arXiv subjects

Bo Zhang

Publications and source records attributed to Bo Zhang.

At least 505 records · Page 28Linked to original sources

arXiv2023

A Wasserstein distance-based spectral clustering method for transaction data analysis

With the rapid development of online payment platforms, it is now possible to record massive transaction data. Clustering on transaction data significantly contributes to analyzing merchants' behavior patterns. This enables payment platforms to provide differentiated services or implement risk management strategies. However, traditional methods exploit transactions by generating low-dimensional features, leading to inevitable information loss. In this study, we use the empirical cumulative distribution of transactions to characterize merchants. We adopt Wasserstein distance to measure the dissimilarity between any two merchants and propose the Wasserstein-distance-based spectral clustering (WSC) approach. Based on the similarities between merchants' transaction distributions, a graph of merchants is generated. Thus, we treat the clustering of merchants as a graph-cut problem and solve it under the framework of spectral clustering. To ensure feasibility of the proposed method on large-scale datasets with limited computational resources, we propose a subsampling method for WSC (SubWSC). The associated theoretical properties are investigated to verify the efficiency of the proposed approach. The simulations and empirical study demonstrate that the proposed method outperforms feature-based methods in finding behavior patterns of merchants.

stat.ME↗

arXiv2023

Conditional Positional Encodings for Vision Transformers

We propose a conditional positional encoding (CPE) scheme for vision Transformers. Unlike previous fixed or learnable positional encodings, which are pre-defined and independent of input tokens, CPE is dynamically generated and conditioned on the local neighborhood of the input tokens. As a result, CPE can easily generalize to the input sequences that are longer than what the model has ever seen during training. Besides, CPE can keep the desired translation-invariance in the image classification task, resulting in improved performance. We implement CPE with a simple Position Encoding Generator (PEG) to get seamlessly incorporated into the current Transformer framework. Built on PEG, we present Conditional Position encoding Vision Transformer (CPVT). We demonstrate that CPVT has visually similar attention maps compared to those with learned positional encodings and delivers outperforming results. Our code is available at https://github.com/Meituan-AutoML/CPVT .

cs.CV↗

arXiv2023

Better Pre-Training by Reducing Representation Confusion

In this work, we revisit the Transformer-based pre-trained language models and identify two different types of information confusion in position encoding and model representations, respectively. Firstly, we show that in the relative position encoding, the joint modeling about relative distances and directions brings confusion between two heterogeneous information. It may make the model unable to capture the associative semantics of the same distance and the opposite directions, which in turn affects the performance of downstream tasks. Secondly, we notice the BERT with Mask Language Modeling (MLM) pre-training objective outputs similar token representations (last hidden states of different tokens) and head representations (attention weights of different heads), which may make the diversity of information expressed by different tokens and heads limited. Motivated by the above investigation, we propose two novel techniques to improve pre-trained language models: Decoupled Directional Relative Position (DDRP) encoding and MTH pre-training objective. DDRP decouples the relative distance features and the directional features in classical relative position encoding. MTH applies two novel auxiliary regularizers besides MLM to enlarge the dissimilarities between (a) last hidden states of different tokens, and (b) attention weights of different heads. These designs allow the model to capture different categories of information more clearly, as a way to alleviate information confusion in representation learning for better optimization. Extensive experiments and ablation studies on GLUE benchmark demonstrate the effectiveness of our proposed methods.

cs.CL↗

arXiv2023

OPT-GAN: A Broad-Spectrum Global Optimizer for Black-box Problems by Learning Distribution

Black-box optimization (BBO) algorithms are concerned with finding the best solutions for problems with missing analytical details. Most classical methods for such problems are based on strong and fixed a priori assumptions, such as Gaussianity. However, the complex real-world problems, especially when the global optimum is desired, could be very far from the a priori assumptions because of their diversities, causing unexpected obstacles. In this study, we propose a generative adversarial net-based broad-spectrum global optimizer (OPT-GAN) which estimates the distribution of optimum gradually, with strategies to balance exploration-exploitation trade-off. It has potential to better adapt to the regularity and structure of diversified landscapes than other methods with fixed prior, e.g., Gaussian assumption or separability. Experiments on diverse BBO benchmarks and high dimensional real world applications exhibit that OPT-GAN outperforms other traditional and neural net-based BBO algorithms.

