arXiv subjects

Zhenyu Yuan

Publications and source records attributed to Zhenyu Yuan.

6 recordsLinked to original sources

arXiv2026

LH2Face: Loss function for Hard High-quality Face

In current practical face authentication systems, most face recognition (FR) algorithms are based on cosine similarity with softmax classification. Despite its reliable classification performance, this method struggles with hard samples. A popular strategy to improve FR performance is incorporating angular or cosine margins. However, it does not take face quality or recognition hardness into account, simply increasing the margin value and thus causing an overly uniform training strategy. To address this problem, a novel loss function is proposed, named Loss function for Hard High-quality Face (LH2Face). Firstly, a similarity measure based on the von Mises-Fisher (vMF) distribution is stated, specifically focusing on the logarithm of the Probability Density Function (PDF), which represents the distance between a probability distribution and a vector. Then, an adaptive margin-based multi-classification method using softmax, called the Uncertainty-Aware Margin Function, is implemented in the article. Furthermore, proxy-based loss functions are used to apply extra constraints between the proxy and sample to optimize their representation space distribution. Finally, a renderer is constructed that optimizes FR through face reconstruction and vice versa. Our LH2Face is superior to similiar schemes on hard high-quality face datasets, achieving 49.39% accuracy on the IJB-B dataset, which surpasses the second-place method by 2.37%.

cs.CV↗

arXiv2025

Charge-polarized superconducting state emerging in a superatomic antipolar metal

The simultaneous presence of polarity and metallicity or superconductivity in a material signifies the exotic polar metallic or superconducting (SC) state, while such materials are extremely rare due to their exclusive nature. Recently, the interweaved CDW and antipolar charge orders have been discovered in a metallic superatomic crystal of Au6Te12Se8 (ATS), while their interplay and competition with the following emergent SC state remains elusive. Here, we report a further experimental investigation of the SC state emerged from the preformed CDW and antipolar order states using scanning tunneling microscopy/spectroscopy in combination with transport and Raman measurements. The temperature-dependent pre-formation and condensation of Cooper pairs are experimentally identified. The pre-existent CDW is gradually suppressed by the preformed Cooper pairs, and then the antipolar charge order is spatially suppressed into a ferrielectric-like polar order by the condensed Cooper pairs of SC state. The exotic charge-polarized superconducting state is discovered in the polar metal of ATS, suggesting a valuable platform for the exploration of intriguing polar superconducting properties.

cond-mat.supr-con↗

arXiv2024

Evidence for an Excitonic Insulator State in Ta$_2$Pd$_3$Te$_5$

The excitonic insulator (EI) is an exotic ground state of narrow-gap semiconductors and semimetals arising from spontaneous condensation of electron-hole pairs bound by attractive Coulomb interaction. Despite research on EIs dating back to half a century ago, their existence in real materials remains a subject of ongoing debate. In this study, through systematic experimental and theoretical investigations, we provide evidence for the existence of an EI ground state in a van der Waals compound Ta$_2$Pd$_3$Te$_5$. Density-functional-theory calculations suggest that it is a semimetal with a small band overlap, whereas various experiments exhibit an insulating ground state with a clear band gap. Upon incorporating electron-hole Coulomb interaction into our calculations, we obtain an EI phase where the electronic symmetry breaking opens a many-body gap. Angle-resolved photoemission spectroscopy measurements exhibit that the band gap is closed with a significant change in the dispersions as the number of thermally excited charge carriers becomes sufficiently large in both equilibrium and nonequilibrium states. Structural measurements reveal a slight breaking of crystal symmetry with exceptionally small lattice distortion in the insulating state, which cannot account for the significant gap opening. Therefore, we attribute the insulating ground state with a gap opening in Ta$_2$Pd$_3$Te$_5$ to exciton condensation, where the coupling to the symmetry-breaking electronic state induces a subtle change in the crystal structure.

cond-mat.mtrl-sci↗

arXiv2021

Charge instability of topological Fermi arcs in chiral crystal CoSi

Topological boundary states, emerged at the spatial boundary between topological non-trivial and trivial phases, are usually gapless, or commonly referred as metallic states. For example, the surface state of a topological insulator is a gapless Dirac state. These metallic topological boundary states are typically well described by non-interacting fermions. However, the behavior of topological boundary states with significant electron-electron interactions, which could turn the gapless boundary states into gapped ordered states, e.g., density wave states or superconducting states, is of great interest theoretically, but is still lacking evidence experimentally. Here, we report the observation of incommensurable charge density wave (CDW) formed on the topological boundary states driven by the electron-electron interactions on the (001) surface of CoSi. The wavevector of CDW varies as the temperature changes, which coincides with the evolution of topological surface Fermi arcs with temperature. The orientation of CDW phase is determined by the chirality of the Fermi arcs, which indicates direct association between CDW and Fermi arcs. Our finding will stimulate the search of more interactions-driven ordered states, such as superconductivity and magnetism, on the boundaries of topological materials.

cond-mat.str-el↗

arXiv2021

A convolutional neural network for prestack fracture detection

Fractures are widely developed in hydrocarbon reservoirs and constitute the accumulation spaces and transport channels of oil and gas. Fracture detection is a fundamental task for reservoir characterization. From prestack seismic gathers, anisotropic analysis and inversion were commonly applied to characterize the dominant orientations and relative intensities of fractures. However, the existing methods were mostly based on the vertical aligned facture hypothesis, it is impossible for them to recognize fracture dip. Furthermore, it is difficult or impractical for existing methods to attain the real fracture densities. Based on data-driven deep learning, this paper designed a convolutional neural network to perform prestack fracture detection. Capitalizing on the connections between seismic responses and fracture parameters, a suitable azimuth dataset was firstly generated through fracture effective medium modeling and anisotropic plane wave analyzing. Then a multi-input and multi-output convolutional neural network was constructed to simultaneously detect fracture density, dip and strike azimuth. The application on a practical survey validated the effectiveness of the proposed CNN model.

physics.geo-ph↗

arXiv2020

Hybrid-DNNs: Hybrid Deep Neural Networks for Mixed Inputs

Rapid development of big data and high-performance computing have encouraged explosive studies of deep learning in geoscience. However, most studies only take single-type data as input, frittering away invaluable multisource, multi-scale information. We develop a general architecture of hybrid deep neural networks (HDNNs) to support mixed inputs. Regarding as a combination of feature learning and target learning, the new proposed networks provide great capacity in high-hierarchy feature extraction and in-depth data mining. Furthermore, the hybrid architecture is an aggregation of multiple networks, demonstrating good flexibility and wide applicability. The configuration of multiple networks depends on application tasks and varies with inputs and targets. Concentrating on reservoir production prediction, a specific HDNN model is configured and applied to an oil development block. Considering their contributions to hydrocarbon production, core photos, logging images and curves, geologic and engineering parameters can all be taken as inputs. After preprocessing, the mixed inputs are prepared as regular-sampled structural and numerical data. For feature learning, convolutional neural networks (CNN) and multilayer perceptron (MLP) network are configured to separately process structural and numerical inputs. Learned features are then concatenated and fed to subsequent networks for target learning. Comparison with typical MLP model and CNN model highlights the superiority of proposed HDNN model with high accuracy and good generalization.

cs.LG↗