Searcharxiv⌕ Search

arXiv subjects

Wei Yao

Publications and source records attributed to Wei Yao.

At least 109 records · Page 6Linked to original sources
arXiv2021

A new weakly supervised approach for ALS point cloud semantic segmentation

While there are novel point cloud semantic segmentation schemes that continuously surpass state-of-the-art results, the success of learning an effective model usually rely on the availability of abundant labeled data. However, data annotation is a time-consuming and labor-intensive task, particularly for large-scale airborne laser scanning (ALS) point clouds involving multiple classes in urban areas. Thus, how to attain promising results while largely reducing labeling works become an essential issue. In this study, we propose a deep-learning based weakly supervised framework for semantic segmentation of ALS point clouds, exploiting potential information from unlabeled data subject to incomplete and sparse labels. Entropy regularization is introduced to penalize the class overlap in predictive probability. Additionally, a consistency constraint by minimizing the discrepancy distance between instant and ensemble predictions is designed to improve the robustness of predictions. Finally, we propose an online soft pseudo-labeling strategy to create extra supervisory sources in an efficient and nonpaprametric way. Extensive experimental analysis using three benchmark datasets demonstrates that in case of sparse point annotations, our proposed method significantly boosts the classification performance without compromising the computational efficiency. It outperforms current weakly supervised methods and achieves a comparable result against full supervision competitors. For the ISPRS 3D Labeling Vaihingen data, by using only 0.1% of labels, our method achieves an overall accuracy of 83.0% and an average F1 score of 70.0%, which have increased by 6.9% and 12.8% respectively, compared to model trained by sparse label information only.

cs.CV↗
arXiv2021

Experimental evidence of plasmarons and effective fine structure constant in electron-doped graphene/h-BN heterostructure

Electron-electron interaction is fundamental in condensed matter physics and can lead to composite quasiparticles called plasmarons, which strongly renormalize the dispersion and carry information of electron-electron coupling strength as defined by the effective fine structure constant $α_{ee}^*$. Although h-BN with unique dielectric properties has been widely used as an important substrate for graphene, so far there is no experimental report of plasmarons in graphene/h-BN yet. Here, we report direct experimental observation of plasmaron dispersion in graphene/h-BN heterostructures through angle-resolved photoemission spectroscopy (ARPES) measurements upon {\it in situ} electron doping. Characteristic diamond-shaped dispersion is observed near the Dirac cone in both 0$^\circ$ (aligned) and 13.5$^\circ$ (twisted) graphene/h-BN, and the electron-electron interaction strength $α_{ee}^*$ is extracted to be $α_{ee}^*\approx0.9\pm 0.1$, highlighting the important role of electron-electron interaction. Our results suggest graphene/h-BN as an ideal platform for investigating strong electron-electron interaction with weak dielectric screening, and lays fundamental physics for gate-tunable nano-electronics and nano-plasmonics.

cond-mat.mes-hall↗
arXiv2021

Double Deep Q-learning Based Real-Time Optimization Strategy for Microgrids

The uncertainties from distributed energy resources (DERs) bring significant challenges to the real-time operation of microgrids. In addition, due to the nonlinear constraints in the AC power flow equation and the nonlinearity of the battery storage model, etc., the optimization of the microgrid is a mixed-integer nonlinear programming (MINLP) problem. It is challenging to solve this kind of stochastic nonlinear optimization problem. To address the challenge, this paper proposes a deep reinforcement learning (DRL) based optimization strategy for the real-time operation of the microgrid. Specifically, we construct the detailed operation model for the microgrid and formulate the real-time optimization problem as a Markov Decision Process (MDP). Then, a double deep Q network (DDQN) based architecture is designed to solve the MINLP problem. The proposed approach can learn a near-optimal strategy only from the historical data. The effectiveness of the proposed algorithm is validated by the simulations on a 10-bus microgrid system and a modified IEEE 69-bus microgrid system. The numerical simulation results demonstrate that the proposed approach outperforms several existing methods.

eess.SY↗
arXiv2021

Self-supervised Depth Estimation Leveraging Global Perception and Geometric Smoothness Using On-board Videos

