Searcharxiv⌕ Search

arXiv subjects

Chao Li

Publications and source records attributed to Chao Li.

At least 289 records · Page 16Linked to original sources
arXiv2024

SVDinsTN: A Tensor Network Paradigm for Efficient Structure Search from Regularized Modeling Perspective

Tensor network (TN) representation is a powerful technique for computer vision and machine learning. TN structure search (TN-SS) aims to search for a customized structure to achieve a compact representation, which is a challenging NP-hard problem. Recent "sampling-evaluation"-based methods require sampling an extensive collection of structures and evaluating them one by one, resulting in prohibitively high computational costs. To address this issue, we propose a novel TN paradigm, named SVD-inspired TN decomposition (SVDinsTN), which allows us to efficiently solve the TN-SS problem from a regularized modeling perspective, eliminating the repeated structure evaluations. To be specific, by inserting a diagonal factor for each edge of the fully-connected TN, SVDinsTN allows us to calculate TN cores and diagonal factors simultaneously, with the factor sparsity revealing a compact TN structure. In theory, we prove a convergence guarantee for the proposed method. Experimental results demonstrate that the proposed method achieves approximately 100 to 1000 times acceleration compared to the state-of-the-art TN-SS methods while maintaining a comparable level of representation ability.

cs.LG↗
arXiv2024

RiskQ: Risk-sensitive Multi-Agent Reinforcement Learning Value Factorization

Multi-agent systems are characterized by environmental uncertainty, varying policies of agents, and partial observability, which result in significant risks. In the context of Multi-Agent Reinforcement Learning (MARL), learning coordinated and decentralized policies that are sensitive to risk is challenging. To formulate the coordination requirements in risk-sensitive MARL, we introduce the Risk-sensitive Individual-Global-Max (RIGM) principle as a generalization of the Individual-Global-Max (IGM) and Distributional IGM (DIGM) principles. This principle requires that the collection of risk-sensitive action selections of each agent should be equivalent to the risk-sensitive action selection of the central policy. Current MARL value factorization methods do not satisfy the RIGM principle for common risk metrics such as the Value at Risk (VaR) metric or distorted risk measurements. Therefore, we propose RiskQ to address this limitation, which models the joint return distribution by modeling quantiles of it as weighted quantile mixtures of per-agent return distribution utilities. RiskQ satisfies the RIGM principle for the VaR and distorted risk metrics. We show that RiskQ can obtain promising performance through extensive experiments. The source code of RiskQ is available in https://github.com/xmu-rl-3dv/RiskQ.

cs.MA↗
arXiv2024

Enhancing Adversarial Training with Prior Knowledge Distillation for Robust Image Compression

Deep neural network-based image compression (NIC) has achieved excellent performance, but NIC method models have been shown to be susceptible to backdoor attacks. Adversarial training has been validated in image compression models as a common method to enhance model robustness. However, the improvement effect of adversarial training on model robustness is limited. In this paper, we propose a prior knowledge-guided adversarial training framework for image compression models. Specifically, first, we propose a gradient regularization constraint for training robust teacher models. Subsequently, we design a knowledge distillation based strategy to generate a priori knowledge from the teacher model to the student model for guiding adversarial training. Experimental results show that our method improves the reconstruction quality by about 9dB when the Kodak dataset is elected as the backdoor attack object for psnr attack. Compared with Ma2023, our method has a 5dB higher PSNR output at high bitrate points.

eess.IV↗
arXiv2024

CETASim: A numerical tool for beam collective effect study in storage rings

We developed a 6D multi-particle tracking program CETASim in C++ programming language to simulate intensity-dependent effects in electron storage rings. The program can simulate the beam collective effects due to short-range/long-range wakefields for single/coupled-bunch instability studies. It also features to simulate interactions among charged ions and the trains of electron bunches, including both fast ion and ion trapping effects. The bunch-by-bunch feedback is also included so that the user can simulate the damping of the unstable motion when its growth rate is faster than the radiation damping rate. The particle dynamics is based on the one-turn map, including the nonlinear effects of amplitude-dependent tune shift, high-order chromaticity, and second-order momentum compaction factor. A skew quadrupole can also be introduced by the users, which is very useful for the emittance sharing and the emittance exchange studies. This paper describes the code structure, the physics models, and the algorithms used in CETASim. We also present the results of its application to PETRA-IV storage ring.

