arXiv subjects

Wei Li

Publications and source records attributed to Wei Li.

At least 685 records · Page 38Linked to original sources

arXiv2023

DI-V2X: Learning Domain-Invariant Representation for Vehicle-Infrastructure Collaborative 3D Object Detection

Vehicle-to-Everything (V2X) collaborative perception has recently gained significant attention due to its capability to enhance scene understanding by integrating information from various agents, e.g., vehicles, and infrastructure. However, current works often treat the information from each agent equally, ignoring the inherent domain gap caused by the utilization of different LiDAR sensors of each agent, thus leading to suboptimal performance. In this paper, we propose DI-V2X, that aims to learn Domain-Invariant representations through a new distillation framework to mitigate the domain discrepancy in the context of V2X 3D object detection. DI-V2X comprises three essential components: a domain-mixing instance augmentation (DMA) module, a progressive domain-invariant distillation (PDD) module, and a domain-adaptive fusion (DAF) module. Specifically, DMA builds a domain-mixing 3D instance bank for the teacher and student models during training, resulting in aligned data representation. Next, PDD encourages the student models from different domains to gradually learn a domain-invariant feature representation towards the teacher, where the overlapping regions between agents are employed as guidance to facilitate the distillation process. Furthermore, DAF closes the domain gap between the students by incorporating calibration-aware domain-adaptive attention. Extensive experiments on the challenging DAIR-V2X and V2XSet benchmark datasets demonstrate DI-V2X achieves remarkable performance, outperforming all the previous V2X models. Code is available at https://github.com/Serenos/DI-V2X

cs.CV↗

arXiv2023

TransHP: Image Classification with Hierarchical Prompting

This paper explores a hierarchical prompting mechanism for the hierarchical image classification (HIC) task. Different from prior HIC methods, our hierarchical prompting is the first to explicitly inject ancestor-class information as a tokenized hint that benefits the descendant-class discrimination. We think it well imitates human visual recognition, i.e., humans may use the ancestor class as a prompt to draw focus on the subtle differences among descendant classes. We model this prompting mechanism into a Transformer with Hierarchical Prompting (TransHP). TransHP consists of three steps: 1) learning a set of prompt tokens to represent the coarse (ancestor) classes, 2) on-the-fly predicting the coarse class of the input image at an intermediate block, and 3) injecting the prompt token of the predicted coarse class into the intermediate feature. Though the parameters of TransHP maintain the same for all input images, the injected coarse-class prompt conditions (modifies) the subsequent feature extraction and encourages a dynamic focus on relatively subtle differences among the descendant classes. Extensive experiments show that TransHP improves image classification on accuracy (e.g., improving ViT-B/16 by +2.83% ImageNet classification accuracy), training data efficiency (e.g., +12.69% improvement under 10% ImageNet training data), and model explainability. Moreover, TransHP also performs favorably against prior HIC methods, showing that TransHP well exploits the hierarchical information. The code is available at: https://github.com/WangWenhao0716/TransHP.

cs.CV↗

arXiv2023

Domain Similarity-Perceived Label Assignment for Domain Generalized Underwater Object Detection

The inherent characteristics and light fluctuations of water bodies give rise to the huge difference between different layers and regions in underwater environments. When the test set is collected in a different marine area from the training set, the issue of domain shift emerges, significantly compromising the model's ability to generalize. The Domain Adversarial Learning (DAL) training strategy has been previously utilized to tackle such challenges. However, DAL heavily depends on manually one-hot domain labels, which implies no difference among the samples in the same domain. Such an assumption results in the instability of DAL. This paper introduces the concept of Domain Similarity-Perceived Label Assignment (DSP). The domain label for each image is regarded as its similarity to the specified domains. Through domain-specific data augmentation techniques, we achieved state-of-the-art results on the underwater cross-domain object detection benchmark S-UODAC2020. Furthermore, we validated the effectiveness of our method in the Cityscapes dataset.

