arXiv subjects

Yang Zhou

Publications and source records attributed to Yang Zhou.

At least 325 records · Page 18Linked to original sources

arXiv2024

Efficient Scene Appearance Aggregation for Level-of-Detail Rendering

Creating an appearance-preserving level-of-detail (LoD) representation for arbitrary 3D scenes is a challenging problem. The appearance of a scene is an intricate combination of both geometry and material models, and is further complicated by correlation due to the spatial configuration of scene elements. We present a novel volumetric representation for the aggregated appearance of complex scenes and an efficient pipeline for LoD generation and rendering. The core of our representation is the Aggregated Bidirectional Scattering Distribution Function (ABSDF) that summarizes the far-field appearance of all surfaces inside a voxel. We propose a closed-form factorization of the ABSDF that accounts for spatially varying and orientation-varying material parameters. We tackle the challenge of capturing the correlation existing locally within a voxel and globally across different parts of the scene. Our method faithfully reproduces appearance and achieves higher quality than existing scene filtering methods while being inherently efficient to render. The memory footprint and rendering cost of our representation are independent of the original scene complexity.

cs.GR↗

arXiv2024

Efficient Federated Learning Using Dynamic Update and Adaptive Pruning with Momentum on Shared Server Data

Despite achieving remarkable performance, Federated Learning (FL) encounters two important problems, i.e., low training efficiency and limited computational resources. In this paper, we propose a new FL framework, i.e., FedDUMAP, with three original contributions, to leverage the shared insensitive data on the server in addition to the distributed data in edge devices so as to efficiently train a global model. First, we propose a simple dynamic server update algorithm, which takes advantage of the shared insensitive data on the server while dynamically adjusting the update steps on the server in order to speed up the convergence and improve the accuracy. Second, we propose an adaptive optimization method with the dynamic server update algorithm to exploit the global momentum on the server and each local device for superior accuracy. Third, we develop a layer-adaptive model pruning method to carry out specific pruning operations, which is adapted to the diverse features of each layer so as to attain an excellent trade-off between effectiveness and efficiency. Our proposed FL model, FedDUMAP, combines the three original techniques and has a significantly better performance compared with baseline approaches in terms of efficiency (up to 16.9 times faster), accuracy (up to 20.4% higher), and computational cost (up to 62.6% smaller).

cs.DC↗

arXiv2024

UrFound: Towards Universal Retinal Foundation Models via Knowledge-Guided Masked Modeling

Retinal foundation models aim to learn generalizable representations from diverse retinal images, facilitating label-efficient model adaptation across various ophthalmic tasks. Despite their success, current retinal foundation models are generally restricted to a single imaging modality, such as Color Fundus Photography (CFP) or Optical Coherence Tomography (OCT), limiting their versatility. Moreover, these models may struggle to fully leverage expert annotations and overlook the valuable domain knowledge essential for domain-specific representation learning. To overcome these limitations, we introduce UrFound, a retinal foundation model designed to learn universal representations from both multimodal retinal images and domain knowledge. UrFound is equipped with a modality-agnostic image encoder and accepts either CFP or OCT images as inputs. To integrate domain knowledge into representation learning, we encode expert annotation in text supervision and propose a knowledge-guided masked modeling strategy for model pre-training. It involves reconstructing randomly masked patches of retinal images while predicting masked text tokens conditioned on the corresponding retinal image. This approach aligns multimodal images and textual expert annotations within a unified latent space, facilitating generalizable and domain-specific representation learning. Experimental results demonstrate that UrFound exhibits strong generalization ability and data efficiency when adapting to various tasks in retinal image analysis. By training on ~180k retinal images, UrFound significantly outperforms the state-of-the-art retinal foundation model trained on up to 1.6 million unlabelled images across 8 public retinal datasets. Our code and data are available at https://github.com/yukkai/UrFound.

cs.CV↗

arXiv2024

Personalized Federated Learning on Heterogeneous and Long-Tailed Data via Expert Collaborative Learning

