Search arXiv⌕ Search

arXiv subjects

Ming Zhang

Publications and source records attributed to Ming Zhang.

At least 271 records · Page 15Linked to original sources
arXiv2023

Orthonormal Product Quantization Network for Scalable Face Image Retrieval

Existing deep quantization methods provided an efficient solution for large-scale image retrieval. However, the significant intra-class variations like pose, illumination, and expressions in face images, still pose a challenge for face image retrieval. In light of this, face image retrieval requires sufficiently powerful learning metrics, which are absent in current deep quantization works. Moreover, to tackle the growing unseen identities in the query stage, face image retrieval drives more demands regarding model generalization and system scalability than general image retrieval tasks. This paper integrates product quantization with orthonormal constraints into an end-to-end deep learning framework to effectively retrieve face images. Specifically, a novel scheme that uses predefined orthonormal vectors as codewords is proposed to enhance the quantization informativeness and reduce codewords' redundancy. A tailored loss function maximizes discriminability among identities in each quantization subspace for both the quantized and original features. An entropy-based regularization term is imposed to reduce the quantization error. Experiments are conducted on four commonly-used face datasets under both seen and unseen identities retrieval settings. Our method outperforms all the compared deep hashing/quantization state-of-the-arts under both settings. Results validate the effectiveness of the proposed orthonormal codewords in improving models' standard retrieval performance and generalization ability. Combing with further experiments on two general image datasets, it demonstrates the broad superiority of our method for scalable image retrieval.

cs.CV↗
arXiv2023

TGNN: A Joint Semi-supervised Framework for Graph-level Classification

This paper studies semi-supervised graph classification, a crucial task with a wide range of applications in social network analysis and bioinformatics. Recent works typically adopt graph neural networks to learn graph-level representations for classification, failing to explicitly leverage features derived from graph topology (e.g., paths). Moreover, when labeled data is scarce, these methods are far from satisfactory due to their insufficient topology exploration of unlabeled data. We address the challenge by proposing a novel semi-supervised framework called Twin Graph Neural Network (TGNN). To explore graph structural information from complementary views, our TGNN has a message passing module and a graph kernel module. To fully utilize unlabeled data, for each module, we calculate the similarity of each unlabeled graph to other labeled graphs in the memory bank and our consistency loss encourages consistency between two similarity distributions in different embedding spaces. The two twin modules collaborate with each other by exchanging instance similarity knowledge to fully explore the structure information of both labeled and unlabeled data. We evaluate our TGNN on various public datasets and show that it achieves strong performance.

cs.LG↗
arXiv2023

Correlation analysis between several observables of OJ 287 radio jet

We collected the archival data of blazar OJ~287 from heterogeneous very long baseline interferometry (VLBI) monitoring programs at 2.3 GHz, 8.6 GHz, 15 GHz and 43 GHz. The data reduction and observable extraction of those multi-band multi-epoch observations are batch-processed consistently with our automated pipeline. We present the multivariate correlation analysis on the observables at each band. We employ the cross-correlation function to search the correlations and the Monte Carlo (MC) technique to verify the certainty of correlations. Several correlations are found. The foremost findings are the correlations between the core flux density and the jet position angles on different scales, which validated the plausible predictions of the jet with precession characteristics. Meanwhile, there is a variation in the offset between the core EVPA and the inner-jet position angle over time at 15~GHz and 43~GHz.

astro-ph.GA↗
arXiv2023

Robust Dancer: Long-term 3D Dance Synthesis Using Unpaired Data

How to automatically synthesize natural-looking dance movements based on a piece of music is an incrementally popular yet challenging task. Most existing data-driven approaches require hard-to-get paired training data and fail to generate long sequences of motion due to error accumulation of autoregressive structure. We present a novel 3D dance synthesis system that only needs unpaired data for training and could generate realistic long-term motions at the same time. For the unpaired data training, we explore the disentanglement of beat and style, and propose a Transformer-based model free of reliance upon paired data. For the synthesis of long-term motions, we devise a new long-history attention strategy. It first queries the long-history embedding through an attention computation and then explicitly fuses this embedding into the generation pipeline via multimodal adaptation gate (MAG). Objective and subjective evaluations show that our results are comparable to strong baseline methods, despite not requiring paired training data, and are robust when inferring long-term music. To our best knowledge, we are the first to achieve unpaired data training - an ability that enables to alleviate data limitations effectively. Our code is released on https://github.com/BFeng14/RobustDancer