cs.CV↗

arXiv2023

Optical Ranging Using Coherent Kerr Soliton Dual-microcombs with Extended Ambiguity Distance

Optical ranging is a key technology in metrology. Optical frequency combs are shown to provide several advantages in light ranging, offering high precision with high acquisition rate. However, performance of traditional ranging systems based on microcombs is limited by the short ambiguity distance and non-real-time processing. Here, we show that dual-comb ranging system using coherent Kerr soliton microcombs and optical switch realizes extended ambiguity distance and provides a route to real-time processing. The ambguity distance is extended to 3.28 m from about 1.5 mm and the uncertainty reaches about 1.05 times 10^-7, while the system is compatible with low-bandwidth detectors. Combining coherent microcomb ranging systems with special FPGA could enable comb-based real-time ranging systems for several applications such as industrial process monitoring.

physics.optics↗

arXiv2023

InternLM-XComposer: A Vision-Language Large Model for Advanced Text-image Comprehension and Composition

We propose InternLM-XComposer, a vision-language large model that enables advanced image-text comprehension and composition. The innovative nature of our model is highlighted by three appealing properties: 1) Interleaved Text-Image Composition: InternLM-XComposer can effortlessly generate coherent and contextual articles that seamlessly integrate images, providing a more engaging and immersive reading experience. Simply provide a writing instruction, and our system will generate the corresponding manuscript. It can intelligently identify the areas in the text where images would enhance the content and automatically insert the most appropriate visual candidates. 2) Comprehension with Rich Multilingual Knowledge: The text-image comprehension is empowered by training on an extensive multi-modal multilingual database with carefully crafted strategies, resulting in a deep understanding of visual content. 3) State-of-the-art Performance: Our model consistently achieves state-of-the-art results across various mainstream benchmarks for vision-language foundational models, including MME Benchmark, MMBench, MMBench-CN, Seed-Bench, CCBench (Chinese Cultural Benchmark), QBench and Tiny LVLM. Owing to the absence of established metrics for quantitatively assessing text-image composition, we have devised a robust evaluation procedure that comprises both human and GPT4-Vision (GPT4-V) to ensure reliability. Notably, our InternLM-XComposer achieves competitive text-image composition scores compared to public solutions, including GPT4-V and GPT3.5. Collectively, InternLM-XComposer seamlessly blends advanced text-image comprehension and composition, revolutionizing vision-language interaction and offering new insights and opportunities. The InternLM-XComposer model series are publicly available at https://github.com/InternLM/InternLM-XComposer.

cs.CV↗

arXiv2023

Brain Computer Interface Technology for Future Battlefield

With the development of artificial intelligence and unmanned equipment, human-machine hybrid formations will be the main focus in future combat formations. With the development of big data and various situational awareness technologies, while enhancing the breadth and depth of information, decision-making has also become more complex. The operation mode of existing unmanned equipment often requires complex manual input, which is not conducive to the battlefield environment. How to reduce the cognitive load of information exchange between soldiers and various unmanned equipment is an important issue in future intelligent warfare. This paper proposes a brain computer interface communication system for soldier combat, which takes into account the characteristics of soldier combat scenarios in design. The stimulation paradigm is combined with helmets, portable computers, and firearms, and brain computer interface technology is used to achieve fast, barrier free, and hands-free communication between humans and machines. Intelligent algorithms are combined to assist decision-making in fully perceiving and fusing situational information on the battlefield, and a large amount of data is processed quickly, understanding and integrating a large amount of data from human and machine networks, achieving real-time perception of battlefield information, making intelligent decisions, and achieving the effect of direct control of drone swarms and other equipment by the human brain to assist in soldier scenarios.