Self-supervised depth estimation has drawn much attention in recent years as it does not require labeled data but image sequences. Moreover, it can be conveniently used in various applications, such as autonomous driving, robotics, realistic navigation, and smart cities. However, extracting global contextual information from images and predicting a geometrically natural depth map remain challenging. In this paper, we present DLNet for pixel-wise depth estimation, which simultaneously extracts global and local features with the aid of our depth Linformer block. This block consists of the Linformer and innovative soft split multi-layer perceptron blocks. Moreover, a three-dimensional geometry smoothness loss is proposed to predict a geometrically natural depth map by imposing the second-order smoothness constraint on the predicted three-dimensional point clouds, thereby realizing improved performance as a byproduct. Finally, we explore the multi-scale prediction strategy and propose the maximum margin dual-scale prediction strategy for further performance improvement. In experiments on the KITTI and Make3D benchmarks, the proposed DLNet achieves performance competitive to those of the state-of-the-art methods, reducing time and space complexities by more than $62\%$ and $56\%$, respectively. Extensive testing on various real-world situations further demonstrates the strong practicality and generalization capability of the proposed model.

cs.CV↗
arXiv2021

Self-energy dynamics and mode-specific phonon threshold effect in a Kekulé-ordered graphene

Electron-phonon interaction and related self-energy are fundamental to both the equilibrium properties and non-equilibrium relaxation dynamics of solids. Although electron-phonon interaction has been suggested by various time-resolved measurements to be important for the relaxation dynamics of graphene, the lack of energy- and momentum-resolved self-energy dynamics prohibits direct identification of the role of specific phonon modes in the relaxation dynamics. Here by performing time- and angle-resolved photoemission spectroscopy measurements on a Kekulé-ordered graphene with folded Dirac cones at the $Γ$ point, we have succeeded in resolving the self-energy effect induced by coupling of electrons to two phonons at $Ω_1$ = 177 meV and $Ω_2$ = 54 meV and revealing its dynamical change in the time domain. Moreover, these strongly coupled phonons define energy thresholds, which separate the hierarchical relaxation dynamics from ultrafast, fast to slow, thereby providing direct experimental evidence for the dominant role of mode-specific phonons in the relaxation dynamics

cond-mat.mes-hall↗
arXiv2021

Experimental evidence of chiral symmetry breaking in Kekulé-ordered graphene

The low-energy excitations of graphene are relativistic massless Dirac fermions with opposite chiralities at valleys K and K'. Breaking the chiral symmetry could lead to gap opening in analogy to dynamical mass generation in particle physics. Here we report direct experimental evidences of chiral symmetry breaking (CSB) from both microscopic and spectroscopic measurements in a Li-intercalated graphene. The CSB is evidenced by gap opening at the Dirac point, Kekulé-O type modulation, and chirality mixing near the gap edge. Our work opens up opportunities for investigating CSB related physics in a Kekulé-ordered graphene.

cond-mat.mes-hall↗
arXiv2021

In the Danger Zone: U-Net Driven Quantile Regression can Predict High-risk SARS-CoV-2 Regions via Pollutant Particulate Matter and Satellite Imagery

Since the outbreak of COVID-19 policy makers have been relying upon non-pharmacological interventions to control the outbreak. With air pollution as a potential transmission vector there is need to include it in intervention strategies. We propose a U-net driven quantile regression model to predict $PM_{2.5}$ air pollution based on easily obtainable satellite imagery. We demonstrate that our approach can reconstruct $PM_{2.5}$ concentrations on ground-truth data and predict reasonable $PM_{2.5}$ values with their spatial distribution, even for locations where pollution data is unavailable. Such predictions of $PM_{2.5}$ characteristics could crucially advise public policy strategies geared to reduce the transmission of and lethality of COVID-19.

cs.CV↗
arXiv2021

Weakly Supervised Pseudo-Label assisted Learning for ALS Point Cloud Semantic Segmentation

Competitive point cloud semantic segmentation results usually rely on a large amount of labeled data. However, data annotation is a time-consuming and labor-intensive task, particularly for three-dimensional point cloud data. Thus, obtaining accurate results with limited ground truth as training data is considerably important. As a simple and effective method, pseudo labels can use information from unlabeled data for training neural networks. In this study, we propose a pseudo-label-assisted point cloud segmentation method with very few sparsely sampled labels that are normally randomly selected for each class. An adaptive thresholding strategy was proposed to generate a pseudo-label based on the prediction probability. Pseudo-label learning is an iterative process, and pseudo labels were updated solely on ground-truth weak labels as the model converged to improve the training efficiency. Experiments using the ISPRS 3D sematic labeling benchmark dataset indicated that our proposed method achieved an equally competitive result compared to that using a full supervision scheme with only up to 2$\unicode{x2030}$ of labeled points from the original training set, with an overall accuracy of 83.7% and an average F1 score of 70.2%.