cs.CV↗
arXiv2023

Disruption Precursor Onset Time Study Based on Semi-supervised Anomaly Detection

The full understanding of plasma disruption in tokamaks is currently lacking, and data-driven methods are extensively used for disruption prediction. However, most existing data-driven disruption predictors employ supervised learning techniques, which require labeled training data. The manual labeling of disruption precursors is a tedious and challenging task, as some precursors are difficult to accurately identify, limiting the potential of machine learning models. To address this issue, commonly used labeling methods assume that the precursor onset occurs at a fixed time before the disruption, which may not be consistent for different types of disruptions or even the same type of disruption, due to the different speeds at which plasma instabilities escalate. This leads to mislabeled samples and suboptimal performance of the supervised learning predictor. In this paper, we present a disruption prediction method based on anomaly detection that overcomes the drawbacks of unbalanced positive and negative data samples and inaccurately labeled disruption precursor samples. We demonstrate the effectiveness and reliability of anomaly detection predictors based on different algorithms on J-TEXT and EAST to evaluate the reliability of the precursor onset time inferred by the anomaly detection predictor. The precursor onset times inferred by these predictors reveal that the labeling methods have room for improvement as the onset times of different shots are not necessarily the same. Finally, we optimize precursor labeling using the onset times inferred by the anomaly detection predictor and test the optimized labels on supervised learning disruption predictors. The results on J-TEXT and EAST show that the models trained on the optimized labels outperform those trained on fixed onset time labels.

physics.plasm-ph↗
arXiv2023

GLCC: A General Framework for Graph-Level Clustering

This paper studies the problem of graph-level clustering, which is a novel yet challenging task. This problem is critical in a variety of real-world applications such as protein clustering and genome analysis in bioinformatics. Recent years have witnessed the success of deep clustering coupled with graph neural networks (GNNs). However, existing methods focus on clustering among nodes given a single graph, while exploring clustering on multiple graphs is still under-explored. In this paper, we propose a general graph-level clustering framework named Graph-Level Contrastive Clustering (GLCC) given multiple graphs. Specifically, GLCC first constructs an adaptive affinity graph to explore instance- and cluster-level contrastive learning (CL). Instance-level CL leverages graph Laplacian based contrastive loss to learn clustering-friendly representations while cluster-level CL captures discriminative cluster representations incorporating neighbor information of each sample. Moreover, we utilize neighbor-aware pseudo-labels to reward the optimization of representation learning. The two steps can be alternatively trained to collaborate and benefit each other. Experiments on a range of well-known datasets demonstrate the superiority of our proposed GLCC over competitive baselines.

cs.LG↗
arXiv2023

GraphVF: Controllable Protein-Specific 3D Molecule Generation with Variational Flow

Designing molecules that bind to specific target proteins is a fundamental task in drug discovery. Recent models leverage geometric constraints to generate ligand molecules that bind cohesively with specific protein pockets. However, these models cannot effectively generate 3D molecules with 2D skeletal curtailments and property constraints, which are pivotal to drug potency and development. To tackle this challenge, we propose GraphVF, a variational flow-based framework that combines 2D topology and 3D geometry, for controllable generation of binding 3D molecules. Empirically, our method achieves state-of-the-art binding affinity and realistic sub-structural layouts for protein-specific generation. In particular, GraphVF represents the first controllable geometry-aware, protein-specific molecule generation method, which can generate binding 3D molecules with tailored sub-structures and physio-chemical properties. Our code is available at https://github.com/Franco-Solis/GraphVF-code.

q-bio.BM↗
arXiv2023

Focus-Driven Contrastive Learniang for Medical Question Summarization

Automatic medical question summarization can significantly help the system to understand consumer health questions and retrieve correct answers. The Seq2Seq model based on maximum likelihood estimation (MLE) has been applied in this task, which faces two general problems: the model can not capture well question focus and and the traditional MLE strategy lacks the ability to understand sentence-level semantics. To alleviate these problems, we propose a novel question focus-driven contrastive learning framework (QFCL). Specially, we propose an easy and effective approach to generate hard negative samples based on the question focus, and exploit contrastive learning at both encoder and decoder to obtain better sentence level representations. On three medical benchmark datasets, our proposed model achieves new state-of-the-art results, and obtains a performance gain of 5.33, 12.85 and 3.81 points over the baseline BART model on three datasets respectively. Further human judgement and detailed analysis prove that our QFCL model learns better sentence representations with the ability to distinguish different sentence meanings, and generates high-quality summaries by capturing question focus.