eess.SY↗

arXiv2023

GenDet: Towards Good Generalizations for AI-Generated Image Detection

The misuse of AI imagery can have harmful societal effects, prompting the creation of detectors to combat issues like the spread of fake news. Existing methods can effectively detect images generated by seen generators, but it is challenging to detect those generated by unseen generators. They do not concentrate on amplifying the output discrepancy when detectors process real versus fake images. This results in a close output distribution of real and fake samples, increasing classification difficulty in detecting unseen generators. This paper addresses the unseen-generator detection problem by considering this task from the perspective of anomaly detection and proposes an adversarial teacher-student discrepancy-aware framework. Our method encourages smaller output discrepancies between the student and the teacher models for real images while aiming for larger discrepancies for fake images. We employ adversarial learning to train a feature augmenter, which promotes smaller discrepancies between teacher and student networks when the inputs are fake images. Our method has achieved state-of-the-art on public benchmarks, and the visualization results show that a large output discrepancy is maintained when faced with various types of generators.

cs.CV↗

arXiv2023

Future Intelligent Data link and Unit-Level Combat System Based on Global Combat Cloud

The development of U.S. Army and NATO data link systems is introduced first, and then the development trend of future intelligent data link is summarized into integration, generalization, multifunctionality and high security. A unit-level combat system architecture based on the global combat cloud, which is capable of realizing the flexible scheduling of global combat resources and maximizing the overall combat effectiveness, is proposed. Intelligent data link is an important part of this solution, providing strong information support for future urban unit-level warfare.

cs.NI↗

arXiv2023

Finite-Temperature Simulations of Quantum Lattice Models with Stochastic Matrix Product States

In this work, we develop a stochastic matrix product state (stoMPS) approach that combines the MPS technique and Monte Carlo samplings and can be applied to simulate quantum lattice models down to low temperature. In particular, we exploit a procedure to unbiasedly sample the local tensors in the matrix product states, which has one physical index of dimension $d$ and two geometric indices of dimension $D$, and find the results can be continuously improved by enlarging $D$. We benchmark the methods on small system sizes and then compare the results to those obtained with minimally entangled typical thermal states, finding that stoMPS has overall better performance with finite $D$. We further exploit the MPS sampling to simulate long spin chains, as well as the triangular and square lattices with cylinder circumference $W$ up to 4. Our results showcase the accuracy and effectiveness of stochastic tensor networks in finite-temperature simulations.

cond-mat.str-el↗

arXiv2023

A Scale-out Decentralized Blockchain Ledger System for Web3.0

The development of underlying technologies in blockchain mostly revolves around a difficult problem: how to enhance the performance of the system and reduce various costs of nodes (such as communication, storage and verification) without compromising the system's security and decentralization. Various layer-1 and layer-2 protocols have provided excellent solutions for this challenge. However, they cannot yet be considered as a ``silver bullet". This paper proposes EZchain -- a novel decentralized ``scale-out" ledger system designed for web3.0, aiming to enable blockchain technology to truly support ledger applications in large-scale fully decentralized networks. Without compromising security and decentralization, EZchain successfully accomplishes the following milestones: 1) Scalability: The theoretical throughput of EZchain can be infinitely expanded, nearly unaffected by bandwidth and other resource constraints. 2) Consumer-Grade Hardware Compatibility: EZchain is designed to be compatible with consumer-grade hardware, supporting storage, computation, and verification requirements. 3) Efficient Transaction Confirmation: EZchain strives to maintain transaction confirmation delays within one minute. Our prototype experiment demonstrates that under typical daily bandwidth network conditions, EZchain's performance in all aspects approaches that of the accounts in centralized payment systems. This provides a solid infrastructure for realizing mobile payments in web3.0.

cs.CR↗

arXiv2023

Note on Disjoint Cycles in Multipartite Tournaments

In 1981, Bermond and Thomassen conjectured that for any positive integer $k$, every digraph with minimum out-degree at least $2k-1$ admits $k$ vertex-disjoint directed cycles. In this short paper, we verify the Bermond-Thomassen conjecture for triangle-free multipartite tournaments and 3-partite tournaments. Furthermore, we characterize 3-partite tournaments with minimum out-degree at least $2k-1$ ($k\geq 2$) such that in each set of $k$ vertex-disjoint directed cycles, every cycle has the same length.