Personalized Federated Learning (PFL) aims to acquire customized models for each client without disclosing raw data by leveraging the collective knowledge of distributed clients. However, the data collected in real-world scenarios is likely to follow a long-tailed distribution. For example, in the medical domain, it is more common for the number of general health notes to be much larger than those specifically relatedto certain diseases. The presence of long-tailed data can significantly degrade the performance of PFL models. Additionally, due to the diverse environments in which each client operates, data heterogeneity is also a classic challenge in federated learning. In this paper, we explore the joint problem of global long-tailed distribution and data heterogeneity in PFL and propose a method called Expert Collaborative Learning (ECL) to tackle this problem. Specifically, each client has multiple experts, and each expert has a different training subset, which ensures that each class, especially the minority classes, receives sufficient training. Multiple experts collaborate synergistically to produce the final prediction output. Without special bells and whistles, the vanilla ECL outperforms other state-of-the-art PFL methods on several benchmark datasets under different degrees of data heterogeneity and long-tailed distribution.

cs.LG↗

arXiv2024

Reputation-Driven Asynchronous Federated Learning for Enhanced Trajectory Prediction with Blockchain

Federated learning combined with blockchain empowers secure data sharing in autonomous driving applications. Nevertheless, with the increasing granularity and complexity of vehicle-generated data, the lack of data quality audits raises concerns about multi-party mistrust in trajectory prediction tasks. In response, this paper proposes an asynchronous federated learning data sharing method based on an interpretable reputation quantization mechanism utilizing graph neural network tools. Data providers share data structures under differential privacy constraints to ensure security while reducing redundant data. We implement deep reinforcement learning to categorize vehicles by reputation level, which optimizes the aggregation efficiency of federated learning. Experimental results demonstrate that the proposed data sharing scheme not only reinforces the security of the trajectory prediction task but also enhances prediction accuracy.

cs.LG↗

arXiv2024

Applicability of Measurement-based Quantum Computation towards Physically-driven Variational Quantum Eigensolver

Variational quantum algorithms are considered one of the most promising methods for obtaining near-term quantum advantages; however, most of these algorithms are only expressed in the conventional quantum circuit scheme. The roadblock to developing quantum algorithms with the measurement-based quantum computation (MBQC) scheme is resource cost. Recently, we discovered that the realization of multi-qubit rotation operations requires a constant number of single-qubit measurements with the MBQC scheme, providing a potential advantage in terms of resource cost. The structure of the Hamiltonian variational ansatz (HVA) aligns well with this characteristic. Thus, we propose an efficient measurement-based quantum algorithm for quantum many-body system simulation tasks, called measurement-based Hamiltonian variational ansatz (MBHVA). We then demonstrate the effectiveness, efficiency, and advantages of the two-dimensional Heisenberg model and the Fermi-Hubbard chain. Numerical experiments show that MBHVA is expected to reduce resource overhead compared to quantum circuits, especially in the presence of large multi-qubit rotation operations. Furthermore, when compared to Measurement-based Hardware Efficient Ansatz (MBHEA), MBHVA also demonstrates superior performance. We conclude that the MBQC scheme is potentially feasible for achieving near-term quantum advantages in terms of both resource efficiency and error mitigation, particularly for photonic platforms.

quant-ph↗

arXiv2024

Single entanglement connection architecture between multi-layer bipartite Hardware Efficient Ansatz

Variational quantum algorithms (VQAs) are among the most promising algorithms to achieve quantum advantages in the NISQ era. One important challenge in implementing such algorithms is to construct an effective parameterized quantum circuit (also called an ansatz). In this work, we propose a single entanglement connection architecture (SECA) for a bipartite hardware efficient ansatz (HEA) by balancing its expressibility, entangling capability, and trainability. Numerical simulations with a one-dimensional Heisenberg model and quadratic unconstrained binary optimization (QUBO) issues were conducted. Our results indicate the superiority of SECA over the common full entanglement connection architecture (FECA) in terms of computational performance. Furthermore, combining SECA with gate-cutting technology to construct distributed quantum computation (DQC) can efficiently expand the size of NISQ devices under low overhead. We also demonstrated the effectiveness and scalability of the DQC scheme. Our study is a useful indication for understanding the characteristics associated with an effective training circuit.