cs.CL↗
arXiv2023

On-chip quantum interference between the origins of a multi-photon state

Path identiy induces a broad interest in recent years due to the foundation for numerous novel quantum information applications. Here, we experimentally demonstrate quantum coherent superposition of two different origins of a four-photon state, where multi-photon frustrated interference emerges from the quantum indistinguishability by path identity. The quantum state is created in four probabilistic photon-pair sources on one integrated silicon photonic chip, two combinations of which can create photon quadruplets. Coherent elimination and revival of distributed four-photons are fully controlled by tuning phases. The experiment gives rise to peculiar quantum interference of two possible ways to create photon quadruplets rather than interference of different intrinsic properties of photons. Besides many known potential applications, this new kind of multi-photon nonlinear interference enables the possibility for various fundamental studies such as nonlocality with multiple spatially separated locations.

quant-ph↗
arXiv2023

Channel Measurement for Holographic MIMO: Benefits and Challenges of Spatial Oversampling

In this paper, the channel of an indoor holographic multiple-input multiple-output (MIMO) system is measured. It is demonstrated through experiments for the first time that the spatial oversampling of holographic MIMO systems is able to increase the capacity of a wireless communication system significantly. However, the antenna efficiency is the most crucial challenge preventing us from getting the capacity improvement. An extended EM-compliant channel model is also proposed for holographic MIMO systems, which is able to take the non-isotropic characteristics of the propagation environment, the antenna pattern distortion, the antenna efficiency, and the polarization characteristics into consideration.

cs.IT↗
arXiv2023

Analytical approximate solutions for scalarized AdS black holes

The spontaneous scalarization of Schwarzscild-AdS is investigated in the Einstein-scalar-Gauss--Bonnet (ESGB) theory. Firstly, we construct scalarized AdS black holes numerically. Secondly, making use of the homotopy analysis method (HAM), we obtain analytical approximate solutions for scalarized AdS black holes in the ESGB theory. It is found that scalarized AdS black holes constructed numerically are consistent with analytical approximate solutions in the whole space.

gr-qc↗
arXiv2022

Revisiting thermodynamic topologies of black holes

In the generalized off-shell free energy landscape, black holes can be treated as thermodynamic topological defects. The local topological properties of the spacetime can be reflected by the winding numbers at the defects, while the global topological nature can be classified by the topological number which is the sum of all local winding numbers. We propose that the winding numbers can be calculated via the residues of isolated one-order pole points of characterized functions constructed from the off-shell free energy. Using the residue method, we show that the topologies of black holes can be divided into three classes with the topological numbers being -1, 0, and 1, respectively, being consistent with the results obtained in [Phys. Rev. Lett. 129, 191101 (2022)] by using the topological current method. Moreover, we point out that standard defect points, generation and annihilation points, and critical points can be distinguished by coefficients of the Laurent series of the off-shell characterized function at those singular points.

gr-qc↗
arXiv2022

A data-driven physics-based transport model of solar energetic particles accelerated by coronal mass ejection shocks propagating through the solar coronal and heliospheric magnetic fields

In an effort to develop computational tools for predicting radiation hazards from solar energetic particles (SEPs), we have created a data-driven physics-based particle transport model to calculate the injection, acceleration and propagation of SEPs from coronal mass ejection (CME) shocks traversing through the solar corona and interplanetary magnetic fields. The model runs on an input of corona and heliospheric plasma and magnetic field configuration from an MHD model driven by solar photospheric magnetic field measurements superposed with observed CME shocks determined from coronagraph images. Using several advanced computation techniques involving stochastic simulation and integration, it rigorously solves the time-dependent 5-dimensional focus transport equation in the phase space that includes pitch-angle scattering, diffusion across magnetic field line, and particle acceleration by CME shocks. We apply the model to the 2011 November 3 CME event. The calculation results reproduce multi-spacecraft SEP observations reasonably well without normalization of particle flux. This circumsolar SEP event seen by spacecraft at Earth, STEREO-A and STEREO-B at widely separated longitudes can be explained by diffusive shock acceleration by a single CME shock with a moderate speed.