math.CO↗

arXiv2023

TIMS: A Tactile Internet-Based Micromanipulation System with Haptic Guidance for Surgical Training

Microsurgery involves the dexterous manipulation of delicate tissue or fragile structures such as small blood vessels, nerves, etc., under a microscope. To address the limitation of imprecise manipulation of human hands, robotic systems have been developed to assist surgeons in performing complex microsurgical tasks with greater precision and safety. However, the steep learning curve for robot-assisted microsurgery (RAMS) and the shortage of well-trained surgeons pose significant challenges to the widespread adoption of RAMS. Therefore, the development of a versatile training system for RAMS is necessary, which can bring tangible benefits to both surgeons and patients. In this paper, we present a Tactile Internet-Based Micromanipulation System (TIMS) based on a ROS-Django web-based architecture for microsurgical training. This system can provide tactile feedback to operators via a wearable tactile display (WTD), while real-time data is transmitted through the internet via a ROS-Django framework. In addition, TIMS integrates haptic guidance to `guide' the trainees to follow a desired trajectory provided by expert surgeons. Learning from demonstration based on Gaussian Process Regression (GPR) was used to generate the desired trajectory. User studies were also conducted to verify the effectiveness of our proposed TIMS, comparing users' performance with and without tactile feedback and/or haptic guidance.

cs.RO↗

arXiv2023

Resonant optical trapping of Janus nanoparticles in plasmonic nanoaperture

Controlled trapping of light absorbing nanoparticles with low-power optical tweezers is crucial for remote manipulation of small objects. This study takes advantage of the synergetic effects of tightly confined local fields of plasmonic nanoaperture, self-induced back-action of nanoparticles, and resonant optical trapping method to demonstrate enhanced manipulation of Janus nanoparticles in metallic nanohole aperture. We theoretically demonstrate that displacement of Au-coated Janus nanoparticles toward plasmonic nanoaperture and proper orientation of the metal coating give rise to enhanced near-field intensity and pronounced optical force. We also explore the effect of resonant optical trapping by employing dual laser system, where an on-resonant green laser excites the metal-coated nanoparticle whereas an off-resonant near-infrared laser plays trapping role. It is found that, at optimum nanoparticle configuration, the resonant optical trapping technique can result in three-fold enhancement of optical force, which is attributed to excitation of surface plasmon resonance in Janus nanoparticles. The findings of this study might pave the way for low power optical manipulation of light-absorbing nanoparticles with possible applications in nanorobotics and drug delivery.

physics.optics↗

arXiv2023

FireMatch: A Semi-Supervised Video Fire Detection Network Based on Consistency and Distribution Alignment

Deep learning techniques have greatly enhanced the performance of fire detection in videos. However, video-based fire detection models heavily rely on labeled data, and the process of data labeling is particularly costly and time-consuming, especially when dealing with videos. Considering the limited quantity of labeled video data, we propose a semi-supervised fire detection model called FireMatch, which is based on consistency regularization and adversarial distribution alignment. Specifically, we first combine consistency regularization with pseudo-label. For unlabeled data, we design video data augmentation to obtain corresponding weakly augmented and strongly augmented samples. The proposed model predicts weakly augmented samples and retains pseudo-label above a threshold, while training on strongly augmented samples to predict these pseudo-labels for learning more robust feature representations. Secondly, we generate video cross-set augmented samples by adversarial distribution alignment to expand the training data and alleviate the decline in classification performance caused by insufficient labeled data. Finally, we introduce a fairness loss to help the model produce diverse predictions for input samples, thereby addressing the issue of high confidence with the non-fire class in fire classification scenarios. The FireMatch achieved an accuracy of 76.92% and 91.81% on two real-world fire datasets, respectively. The experimental results demonstrate that the proposed method outperforms the current state-of-the-art semi-supervised classification methods.

