETSs) are the main culprits of the performance of low-density parity-check (LDPC) codes in the error floor region. Due to their large quantities and complex structures, ETSs are difficult to analyze. This paper studies the impact of the distance between cycles on ETSs, focusing on two special graph classes: theta graphs and dumbbell graphs, which correspond to cycles with negative and non-negative distances, respectively. We determine the Turán numbers of these graphs and prove that increasing the distance between cycles can eliminate more ETSs. Additionally, using the linear state-space model and spectral theory, we prove that increasing the length of cycles or distance between cycles decreases the spectral radius of the system matrix, thereby reducing the harmfulness of ETSs. This is consistent with the conclusion obtained using Turán numbers. For specific cases when removing two 6-cycles with distance of -1, 0 and 1, respectively, we calculate the sizes, spectral radii, and error probabilities of ETSs. These results confirm that the performance of LDPC codes improves as the distance between cycles increases. Furthermore, we design the PEG-CYCLE algorithm, which greedily maximizes the distance between cycles in the Tanner graph. Numerical results show that the QC-LDPC codes constructed by our method achieve performance comparable to or even superior to state-of-the-art construction methods.

cs.IT↗

arXiv2025

A Survey on Mamba Architecture for Vision Applications

Transformers have become foundational for visual tasks such as object detection, semantic segmentation, and video understanding, but their quadratic complexity in attention mechanisms presents scalability challenges. To address these limitations, the Mamba architecture utilizes state-space models (SSMs) for linear scalability, efficient processing, and improved contextual awareness. This paper investigates Mamba architecture for visual domain applications and its recent advancements, including Vision Mamba (ViM) and VideoMamba, which introduce bidirectional scanning, selective scanning mechanisms, and spatiotemporal processing to enhance image and video understanding. Architectural innovations like position embeddings, cross-scan modules, and hierarchical designs further optimize the Mamba framework for global and local feature extraction. These advancements position Mamba as a promising architecture in computer vision research and applications.

cs.CV↗

arXiv2025

Tiling $H$ in dense graphs

We determine asymptotically the two extremal constructions for the tiling problem of the $H$-shaped tree. In particular, the first extremal construction is close to the complement of two cliques, in contrast to previously studied bipartite graphs, where the first extremal construction is close to the complement of a single clique. This result refutes one of Lang's conjectures [arXiv:2308.12281], which seeks to generalize the Erdős Matching Conjecture.

math.CO↗

arXiv2025

Extremal density for subdivisions with length or sparsity constraints

Given a graph $H$, a balanced subdivision of $H$ is obtained by replacing all edges of $H$ with internally disjoint paths of the same length. In this paper, we prove that for any graph $H$, a linear-in-$e(H)$ bound on average degree guarantees a balanced $H$-subdivision. This strengthens an old result of Bollobás and Thomason, and resolves a question of Gil-Fernández, Hyde, Liu, Pikhurko and Wu. We observe that this linear bound on average degree is best possible whenever $H$ is logarithmically dense. We further show that this logarithmic density is the critical threshold: for many graphs $H$ below this density, its subdivisions are forcible by a sublinear-in-$e(H)$ bound on average degree. We provide such examples by proving that the subdivisions of any almost bipartite graph $H$ with sublogarithmic density are forcible by a sublinear-in-$e(H)$ bound on average degree, provided that $H$ satisfies some additional separability condition.

math.CO↗

arXiv2025

ART: Distribution-Free and Model-Agnostic Changepoint Detection with Finite-Sample Guarantees

We introduce ART, a distribution-free and model-agnostic framework for changepoint detection that provides finite-sample guarantees. ART transforms independent observations into real-valued scores via a symmetric function, ensuring exchangeability in the absence of changepoints. These scores are then ranked and aggregated to detect distributional changes. The resulting test offers exact Type-I error control, agnostic to specific distributional or model assumptions. Moreover, ART seamlessly extends to multi-scale settings, enabling robust multiple changepoint estimation and post-detection inference with finite-sample error rate control. By locally ranking the scores and performing aggregations across multiple prespecified intervals, ART identifies changepoint intervals and refines subsequent inference while maintaining its distribution-free and model-agnostic nature. This adaptability makes ART as a reliable and versatile tool for modern changepoint analysis, particularly in high-dimensional data contexts and applications leveraging machine learning methods.

stat.ME↗

arXiv2025

FgC2F-UDiff: Frequency-guided and Coarse-to-fine Unified Diffusion Model for Multi-modality Missing MRI Synthesis