quant-ph↗

arXiv2024

DVPE: Divided View Position Embedding for Multi-View 3D Object Detection

Sparse query-based paradigms have achieved significant success in multi-view 3D detection for autonomous vehicles. Current research faces challenges in balancing between enlarging receptive fields and reducing interference when aggregating multi-view features. Moreover, different poses of cameras present challenges in training global attention models. To address these problems, this paper proposes a divided view method, in which features are modeled globally via the visibility crossattention mechanism, but interact only with partial features in a divided local virtual space. This effectively reduces interference from other irrelevant features and alleviates the training difficulties of the transformer by decoupling the position embedding from camera poses. Additionally, 2D historical RoI features are incorporated into the object-centric temporal modeling to utilize highlevel visual semantic information. The model is trained using a one-to-many assignment strategy to facilitate stability. Our framework, named DVPE, achieves state-of-the-art performance (57.2% mAP and 64.5% NDS) on the nuScenes test set. Codes will be available at https://github.com/dop0/DVPE.

cs.CV↗

arXiv2024

New Capability to Look Up an ASL Sign from a Video Example

Looking up an unknown sign in an ASL dictionary can be difficult. Most ASL dictionaries are organized based on English glosses, despite the fact that (1) there is no convention for assigning English-based glosses to ASL signs; and (2) there is no 1-1 correspondence between ASL signs and English words. Furthermore, what if the user does not know either the meaning of the target sign or its possible English translation(s)? Some ASL dictionaries enable searching through specification of articulatory properties, such as handshapes, locations, movement properties, etc. However, this is a cumbersome process and does not always result in successful lookup. Here we describe a new system, publicly shared on the Web, to enable lookup of a video of an ASL sign (e.g., a webcam recording or a clip from a continuous signing video). The user submits a video for analysis and is presented with the five most likely sign matches, in decreasing order of likelihood, so that the user can confirm the selection and then be taken to our ASLLRP Sign Bank entry for that sign. Furthermore, this video lookup is also integrated into our newest version of SignStream(R) software to facilitate linguistic annotation of ASL video data, enabling the user to directly look up a sign in the video being annotated, and, upon confirmation of the match, to directly enter into the annotation the gloss and features of that sign, greatly increasing the efficiency and consistency of linguistic annotations of ASL video data.

cs.CV↗

arXiv2024

Classification Theorem For Positive Critical Points Of Sobolev Trace Inequality

We consider the Euler-Lagrange equation of Sobolev trace inequality and prove several classification results. Exploiting the moving sphere method, it has been shown, when $p=2$, positive solutions of Euler-Lagrange equation of Sobolev trace inequality are classified. Since the moving sphere method strongly relies on the symmetries of the equation, in this paper we use asymptotic estimates and two important integral identities to classify positive solutions of Euler-Langrange equation of Sobolev trace inequality under finite energy when $1<p<n$.

math.AP↗

arXiv2024

SDPT: Synchronous Dual Prompt Tuning for Fusion-based Visual-Language Pre-trained Models