cs.LG↗

arXiv2023

VLBI astrometry on the white dwarf pulsar AR Scorpii

AR Scorpii (AR Sco), the only-known radio-pulsing white dwarf binary, shows unusual pulsating emission at the radio, infrared, optical and ultraviolet bands. To determine its astrometric parameters at the radio band independently, we conducted multi-epoch Very Long Baseline Interferometry (VLBI) phase-referencing observations with the European VLBI Network (EVN) at 5 GHz and the Chinese VLBI Network (CVN) plus the Warkworth 30-metre telescope (New Zealand) at 8.6 GHz. By using the differential VLBI astrometry, we provide high-precision astrometric measurements on the parallax ($π=8.52_{-0.07}^{+0.04}$ mas), and proper motion ($μ_α=9.48_{-0.07}^{+0.04}$ mas yr$^{-1}$, $μ_δ=-51.32_{-0.38}^{+0.22}$ mas yr$^{-1}$). The new VLBI results agree with the optical Gaia astrometry. Our kinematic analysis reveals that the Galactic space velocities of AR Sco are quite consistent with that of both intermediate polars (IPs) and polars. Combined with the previous tightest VLBI constraint on the size, our parallax distance suggests that the radio emission of AR Sco should be located within the light cylinder of its white dwarf.

astro-ph.SR↗

arXiv2023

AI of Brain and Cognitive Sciences: From the Perspective of First Principles

Nowadays, we have witnessed the great success of AI in various applications, including image classification, game playing, protein structure analysis, language translation, and content generation. Despite these powerful applications, there are still many tasks in our daily life that are rather simple to humans but pose great challenges to AI. These include image and language understanding, few-shot learning, abstract concepts, and low-energy cost computing. Thus, learning from the brain is still a promising way that can shed light on the development of next-generation AI. The brain is arguably the only known intelligent machine in the universe, which is the product of evolution for animals surviving in the natural environment. At the behavior level, psychology and cognitive sciences have demonstrated that human and animal brains can execute very intelligent high-level cognitive functions. At the structure level, cognitive and computational neurosciences have unveiled that the brain has extremely complicated but elegant network forms to support its functions. Over years, people are gathering knowledge about the structure and functions of the brain, and this process is accelerating recently along with the initiation of giant brain projects worldwide. Here, we argue that the general principles of brain functions are the most valuable things to inspire the development of AI. These general principles are the standard rules of the brain extracting, representing, manipulating, and retrieving information, and here we call them the first principles of the brain. This paper collects six such first principles. They are attractor network, criticality, random network, sparse coding, relational memory, and perceptual learning. On each topic, we review its biological background, fundamental property, potential application to AI, and future development.

q-bio.NC↗

arXiv2023

Danlu Tongdu tablets treat lumbar spinal stenosis through reducing reactive oxygen species and apoptosis by regulating CDK2/CDK4/CDKN1A expression

Lumbar spinal stenosis (LSS) is caused by the compression of the nerve root or cauda equina nerve by stenosis of the lumbar spinal canal or intervertebral foramen, and is manifested as chronic low back and leg pain. Danlu Tongdu (DLTD) tablets can relieve chronic pain caused by LSS, but the molecular mechanism remains largely unknown. In this study, the potential molecular mechanism of DLTD tablets in the treatment of LSS was firstly predicted by network pharmacology method. Results showed that DLTD functions in regulating anti-oxidative, apoptosis, and inflammation signaling pathways. Furthermore, the flow cytometry results showed that DLTD tablets efficiently reduced ROS content and inhibited rat neural stem cell apoptosis induced by hydrogen peroxide. DLTD also inhibited the mitochondrial membrane potential damage induced by hydrogen peroxide. Elisa analysis showed that DLTD induced cell cycle related protein, CDK2 and CDK4 and reduced CDKN1A protein expression level. Taken together, our study provided new insights of DLTD in treating LSS through reducing ROS content, decreasing apoptosis by inhibiting CDKN1A and promoting CDK2 and CDK4 expression levels.