Multi-modality magnetic resonance imaging (MRI) is essential for the diagnosis and treatment of brain tumors. However, missing modalities are commonly observed due to limitations in scan time, scan corruption, artifacts, motion, and contrast agent intolerance. Synthesis of missing MRI has been a means to address the limitations of modality insufficiency in clinical practice and research. However, there are still some challenges, such as poor generalization, inaccurate non-linear mapping, and slow processing speeds. To address the aforementioned issues, we propose a novel unified synthesis model, the Frequency-guided and Coarse-to-fine Unified Diffusion Model (FgC2F-UDiff), designed for multiple inputs and outputs. Specifically, the Coarse-to-fine Unified Network (CUN) fully exploits the iterative denoising properties of diffusion models, from global to detail, by dividing the denoising process into two stages, coarse and fine, to enhance the fidelity of synthesized images. Secondly, the Frequency-guided Collaborative Strategy (FCS) harnesses appropriate frequency information as prior knowledge to guide the learning of a unified, highly non-linear mapping. Thirdly, the Specific-acceleration Hybrid Mechanism (SHM) integrates specific mechanisms to accelerate the diffusion model and enhance the feasibility of many-to-many synthesis. Extensive experimental evaluations have demonstrated that our proposed FgC2F-UDiff model achieves superior performance on two datasets, validated through a comprehensive assessment that includes both qualitative observations and quantitative metrics, such as PSNR SSIM, LPIPS, and FID.

eess.IV↗

arXiv2024

KA-GNN: Kolmogorov-Arnold Graph Neural Networks for Molecular Property Prediction

As key models in geometric deep learning, graph neural networks have demonstrated enormous power in molecular data analysis. Recently, a specially-designed learning scheme, known as Kolmogorov-Arnold Network (KAN), shows unique potential for the improvement of model accuracy, efficiency, and explainability. Here we propose the first non-trivial Kolmogorov-Arnold Network-based Graph Neural Networks (KA-GNNs), including KAN-based graph convolutional networks(KA-GCN) and KAN-based graph attention network (KA-GAT). The essential idea is to utilizes KAN's unique power to optimize GNN architectures at three major levels, including node embedding, message passing, and readout. Further, with the strong approximation capability of Fourier series, we develop Fourier series-based KAN model and provide a rigorous mathematical prove of the robust approximation capability of this Fourier KAN architecture. To validate our KA-GNNs, we consider seven most-widely-used benchmark datasets for molecular property prediction and extensively compare with existing state-of-the-art models. It has been found that our KA-GNNs can outperform traditional GNN models. More importantly, our Fourier KAN module can not only increase the model accuracy but also reduce the computational time. This work not only highlights the great power of KA-GNNs in molecular property prediction but also provides a novel geometric deep learning framework for the general non-Euclidean data analysis.

cs.LG↗

arXiv2024

Vertex-distinguishing and sum-distinguishing edge coloring of regular graphs

Given an integer $k\ge1$, an edge-$k$-coloring of a graph $G$ is an assignment of $k$ colors $1,\ldots,k$ to the edges of $G$ such that no two adjacent edges receive the same color. A vertex-distinguishing (resp. sum-distinguishing) edge-$k$-coloring of $G$ is an edge-$k$-coloring such that for any two distinct vertices $u$ and $v$, the set (resp. sum) of colors taken from all the edges incident with $u$ is different from that taken from all the edges incident with $v$. The vertex-distinguishing chromatic index (resp. sum-distinguishing chromatic index), denoted $χ'_{vd}(G)$ (resp. $χ'_{sd}(G)$), is the smallest value $k$ such that $G$ has a vertex-distinguishing-edge-$k$-coloring (resp. sum-distinguishing-edge-$k$-coloring). Let $G$ be a $d$-regular graph on $n$ vertices, where $n$ is even and sufficiently large. We show that $χ'_{vd}(G) =d+2$ if $d$ is arbitrarily close to $n/2$ from above, and $χ'_{sd}(G) =d+2$ if $d\ge \frac{2n}{3}$. Our first result strengthens a result of Balister et al. in 2004 for such class of regular graphs, and our second result constitutes a significant advancement in the field of sum-distinguishing edge coloring. To achieve these results, we introduce novel edge coloring results which may be of independent interest.

math.CO↗

arXiv2024

Theoretical Studies on Sodium Storage Mechanism in Hard Carbon Anodes of Sodium-Ion Batteries: Molecular Simulations Based on Machine Learning Force Fields