cs.CV↗

arXiv2023

Wavelet-Based Network For High Dynamic Range Imaging

High dynamic range (HDR) imaging from multiple low dynamic range (LDR) images has been suffering from ghosting artifacts caused by scene and objects motion. Existing methods, such as optical flow based and end-to-end deep learning based solutions, are error-prone either in detail restoration or ghosting artifacts removal. Comprehensive empirical evidence shows that ghosting artifacts caused by large foreground motion are mainly low-frequency signals and the details are mainly high-frequency signals. In this work, we propose a novel frequency-guided end-to-end deep neural network (FHDRNet) to conduct HDR fusion in the frequency domain, and Discrete Wavelet Transform (DWT) is used to decompose inputs into different frequency bands. The low-frequency signals are used to avoid specific ghosting artifacts, while the high-frequency signals are used for preserving details. Using a U-Net as the backbone, we propose two novel modules: merging module and frequency-guided upsampling module. The merging module applies the attention mechanism to the low-frequency components to deal with the ghost caused by large foreground motion. The frequency-guided upsampling module reconstructs details from multiple frequency-specific components with rich details. In addition, a new RAW dataset is created for training and evaluating multi-frame HDR imaging algorithms in the RAW domain. Extensive experiments are conducted on public datasets and our RAW dataset, showing that the proposed FHDRNet achieves state-of-the-art performance.

eess.IV↗

arXiv2023

An invariant feature extraction for multi-modal images matching

This paper aims at providing an effective multi-modal images invariant feature extraction and matching algorithm for the application of multi-source data analysis. Focusing on the differences and correlation of multi-modal images, a feature-based matching algorithm is implemented. The key technologies include phase congruency (PC) and Shi-Tomasi feature point for keypoints detection, LogGabor filter and a weighted partial main orientation map (WPMOM) for feature extraction, and a multi-scale process to deal with scale differences and optimize matching results. The experimental results on practical data from multiple sources prove that the algorithm has effective performances on multi-modal images, which achieves accurate spatial alignment, showing practical application value and good generalization.

eess.IV↗

arXiv2023

Topological light guiding and trapping via shifted photonic crystal interfaces

Photonic crystals (PCs) are periodic dielectric structures that severed as an excellent platform to manipulate light. A conventional way to guide/trap light via PCs is to introduce a line or point defect by removing or modifying several unit cells. Here we show that the light can be effectively guided and trapped in the glided photonic crystal interfaces (GPCIs). The projected band gap of GPCIs, which depends on the glide parameter, is characterized by a Dirac mass. Interestingly, the GPCIs with zero Dirac mass is a glide-symmetric waveguide featured with excellent transmission performance even in the presence of sharp corners and disorders. Moreover, placing two GPCIs with opposite Dirac mass together results in a photonic bound state due to the Jackiw-Rebbi theory. Our work provides an alternative way towards the design of ultracompact photonic devices such as GPCIs-induced coupled cavity-waveguide system and waveguide splitter.

physics.optics↗

arXiv2023

Supervised, semi-supervised, and unsupervised learning of the Domany-Kinzel model

The Domany Kinzel (DK) model encompasses several types of non-equilibrium phase transitions, depending on the selected parameters. We apply supervised, semi-supervised, and unsupervised learning methods to studying the phase transitions and critical behaviors of the (1 + 1)-dimensional DK model. The supervised and the semi-supervised learning methods permit the estimations of the critical points, the spatial and temporal correlation exponents, concerning labelled and unlabelled DK configurations, respectively. Furthermore, we also predict the critical points by employing principal component analysis (PCA) and autoencoder. The PCA and autoencoder can produce results in good agreement with simulated particle number density.

physics.comp-ph↗