Prompt tuning methods have achieved remarkable success in parameter-efficient fine-tuning on large pre-trained models. However, their application to dual-modal fusion-based visual-language pre-trained models (VLPMs), such as GLIP, has encountered issues. Existing prompt tuning methods have not effectively addressed the modal mapping and aligning problem for tokens in different modalities, leading to poor transfer generalization. To address this issue, we propose Synchronous Dual Prompt Tuning (SDPT). SDPT initializes a single set of learnable unified prototype tokens in the established modal aligning space to represent the aligned semantics of text and image modalities for downstream tasks. Furthermore, SDPT establishes inverse linear projections that require no training to embed the information of unified prototype tokens into the input space of different modalities. The inverse linear projections allow the unified prototype token to synchronously represent the two modalities and enable SDPT to share the unified semantics of text and image for downstream tasks across different modal prompts. Experimental results demonstrate that SDPT assists fusion-based VLPMs to achieve superior outcomes with only 0.04\% of model parameters for training across various scenarios, outperforming other single- or dual-modal methods. The code will be released at https://github.com/wuyongjianCODE/SDPT.

cs.CV↗

arXiv2024

GRIP: Generating Interaction Poses Using Spatial Cues and Latent Consistency

Hands are dexterous and highly versatile manipulators that are central to how humans interact with objects and their environment. Consequently, modeling realistic hand-object interactions, including the subtle motion of individual fingers, is critical for applications in computer graphics, computer vision, and mixed reality. Prior work on capturing and modeling humans interacting with objects in 3D focuses on the body and object motion, often ignoring hand pose. In contrast, we introduce GRIP, a learning-based method that takes, as input, the 3D motion of the body and the object, and synthesizes realistic motion for both hands before, during, and after object interaction. As a preliminary step before synthesizing the hand motion, we first use a network, ANet, to denoise the arm motion. Then, we leverage the spatio-temporal relationship between the body and the object to extract two types of novel temporal interaction cues, and use them in a two-stage inference pipeline to generate the hand motion. In the first stage, we introduce a new approach to enforce motion temporal consistency in the latent space (LTC), and generate consistent interaction motions. In the second stage, GRIP generates refined hand poses to avoid hand-object penetrations. Given sequences of noisy body and object motion, GRIP upgrades them to include hand-object interaction. Quantitative experiments and perceptual studies demonstrate that GRIP outperforms baseline methods and generalizes to unseen objects and motions from different motion-capture datasets.

cs.CV↗

arXiv2024

Entanglement Negativity and Defect Extremal Surface

We study entanglement negativity for evaporating black hole based on the holographic model with defect brane. We introduce a defect extremal surface formula for entanglement negativity. Based on partial reduction, we show the equivalence between defect extremal surface formula and island formula for entanglement negativity in AdS$_3$/BCFT$_2$. Extending the study to the model of eternal black hole plus CFT bath, we find that black hole-black hole negativity decreases until vanishing, left black hole-left radiation negativity is always a constant, radiation-radiation negativity increases and then saturates at a time later than Page time. In all the time dependent cases, defect extremal surface formula agrees with island formula.

hep-th↗

arXiv2024

Region Attention Transformer for Medical Image Restoration

Transformer-based methods have demonstrated impressive results in medical image restoration, attributed to the multi-head self-attention (MSA) mechanism in the spatial dimension. However, the majority of existing Transformers conduct attention within fixed and coarsely partitioned regions (\text{e.g.} the entire image or fixed patches), resulting in interference from irrelevant regions and fragmentation of continuous image content. To overcome these challenges, we introduce a novel Region Attention Transformer (RAT) that utilizes a region-based multi-head self-attention mechanism (R-MSA). The R-MSA dynamically partitions the input image into non-overlapping semantic regions using the robust Segment Anything Model (SAM) and then performs self-attention within these regions. This region partitioning is more flexible and interpretable, ensuring that only pixels from similar semantic regions complement each other, thereby eliminating interference from irrelevant regions. Moreover, we introduce a focal region loss to guide our model to adaptively focus on recovering high-difficulty regions. Extensive experiments demonstrate the effectiveness of RAT in various medical image restoration tasks, including PET image synthesis, CT image denoising, and pathological image super-resolution. Code is available at \href{https://github.com/Yaziwel/Region-Attention-Transformer-for-Medical-Image-Restoration.git}{https://github.com/RAT}.

eess.IV↗

arXiv2024

Multiple scattering and diffusion of scalar coherent waves in a group of small spheroidal particles with random orientations