Sodium-ion batteries (SIBs) have garnered significant attention in recent years as a promising alternative to lithium-ion batteries (LIBs) due to their low cost, abundant sodium resources, and excellent cycling performance. Hard carbon materials, characterized by their high specific capacity, outstanding cycling stability, and low cost, have emerged as potential candidates for SIB anodes. However, the sodium storage mechanism in hard carbon anodes remains highly complex, especially in disordered structures, and is yet to be fully understood. To address this, we employed relative machine learning force fields (MLFFs) in conjunction with multiscale simulation techniques to systematically investigate the sodium storage behavior in hard carbon. By integrating simulations, this study provides a detailed exploration of sodium adsorption, intercalation, and filling mechanisms. High-precision, large-scale simulations reveal the dynamic behavior and distribution patterns of sodium ions in hard carbon. The findings not only deepen our understanding of sodium storage mechanisms in hard carbon anodes, but also offer a theoretical foundation for optimizing future SIB designs, while introducing novel simulation methodologies and technical frameworks to enhance battery performance.

cond-mat.mtrl-sci↗

arXiv2024

On the lifting degree of girth-8 QC-LDPC codes

The lifting degree and the deterministic construction of quasi-cyclic low-density parity-check (QC-LDPC) codes have been extensively studied, with many construction methods in the literature, including those based on finite geometry, array-based codes, computer search, and combinatorial techniques. In this paper, we focus on the lifting degree $p$ required for achieving a girth of 8 in $(3,L)$ fully connected QC-LDPC codes, and we propose an improvement over the classical lower bound $p\geq 2L-1$, enhancing it to $p\geq \sqrt{5L^2-11L+\frac{13}{2}}+\frac{1}{2}$. Moreover, we demonstrate that for girth-8 QC-LDPC codes containing an arithmetic row in the exponent matrix, a necessary condition for achieving a girth of 8 is $p\geq \frac{1}{2}L^2+\frac{1}{2}L$. Additionally, we present a corresponding deterministic construction of $(3,L)$ QC-LDPC codes with girth 8 for any $p\geq \frac{1}{2}L^2+\frac{1}{2}L+\lfloor \frac{L-1}{2}\rfloor$, which approaches the lower bound of $\frac{1}{2}L^2+\frac{1}{2}L$. Under the same conditions, this construction achieves a smaller lifting degree compared to prior methods. To the best of our knowledge, the proposed order of lifting degree matches the smallest known, on the order of $\frac{1}{2}L^2+\mathcal{O} (L)$.

cs.IT↗

arXiv2024

Depth-Wise Convolutions in Vision Transformers for Efficient Training on Small Datasets

The Vision Transformer (ViT) leverages the Transformer's encoder to capture global information by dividing images into patches and achieves superior performance across various computer vision tasks. However, the self-attention mechanism of ViT captures the global context from the outset, overlooking the inherent relationships between neighboring pixels in images or videos. Transformers mainly focus on global information while ignoring the fine-grained local details. Consequently, ViT lacks inductive bias during image or video dataset training. In contrast, convolutional neural networks (CNNs), with their reliance on local filters, possess an inherent inductive bias, making them more efficient and quicker to converge than ViT with less data. In this paper, we present a lightweight Depth-Wise Convolution module as a shortcut in ViT models, bypassing entire Transformer blocks to ensure the models capture both local and global information with minimal overhead. Additionally, we introduce two architecture variants, allowing the Depth-Wise Convolution modules to be applied to multiple Transformer blocks for parameter savings, and incorporating independent parallel Depth-Wise Convolution modules with different kernels to enhance the acquisition of local information. The proposed approach significantly boosts the performance of ViT models on image classification, object detection, and instance segmentation by a large margin, especially on small datasets, as evaluated on CIFAR-10, CIFAR-100, Tiny-ImageNet and ImageNet for image classification, and COCO for object detection and instance segmentation. The source code can be accessed at https://github.com/ZTX-100/Efficient_ViT_with_DW.