q-bio.QM↗

arXiv2023

DarkVision: A Benchmark for Low-light Image/Video Perception

Imaging and perception in photon-limited scenarios is necessary for various applications, e.g., night surveillance or photography, high-speed photography, and autonomous driving. In these cases, cameras suffer from low signal-to-noise ratio, which degrades the image quality severely and poses challenges for downstream high-level vision tasks like object detection and recognition. Data-driven methods have achieved enormous success in both image restoration and high-level vision tasks. However, the lack of high-quality benchmark dataset with task-specific accurate annotations for photon-limited images/videos delays the research progress heavily. In this paper, we contribute the first multi-illuminance, multi-camera, and low-light dataset, named DarkVision, serving for both image enhancement and object detection. We provide bright and dark pairs with pixel-wise registration, in which the bright counterpart provides reliable reference for restoration and annotation. The dataset consists of bright-dark pairs of 900 static scenes with objects from 15 categories, and 32 dynamic scenes with 4-category objects. For each scene, images/videos were captured at 5 illuminance levels using three cameras of different grades, and average photons can be reliably estimated from the calibration data for quantitative studies. The static-scene images and dynamic videos respectively contain around 7,344 and 320,667 instances in total. With DarkVision, we established baselines for image/video enhancement and object detection by representative algorithms. To demonstrate an exemplary application of DarkVision, we propose two simple yet effective approaches for improving performance in video enhancement and object detection respectively. We believe DarkVision would advance the state-of-the-arts in both imaging and related computer vision tasks in low-light environment.

cs.CV↗

arXiv2023

YOLOv6 v3.0: A Full-Scale Reloading

The YOLO community has been in high spirits since our first two releases! By the advent of Chinese New Year 2023, which sees the Year of the Rabbit, we refurnish YOLOv6 with numerous novel enhancements on the network architecture and the training scheme. This release is identified as YOLOv6 v3.0. For a glimpse of performance, our YOLOv6-N hits 37.5% AP on the COCO dataset at a throughput of 1187 FPS tested with an NVIDIA Tesla T4 GPU. YOLOv6-S strikes 45.0% AP at 484 FPS, outperforming other mainstream detectors at the same scale (YOLOv5-S, YOLOv8-S, YOLOX-S and PPYOLOE-S). Whereas, YOLOv6-M/L also achieve better accuracy performance (50.0%/52.8% respectively) than other detectors at a similar inference speed. Additionally, with an extended backbone and neck design, our YOLOv6-L6 achieves the state-of-the-art accuracy in real-time. Extensive experiments are carefully conducted to validate the effectiveness of each improving component. Our code is made available at https://github.com/meituan/YOLOv6.

cs.CV↗

arXiv2023

Towards simultaneous coherent radiation in the visible and microwave bands with doped molecular crystals

Coherent sources exploiting the stimulated emission of non-equilibrium quantum systems, i.e. gain media, have proven indispensable for advancing fundamental research and engineering. The operating electromagnetic bands of such coherent sources have been continuously enriched for increasing demands.Nevertheless, for a single bench top coherent source, simultaneous generation of radiation in multiple bands, especially when the bands are widely separated, present formidable challenges with a single gain medium. Here, we propose a mechanism of simultaneously realizing the stimulated emission of radiation in the visible and microwave bands, i.e. lasing and masing actions, at ambient conditions by utilizing photoexcited singlet and triplet states of the pentacene molecules that are doped in p-terphenyl. The possibility is validated by the observed amplified spontaneous emission (ASE) at 645 nm with a narrow linewidth around 1 nm from the pentacene-doped p-terphenyl crystal used for masing at 1.45 GHz and consolidated by a 20 fold lower threshold of ASE compared to the reported masing threshold. The overall threshold of the pentacene-based multiband coherent source can be optimized by appropriate alignment of the pump-light polarization with the pentacene's transition dipole moment. Our work not only shows a great promise on immediate realization of multiband coherent sources but also establishes an intriguing solid-state platform for fundamental research of quantum optics in multiple frequency domains.

physics.optics↗

arXiv2022

Diagnosis of ultrafast ultraintense laser pulse characteristics by machine-learning-assisted electron spin

Rapid development of ultrafast ultraintense laser technologies continues to create opportunities for studying strong-field physics under extreme conditions. However, accurate determination of the spatial and temporal characteristics of a laser pulse is still a great challenge, especially when laser powers higher than hundreds of terawatts are involved. In this paper, by utilizing the radiative spin-flip effect, we find that the spin depolarization of an electron beam can be employed to diagnose characteristics of ultrafast ultraintense lasers with peak intensities around $10^{20}$-$10^{22}$~W/cm$^2$. With three shots, our machine-learning-assisted model can predict, simultaneously, the pulse duration, peak intensity, and focal radius of a focused Gaussian ultrafast ultraintense laser (in principle, the profile can be arbitrary) with relative errors of $0.1\%$-$10\%$. The underlying physics and an alternative diagnosis method (without the assistance of machine learning) are revealed by the asymptotic approximation of the final spin degree of polarization. Our proposed scheme exhibits robustness and detection accuracy with respect to fluctuations in the electron beam parameters. Accurate measurements of the ultrafast ultraintense laser parameters will lead to much higher precision in, for example, laser nuclear physics investigations and laboratory astrophysics studies. Robust machine learning techniques may also find applications in more general strong-field physics scenarios.