physics.acc-ph↗
arXiv2024

Enhanced Hydrogen Evolution Catalysis of Pentlandite due to the Increases in Coordination Number and Sulfur Vacancy during Cubic-Hexagonal Phase Transition

The search for new phases is an important direction in materials science. The phase transition of sulfides results in significant changes in catalytic performance, such as MoS2 and WS2. Cubic pentlandite [cPn, (Fe, Ni)9S8] can be a functional material in batteries, solar cells, and catalytic fields. However, no report about the material properties of other phases of pentlandite exists. In this study, the unit-cell parameters of a new phase of pentlandite, sulfur-vacancy enriched hexagonal pentlandite (hPn), and the phase boundary between cPn and hPn were determined for the first time. Compared to cPn, the hPn shows a high coordination number, more sulfur vacancies, and high conductivity, which result in significantly higher hydrogen evolution performance of hPn than that of cPn and make the non-nano rock catalyst hPn superior to other most known nanosulfide catalysts. The increase of sulfur vacancies during phase transition provides a new approach to designing functional materials.

physics.chem-ph↗
arXiv2024

Transformations in Learned Image Compression from a Modulation Perspective

In this paper, a unified transformation method in learned image compression(LIC) is proposed from the perspective of modulation. Firstly, the quantization in LIC is considered as a generalized channel with additive uniform noise. Moreover, the LIC is interpreted as a particular communication system according to the consistency in structures and optimization objectives. Thus, the technology of communication systems can be applied to guide the design of modules in LIC. Furthermore, a unified transform method based on signal modulation (TSM) is defined. In the view of TSM, the existing transformation methods are mathematically reduced to a linear modulation. A series of transformation methods, e.g. TPM and TJM, are obtained by extending to nonlinear modulation. The experimental results on various datasets and backbone architectures verify that the effectiveness and robustness of the proposed method. More importantly, it further confirms the feasibility of guiding LIC design from a communication perspective. For example, when backbone architecture is hyperprior combining context model, our method achieves 3.52$\%$ BD-rate reduction over GDN on Kodak dataset without increasing complexity.

eess.IV↗
arXiv2024

Optimized Vectorizing of Building Structures with Switch: High-Efficiency Convolutional Channel-Switch Hybridization Strategy

The building planar graph reconstruction, a.k.a. footprint reconstruction, which lies in the domain of computer vision and geoinformatics, has been long afflicted with the challenge of redundant parameters in conventional convolutional models. Therefore, in this letter, we proposed an advanced and adaptive shift architecture, namely the Switch operator, which incorporates non-exponential growth parameters while retaining analogous functionalities to integrate local feature spatial information, resembling a high-dimensional convolution operation. The Switch operator, cross-channel operation, architecture implements the XOR operation to alternately exchange adjacent or diagonal features, and then blends alternating channels through a 1x1 convolution operation to consolidate information from different channels. The SwitchNN architecture, on the other hand, incorporates a group-based parameter-sharing mechanism inspired by the convolutional neural network process and thereby significantly reducing the number of parameters. We validated our proposed approach through experiments on the SpaceNet corpus, a publicly available dataset annotated with 2,001 buildings across the cities of Los Angeles, Las Vegas, and Paris. Our results demonstrate the effectiveness of this innovative architecture in building planar graph reconstruction from 2D building images.

cs.AI↗
arXiv2024

Chlorine and zinc co-doping effects on the electronic structure and optical properties of γ-CuI

The effects of chlorine (Cl) and zinc (Zn) co-doping on the electronic structure and optical properties of the zinc blende (γ) phase of copper iodide (γ-CuI) scintillator material are investigated by using first-principles density functional theory calculations. The band structure, density of states, dielectric function, absorption coefficients, and reflectivity were analyzed before and after doping. Results show co-doping significantly modifies the band structure, reduces the band gap, and generates impurity energy levels. Cl doping enhances absorption in the high energy region while reducing visible light absorption. Zn doping induces a redshift in absorption and n-type conductivity at high concentrations. With suitable co-doping ratios, the absorption coefficient and reflectivity of γ-CuI can be optimized in the visible range to improve scintillation light yield. The calculations provide guidance for co-doping γ-CuI scintillators to achieve superior detection performance. The n-type conductivity also makes doped γ-CuI promising for optoelectronic applications.

cond-mat.mtrl-sci↗
arXiv2024

Self-supervised Trajectory Representation Learning with Temporal Regularities and Travel Semantics