cs.CV↗

arXiv2024

Universal Online Convex Optimization Meets Second-order Bounds

Recently, several universal methods have been proposed for online convex optimization, and attain minimax rates for multiple types of convex functions simultaneously. However, they need to design and optimize one surrogate loss for each type of functions, making it difficult to exploit the structure of the problem and utilize existing algorithms. In this paper, we propose a simple strategy for universal online convex optimization, which avoids these limitations. The key idea is to construct a set of experts to process the original online functions, and deploy a meta-algorithm over the linearized losses to aggregate predictions from experts. Specifically, the meta-algorithm is required to yield a second-order bound with excess losses, so that it can leverage strong convexity and exponential concavity to control the meta-regret. In this way, our strategy inherits the theoretical guarantee of any expert designed for strongly convex functions and exponentially concave functions, up to a double logarithmic factor. As a result, we can plug in off-the-shelf online solvers as black-box experts to deliver problem-dependent regret bounds. For general convex functions, it maintains the minimax optimality and also achieves a small-loss bound. Furthermore, we extend our universal strategy to online composite optimization, where the loss function comprises a time-varying function and a fixed regularizer. To deal with the composite loss functions, we employ a meta-algorithm based on the optimistic online learning framework, which not only possesses a second-order bound, but also can utilize estimations for upcoming loss functions. With appropriate configurations, we demonstrate that the additional regularizer does not contribute to the meta-regret, thus maintaining the universality in the composite setting.

cs.LG↗

arXiv2024

Robust 3D Point Clouds Classification based on Declarative Defenders

3D point cloud classification requires distinct models from 2D image classification due to the divergent characteristics of the respective input data. While 3D point clouds are unstructured and sparse, 2D images are structured and dense. Bridging the domain gap between these two data types is a non-trivial challenge to enable model interchangeability. Recent research using Lattice Point Classifier (LPC) highlights the feasibility of cross-domain applicability. However, the lattice projection operation in LPC generates 2D images with disconnected projected pixels. In this paper, we explore three distinct algorithms for mapping 3D point clouds into 2D images. Through extensive experiments, we thoroughly examine and analyze their performance and defense mechanisms. Leveraging current large foundation models, we scrutinize the feature disparities between regular 2D images and projected 2D images. The proposed approaches demonstrate superior accuracy and robustness against adversarial attacks. The generative model-based mapping algorithms yield regular 2D images, further minimizing the domain gap from regular 2D classification tasks. The source code is available at https://github.com/KaidongLi/pytorch-LatticePointClassifier.git.

cs.CV↗

arXiv2024

Occluded Human Pose Estimation based on Limb Joint Augmentation

Human pose estimation aims at locating the specific joints of humans from the images or videos. While existing deep learning-based methods have achieved high positioning accuracy, they often struggle with generalization in occlusion scenarios. In this paper, we propose an occluded human pose estimation framework based on limb joint augmentation to enhance the generalization ability of the pose estimation model on the occluded human bodies. Specifically, the occlusion blocks are at first employed to randomly cover the limb joints of the human bodies from the training images, imitating the scene where the objects or other people partially occlude the human body. Trained by the augmented samples, the pose estimation model is encouraged to accurately locate the occluded keypoints based on the visible ones. To further enhance the localization ability of the model, this paper constructs a dynamic structure loss function based on limb graphs to explore the distribution of occluded joints by evaluating the dependence between adjacent joints. Extensive experimental evaluations on two occluded datasets, OCHuman and CrowdPose, demonstrate significant performance improvements without additional computation cost during inference.

cs.CV↗

arXiv2024

MaskBlur: Spatial and Angular Data Augmentation for Light Field Image Super-Resolution

Data augmentation (DA) is an effective approach for enhancing model performance with limited data, such as light field (LF) image super-resolution (SR). LF images inherently possess rich spatial and angular information. Nonetheless, there is a scarcity of DA methodologies explicitly tailored for LF images, and existing works tend to concentrate solely on either the spatial or angular domain. This paper proposes a novel spatial and angular DA strategy named MaskBlur for LF image SR by concurrently addressing spatial and angular aspects. MaskBlur consists of spatial blur and angular dropout two components. Spatial blur is governed by a spatial mask, which controls where pixels are blurred, i.e., pasting pixels between the low-resolution and high-resolution domains. The angular mask is responsible for angular dropout, i.e., selecting which views to perform the spatial blur operation. By doing so, MaskBlur enables the model to treat pixels differently in the spatial and angular domains when super-resolving LF images rather than blindly treating all pixels equally. Extensive experiments demonstrate the efficacy of MaskBlur in significantly enhancing the performance of existing SR methods. We further extend MaskBlur to other LF image tasks such as denoising, deblurring, low-light enhancement, and real-world SR. Code is publicly available at \url{https://github.com/chaowentao/MaskBlur}.

eess.IV↗