physics.plasm-ph↗

arXiv2022

LAMOST medium-resolution spectroscopic survey of binarity and exotic star (LAMOST-MRS-B): Observation strategy and target selection

LAMOST-MRS-B is one of the sub-surveys of LAMOST medium-resolution (R~7500) spectroscopic survey. It aims at studying the statistical properties (e.g., binary fraction, orbital period distribution, mass ratio distribution) of binary stars and exotic stars. We intend to observe about 30000 stars (10 mag <= G <= 14.5 mag) with at least 10 visits in five years. We first planned to observe 25 plates around the galactic plane in 2018. Then the plates were reduced to 12 in 2019 because of the limitation of observation. At the same time, two new plates located at the high galactic latitude were added to explore binary properties influenced by the different environments. In this survey project, we set the identified exotic and low-metallicity stars with the highest observation priorities. For the rest of the selected stars, we gave higher priority to the relatively brighter stars in order to obtain high-quality spectra as many as possible. Spectra of 49129 stars have been obtained in LAMOST-MRS-B field and released in DR8, of which 28828 and 3375 stars have been visited more than twice and ten times with SNR >= 10, respectively. Most of the sources are B-, A-, and F-type stars with 0.6 < [Fe/H] < 0.4 dex. We also obtain 347 identified variable and exotic stars and about 250 stars with [Fe/H] < 1 dex. We measure radial velocities (RVs) by using 892233 spectra of the stars. The uncertainties of RV achieve about 1 km/s and 10 km/s1 for 95% of late- and early-type stars, respectively. The datasets presented in this paper are available at http://www.doi.org/10.57760/sciencedb.j00113.00035.

astro-ph.SR↗

arXiv2022

Simultaneously Optimizing Perturbations and Positions for Black-box Adversarial Patch Attacks

Adversarial patch is an important form of real-world adversarial attack that brings serious risks to the robustness of deep neural networks. Previous methods generate adversarial patches by either optimizing their perturbation values while fixing the pasting position or manipulating the position while fixing the patch's content. This reveals that the positions and perturbations are both important to the adversarial attack. For that, in this paper, we propose a novel method to simultaneously optimize the position and perturbation for an adversarial patch, and thus obtain a high attack success rate in the black-box setting. Technically, we regard the patch's position, the pre-designed hyper-parameters to determine the patch's perturbations as the variables, and utilize the reinforcement learning framework to simultaneously solve for the optimal solution based on the rewards obtained from the target model with a small number of queries. Extensive experiments are conducted on the Face Recognition (FR) task, and results on four representative FR models show that our method can significantly improve the attack success rate and query efficiency. Besides, experiments on the commercial FR service and physical environments confirm its practical application value. We also extend our method to the traffic sign recognition task to verify its generalization ability.

cs.CV↗

arXiv2022

Subsampling Spectral Clustering for Large-Scale Social Networks

Online social network platforms such as Twitter and Sina Weibo have been extremely popular over the past 20 years. Identifying the network community of a social platform is essential to exploring and understanding the users' interests. However, the rapid development of science and technology has generated large amounts of social network data, creating great computational challenges for community detection in large-scale social networks. Here, we propose a novel subsampling spectral clustering algorithm to identify community structures in large-scale social networks with limited computing resources. More precisely, spectral clustering is conducted using only the information of a small subsample of the network nodes, resulting in a huge reduction in computational time. As a result, for large-scale datasets, the method can be realized even using a personal computer. Specifically, we introduce two different sampling techniques, namely simple random subsampling and degree corrected subsampling. The methodology is applied to the dataset collected from Sina Weibo, which is one of the largest Twitter-type social network platforms in China. Our method can very effectively identify the community structure of registered users. This community structure information can be applied to help Sina Weibo promote advertisements to target users and increase user activity.

cs.SI↗

arXiv2022

Quantum sensing of temperature close to absolute zero in a Bose-Einstein condensate