In this manuscript we study multiple scattering and diffusion of scalar wave in a group of monodisperse spheroidal particles with random orientations. We begin by fixing a spheroid in a prolate spheroidal coordinate system, and attain the expansion of the scalar Green's function in this space. The expansion is firstly based on spheroidal wave functions, and then we transform it into the expansion of spherical wave functions. Next, we average the Green's function over the orientations of the spheroid to get the averaged transition operator. Finally, we calculate the transport mean free path and anisotropy factor for the spheroidal particles group, based on the irreducible vertex in the Bethe-Salpeter equation. The approaches to get the average transition operator and the mean free paths in this manuscript will be of benefit to the research area of multiple scattering by non-spherical particles.

physics.optics↗

arXiv2024

Regularity of the $p$-Gauss curvature flow with flat side

We study the regularity of the $p$-Gauss curvature flow with flat side. In our previous paper(arxiv:2403.12292), we obtained the regularity of the interface, namely the boundary of the flat part. In this paper, we study the regularity of the convex hypersurface near the interface.

math.DG↗

arXiv2024

Physically Analyzable AI-Based Nonlinear Platoon Dynamics Modeling During Traffic Oscillation: A Koopman Approach

Given the complexity and nonlinearity inherent in traffic dynamics within vehicular platoons, there exists a critical need for a modeling methodology with high accuracy while concurrently achieving physical analyzability. Currently, there are two predominant approaches: the physics model-based approach and the Artificial Intelligence (AI)--based approach. Knowing the facts that the physical-based model usually lacks sufficient modeling accuracy and potential function mismatches and the pure-AI-based method lacks analyzability, this paper innovatively proposes an AI-based Koopman approach to model the unknown nonlinear platoon dynamics harnessing the power of AI and simultaneously maintain physical analyzability, with a particular focus on periods of traffic oscillation. Specifically, this research first employs a deep learning framework to generate the embedding function that lifts the original space into the embedding space. Given the embedding space descriptiveness, the platoon dynamics can be expressed as a linear dynamical system founded by the Koopman theory. Based on that, the routine of linear dynamical system analysis can be conducted on the learned traffic linear dynamics in the embedding space. By that, the physical interpretability and analyzability of model-based methods with the heightened precision inherent in data-driven approaches can be synergized. Comparative experiments have been conducted with existing modeling approaches, which suggests our method's superiority in accuracy. Additionally, a phase plane analysis is performed, further evidencing our approach's effectiveness in replicating the complex dynamic patterns. Moreover, the proposed methodology is proven to feature the capability of analyzing the stability, attesting to the physical analyzability.

eess.SY↗

arXiv2024

Efficient Enumeration of Large Maximal k-Plexes

Finding cohesive subgraphs in a large graph has many important applications, such as community detection and biological network analysis. Clique is often a too strict cohesive structure since communities or biological modules rarely form as cliques for various reasons such as data noise. Therefore, $k$-plex is introduced as a popular clique relaxation, which is a graph where every vertex is adjacent to all but at most $k$ vertices. In this paper, we propose a fast branch-and-bound algorithm as well as its task-based parallel version to enumerate all maximal $k$-plexes with at least $q$ vertices. Our algorithm adopts an effective search space partitioning approach that provides a lower time complexity, a new pivot vertex selection method that reduces candidate vertex size, an effective upper-bounding technique to prune useless branches, and three novel pruning techniques by vertex pairs. Our parallel algorithm uses a timeout mechanism to eliminate straggler tasks, and maximizes cache locality while ensuring load balancing. Extensive experiments show that compared with the state-of-the-art algorithms, our sequential and parallel algorithms enumerate large maximal $k$-plexes with up to $5 \times$ and $18.9 \times$ speedup, respectively. Ablation results also demonstrate that our pruning techniques bring up to $7 \times$ speedup compared with our basic algorithm.

cs.DS↗