Trajectory Representation Learning (TRL) is a powerful tool for spatial-temporal data analysis and management. TRL aims to convert complicated raw trajectories into low-dimensional representation vectors, which can be applied to various downstream tasks, such as trajectory classification, clustering, and similarity computation. Existing TRL works usually treat trajectories as ordinary sequence data, while some important spatial-temporal characteristics, such as temporal regularities and travel semantics, are not fully exploited. To fill this gap, we propose a novel Self-supervised trajectory representation learning framework with TemporAl Regularities and Travel semantics, namely START. The proposed method consists of two stages. The first stage is a Trajectory Pattern-Enhanced Graph Attention Network (TPE-GAT), which converts the road network features and travel semantics into representation vectors of road segments. The second stage is a Time-Aware Trajectory Encoder (TAT-Enc), which encodes representation vectors of road segments in the same trajectory as a trajectory representation vector, meanwhile incorporating temporal regularities with the trajectory representation. Moreover, we also design two self-supervised tasks, i.e., span-masked trajectory recovery and trajectory contrastive learning, to introduce spatial-temporal characteristics of trajectories into the training process of our START framework. The effectiveness of the proposed method is verified by extensive experiments on two large-scale real-world datasets for three downstream tasks. The experiments also demonstrate that our method can be transferred across different cities to adapt heterogeneous trajectory datasets.

cs.LG↗
arXiv2024

Data-efficient Event Camera Pre-training via Disentangled Masked Modeling

In this paper, we present a new data-efficient voxel-based self-supervised learning method for event cameras. Our pre-training overcomes the limitations of previous methods, which either sacrifice temporal information by converting event sequences into 2D images for utilizing pre-trained image models or directly employ paired image data for knowledge distillation to enhance the learning of event streams. In order to make our pre-training data-efficient, we first design a semantic-uniform masking method to address the learning imbalance caused by the varying reconstruction difficulties of different regions in non-uniform data when using random masking. In addition, we ease the traditional hybrid masked modeling process by explicitly decomposing it into two branches, namely local spatio-temporal reconstruction and global semantic reconstruction to encourage the encoder to capture local correlations and global semantics, respectively. This decomposition allows our selfsupervised learning method to converge faster with minimal pre-training data. Compared to previous approaches, our self-supervised learning method does not rely on paired RGB images, yet enables simultaneous exploration of spatial and temporal cues in multiple scales. It exhibits excellent generalization performance and demonstrates significant improvements across various tasks with fewer parameters and lower computational costs.

cs.CV↗
arXiv2024

Foundry's perspective on laser and SOA module integration with silicon photonics

Silicon photonic integrated circuit (PIC) builds on the demand for a low cost approach from established silicon-based manufacturing infrastructure traditionally built for electronics. Besides its natural abundance, silicon has desirable properties such as optically low loss (at certain critical wavelengths), and small form factor to enable high density scaled-up optical on-chip circuitry. However, given its indirect bandgap, the platform is typically integrated with other direct bandgap (e.g., III-V semiconductor) platforms for on-chip light source. An effective solution to integrating light source onto silicon photonics platform is integral to a practical scaled-up and full-fledged integrated photonics implementation. Here, we discuss the integration solutions, and present our foundry's perspective toward realizing it.

physics.app-ph↗
arXiv2024

A Note about Isotopy and Concordance of Positive Scalar Curvature Metrics on Compact Manifolds with Boundary

We study notions of isotopy and concordance for Riemannian metrics on manifolds with boundary and, in particular, we introduce two variants of the concept of minimal concordance, the weaker one naturally arising when considering certain spaces of metrics defined by a suitable spectral ''stability'' condition. We develop some basic tools and obtain a rather complete picture in the case of surfaces.