astro-ph.SR↗
arXiv2022

Holographic complexity of rotating black holes with conical deficits

Based on the complexity equals action (CA) and complexity equals volume (CV) conjectures, we investigate the holographic complexity of a slowly accelerating Kerr-AdS black hole in the bulk Einstein gravity theory which is dual to holographic states with rotation and conical deficits in the boundary quantum system. Upon obtaining an implicit form of the Wheeler-DeWitt patch, we evaluate the action and show that the growth rate of the CA complexity violates volume-scaling formulation in large black hole limit due to the non-trivial contribution from the not-too-small acceleration of the black hole. Moreover, in an ensemble with fixed entropy, pressure, and angular momentum, we also find that complexity of formation decreases with both the average and difference of the conical deficits on the poles when the black hole is close to the static limit but increases with the deficits when the black hole is close to the extremal regime.

hep-th↗
arXiv2022

Gravitational decoupling for hairy black holes in asymptotically AdS spacetimes

In this study, the gravitational decoupling approach via extended geometric deformation is utilized to generate analytical black hole solutions owing to its simplicity and effectiveness. Considering the external fields surrounding Schwarzschild AdS black holes, we derive hairy black hole solutions in asymptotic AdS spacetime, satisfying the strong and dominant energy conditions. Moreover, we find that if the black hole spacetime is a fluid system, the fluid under each of these conditions is anisotropic.

gr-qc↗
arXiv2022

2D Human Pose Estimation with Explicit Anatomical Keypoints Structure Constraints

Recently, human pose estimation mainly focuses on how to design a more effective and better deep network structure as human features extractor, and most designed feature extraction networks only introduce the position of each anatomical keypoint to guide their training process. However, we found that some human anatomical keypoints kept their topology invariance, which can help to localize them more accurately when detecting the keypoints on the feature map. But to the best of our knowledge, there is no literature that has specifically studied it. Thus, in this paper, we present a novel 2D human pose estimation method with explicit anatomical keypoints structure constraints, which introduces the topology constraint term that consisting of the differences between the distance and direction of the keypoint-to-keypoint and their groundtruth in the loss object. More importantly, our proposed model can be plugged in the most existing bottom-up or top-down human pose estimation methods and improve their performance. The extensive experiments on the benchmark dataset: COCO keypoint dataset, show that our methods perform favorably against the most existing bottom-up and top-down human pose estimation methods, especially for Lite-HRNet, when our model is plugged into it, its AP scores separately raise by 2.9\% and 3.3\% on COCO val2017 and test-dev2017 datasets.

cs.CV↗
arXiv2022

TIER-A: Denoising Learning Framework for Information Extraction

With the development of deep neural language models, great progress has been made in information extraction recently. However, deep learning models often overfit on noisy data points, leading to poor performance. In this work, we examine the role of information entropy in the overfitting process and draw a key insight that overfitting is a process of overconfidence and entropy decreasing. Motivated by such properties, we propose a simple yet effective co-regularization joint-training framework TIER-A, Aggregation Joint-training Framework with Temperature Calibration and Information Entropy Regularization. Our framework consists of several neural models with identical structures. These models are jointly trained and we avoid overfitting by introducing temperature and information entropy regularization. Extensive experiments on two widely-used but noisy datasets, TACRED and CoNLL03, demonstrate the correctness of our assumption and the effectiveness of our framework.

cs.CL↗
arXiv2022

Spin-induced scalarization of Kerr-Newman black hole in extended scalar-tensor theory

With certain non-minimal coupling between a massless scalar field and the Gauss-Bonnet curvature invariant in the extended scalar-tensor-Gauss-Bonnet (ESTGB) field theory, tachyonic instability of Kerr-Newman (KN) black hole is promoted. Critical spin and charge for the onset of the spontaneous scalarization phenomenon for the KN black hole are calculated in the infinitely large coupling limit. Then analytical formula for the coupling-strength-dependent critical existence line is obtained for the black-hole-scalar-field configuration in a finite large coupling regime. Moreover, numerical methods are used to perform threshold curves which are boundaries between bald KN black holes and their hairy counterparts. Intriguingly, we get to know KN black hole can be scalarized in the vanishing spin limit in ESTGB theory.

gr-qc↗