We propose a theoretical scheme for quantum sensing of temperature close to absolute zero in a quasi-one-dimensional Bose-Einstein condensate (BEC). In our scheme, a single-atom impurity qubit is used as a temper-ature sensor. We investigate the sensitivity of the single-atom sensor in estimating the temperature of the BEC. We demonstrate that the sensitivity of the temperature sensor can saturate the quantum Cramer-Rao bound by means of measuring quantum coherence of the probe qubit. We study the temperature sensing performance by the use of quantum signal-to-noise ratio (QSNR). It is indicated that there is an optimal encoding time that the QSNR can reach its maximum in the full-temperature regime. In particular, we find that the QSNR reaches a finite upper bound in the weak coupling regime even when the temperature is close to absolute zero, which implies that the sensing-error-divergence problem is avoided in our scheme. Our work opens a way for quantum sensing of temperature close to absolute zero in the BEC.

quant-ph↗

arXiv2022

Overview of the Observing System and Initial Scientific Accomplishments of the East Asian VLBI Network (EAVN)

The East Asian VLBI Network (EAVN) is an international VLBI facility in East Asia and is operated under mutual collaboration between East Asian countries, as well as part of Southeast Asian and European countries. EAVN currently consists of 16 radio telescopes and three correlators located in China, Japan, and Korea, and is operated mainly at three frequency bands, 6.7, 22, and 43 GHz with the longest baseline length of 5078 km, resulting in the highest angular resolution of 0.28 milliarcseconds at 43 GHz. One of distinct capabilities of EAVN is multi-frequency simultaneous data reception at nine telescopes, which enable us to employ the frequency phase transfer technique to obtain better sensitivity at higher observing frequencies. EAVN started its open-use program in the second half of 2018, providing a total observing time of more than 1100 hours in a year. EAVN fills geographical gap in global VLBI array, resulting in enabling us to conduct contiguous high-resolution VLBI observations. EAVN has produced various scientific accomplishments especially in observations toward active galactic nuclei, evolved stars, and star-forming regions. These activities motivate us to initiate launch of the 'Global VLBI Alliance' to provide an opportunity of VLBI observation with the longest baselines on the earth.

astro-ph.IM↗

arXiv2022

Rodin: A Generative Model for Sculpting 3D Digital Avatars Using Diffusion

This paper presents a 3D generative model that uses diffusion models to automatically generate 3D digital avatars represented as neural radiance fields. A significant challenge in generating such avatars is that the memory and processing costs in 3D are prohibitive for producing the rich details required for high-quality avatars. To tackle this problem we propose the roll-out diffusion network (Rodin), which represents a neural radiance field as multiple 2D feature maps and rolls out these maps into a single 2D feature plane within which we perform 3D-aware diffusion. The Rodin model brings the much-needed computational efficiency while preserving the integrity of diffusion in 3D by using 3D-aware convolution that attends to projected features in the 2D feature plane according to their original relationship in 3D. We also use latent conditioning to orchestrate the feature generation for global coherence, leading to high-fidelity avatars and enabling their semantic editing based on text prompts. Finally, we use hierarchical synthesis to further enhance details. The 3D avatars generated by our model compare favorably with those produced by existing generative techniques. We can generate highly detailed avatars with realistic hairstyles and facial hair like beards. We also demonstrate 3D avatar generation from image or text as well as text-guided editability.

cs.CV↗

arXiv2022

Recognizing Object by Components with Human Prior Knowledge Enhances Adversarial Robustness of Deep Neural Networks

Adversarial attacks can easily fool object recognition systems based on deep neural networks (DNNs). Although many defense methods have been proposed in recent years, most of them can still be adaptively evaded. One reason for the weak adversarial robustness may be that DNNs are only supervised by category labels and do not have part-based inductive bias like the recognition process of humans. Inspired by a well-known theory in cognitive psychology -- recognition-by-components, we propose a novel object recognition model ROCK (Recognizing Object by Components with human prior Knowledge). It first segments parts of objects from images, then scores part segmentation results with predefined human prior knowledge, and finally outputs prediction based on the scores. The first stage of ROCK corresponds to the process of decomposing objects into parts in human vision. The second stage corresponds to the decision process of the human brain. ROCK shows better robustness than classical recognition models across various attack settings. These results encourage researchers to rethink the rationality of currently widely-used DNN-based object recognition models and explore the potential of part-based models, once important but recently ignored, for improving robustness.

cs.CV↗