math.DG↗
arXiv2024

NOAH: Learning Pairwise Object Category Attentions for Image Classification

A modern deep neural network (DNN) for image classification tasks typically consists of two parts: a backbone for feature extraction, and a head for feature encoding and class predication. We observe that the head structures of mainstream DNNs adopt a similar feature encoding pipeline, exploiting global feature dependencies while disregarding local ones. In this paper, we revisit the feature encoding problem, and propose Non-glObal Attentive Head (NOAH) that relies on a new form of dot-product attention called pairwise object category attention (POCA), efficiently exploiting spatially dense category-specific attentions to augment classification performance. NOAH introduces a neat combination of feature split, transform and merge operations to learn POCAs at local to global scales. As a drop-in design, NOAH can be easily used to replace existing heads of various types of DNNs, improving classification performance while maintaining similar model efficiency. We validate the effectiveness of NOAH on ImageNet classification benchmark with 25 DNN architectures spanning convolutional neural networks, vision transformers and multi-layer perceptrons. In general, NOAH is able to significantly improve the performance of lightweight DNNs, e.g., showing 3.14\%|5.3\%|1.9\% top-1 accuracy improvement to MobileNetV2 (0.5x)|Deit-Tiny (0.5x)|gMLP-Tiny (0.5x). NOAH also generalizes well when applied to medium-size and large-size DNNs. We further show that NOAH retains its efficacy on other popular multi-class and multi-label image classification benchmarks as well as in different training regimes, e.g., showing 3.6\%|1.1\% mAP improvement to large ResNet101|ViT-Large on MS-COCO dataset. Project page: https://github.com/OSVAI/NOAH.

cs.CV↗
arXiv2024

SAR-RARP50: Segmentation of surgical instrumentation and Action Recognition on Robot-Assisted Radical Prostatectomy Challenge

Surgical tool segmentation and action recognition are fundamental building blocks in many computer-assisted intervention applications, ranging from surgical skills assessment to decision support systems. Nowadays, learning-based action recognition and segmentation approaches outperform classical methods, relying, however, on large, annotated datasets. Furthermore, action recognition and tool segmentation algorithms are often trained and make predictions in isolation from each other, without exploiting potential cross-task relationships. With the EndoVis 2022 SAR-RARP50 challenge, we release the first multimodal, publicly available, in-vivo, dataset for surgical action recognition and semantic instrumentation segmentation, containing 50 suturing video segments of Robotic Assisted Radical Prostatectomy (RARP). The aim of the challenge is twofold. First, to enable researchers to leverage the scale of the provided dataset and develop robust and highly accurate single-task action recognition and tool segmentation approaches in the surgical domain. Second, to further explore the potential of multitask-based learning approaches and determine their comparative advantage against their single-task counterparts. A total of 12 teams participated in the challenge, contributing 7 action recognition methods, 9 instrument segmentation techniques, and 4 multitask approaches that integrated both action recognition and instrument segmentation. The complete SAR-RARP50 dataset is available at: https://rdr.ucl.ac.uk/projects/SARRARP50_Segmentation_of_surgical_instrumentation_and_Action_Recognition_on_Robot-Assisted_Radical_Prostatectomy_Challenge/191091

cs.CV↗
arXiv2024

Quaternary codes and their binary images

Recently, simplicial complexes are used in constructions of several infinite families of minimal and optimal linear codes by Hyun {\em et al.} Building upon their research, in this paper more linear codes over the ring $\mathbb{Z}_4$ are constructed by simplicial complexes. Specifically, the Lee weight distributions of the resulting quaternary codes are determined and two infinite families of four-Lee-weight quaternary codes are obtained. Compared to the databases of $\mathbb Z_4$ codes by Aydin {\em et al.}, at least nine new quaternary codes are found. Thanks to the special structure of the defining sets, we have the ability to determine whether the Gray images of certain obtained quaternary codes are linear or not. This allows us to obtain two infinite families of binary nonlinear codes and one infinite family of binary minimal linear codes. Furthermore, utilizing these minimal binary codes, some secret sharing schemes as a byproduct also are established.

cs.IT↗
arXiv2024

Probing charge redistribution at the interface of self-assembled cyclo-P5 pentamers on Ag(111)

Phosphorus pentamer (cyclo-P5-) ions are unstable in nature but can be synthesized at the Ag(111) surface. Unlike monolayer black phosphorous, little is known about their electronic properties when in contact with metal electrodes, although this is crucial for future applications. Here we characterize the atomic structure of cyclo-P5 assembled on Ag(111) using atomic force microscopy with functionalized tips and density functional theory. Combining force and tunneling spectroscopy, we find that a strong charge transfer induces an inward dipole moment at the cyclo-P5/Ag interface as well as the formation of an interface state. We probe the image potential states by field-effect resonant tunneling and quantify the increase of the local change of work function of 0.46 eV at the cyclo-P5 assembly. Our results suggest that the high-quality of the cyclo-P5/Ag interface might serve as a prototypical system for electric contacts in phosphorus-based semiconductor devices.

cond-mat.mtrl-sci↗