cs.CV↗
arXiv2021

Instance segmentation of fallen trees in aerial color infrared imagery using active multi-contour evolution with fully convolutional network-based intensity priors

In this paper, we introduce a framework for segmenting instances of a common object class by multiple active contour evolution over semantic segmentation maps of images obtained through fully convolutional networks. The contour evolution is cast as an energy minimization problem, where the aggregate energy functional incorporates a data fit term, an explicit shape model, and accounts for object overlap. Efficient solution neighborhood operators are proposed, enabling optimization through metaheuristics such as simulated annealing. We instantiate the proposed framework in the context of segmenting individual fallen stems from high-resolution aerial multispectral imagery. We validated our approach on 3 real-world scenes of varying complexity. The test plots were situated in regions of the Bavarian Forest National Park, Germany, which sustained a heavy bark beetle infestation. Evaluations were performed on both the polygon and line segment level, showing that the multi-contour segmentation can achieve up to 0.93 precision and 0.82 recall. An improvement of up to 7 percentage points (pp) in recall and 6 in precision compared to an iterative sample consensus line segment detection was achieved. Despite the simplicity of the applied shape parametrization, an explicit shape model incorporated into the energy function improved the results by up to 4 pp of recall. Finally, we show the importance of using a deep learning based semantic segmentation method as the basis for individual stem detection. Our method is a step towards increased accessibility of automatic fallen tree mapping, due to higher cost efficiency of aerial imagery acquisition compared to laser scanning. The precise fallen tree maps could be further used as a basis for plant and animal habitat modeling, studies on carbon sequestration as well as soil quality in forest ecosystems.

cs.CV↗
arXiv2021

Pairwise Point Cloud Registration using Graph Matching and Rotation-invariant Features

Registration is a fundamental but critical task in point cloud processing, which usually depends on finding element correspondence from two point clouds. However, the finding of reliable correspondence relies on establishing a robust and discriminative description of elements and the correct matching of corresponding elements. In this letter, we develop a coarse-to-fine registration strategy, which utilizes rotation-invariant features and a new weighted graph matching method for iteratively finding correspondence. In the graph matching method, the similarity of nodes and edges in Euclidean and feature space are formulated to construct the optimization function. The proposed strategy is evaluated using two benchmark datasets and compared with several state-of-the-art methods. Regarding the experimental results, our proposed method can achieve a fine registration with rotation errors of less than 0.2 degrees and translation errors of less than 0.1m.

cs.CV↗
arXiv2020

Generalized Operating Procedure for Deep Learning: an Unconstrained Optimal Design Perspective

Deep learning (DL) has brought about remarkable breakthrough in processing images, video and speech due to its efficacy in extracting highly abstract representation and learning very complex functions. However, there is seldom operating procedure reported on how to make it for real use cases. In this paper, we intend to address this problem by presenting a generalized operating procedure for DL from the perspective of unconstrained optimal design, which is motivated by a simple intension to remove the barrier of using DL, especially for those scientists or engineers who are new but eager to use it. Our proposed procedure contains seven steps, which are project/problem statement, data collection, architecture design, initialization of parameters, defining loss function, computing optimal parameters, and inference, respectively. Following this procedure, we build a multi-stream end-to-end speaker verification system, in which the input speech utterance is processed by multiple parallel streams within different frequency range, so that the acoustic modeling can be more robust resulting from the diversity of features. Trained with VoxCeleb dataset, our experimental results verify the effectiveness of our proposed operating procedure, and also show that our multi-stream framework outperforms single-stream baseline with 20 % relative reduction in minimum decision cost function (minDCF).

cs.LG↗
arXiv2020

Progress on band structure engineering of twisted bilayer and two-dimensional moiré heterostructures

Artificially constructed van der Waals heterostructures (vdWHs) provide an ideal platform for realizing emerging quantum phenomena in condensed matter physics. Two methods for building vdWHs have been developed: stacking two-dimensional (2D) materials into a bilayer structure with different lattice constants, or with different orientations. The interlayer coupling stemming from commensurate or incommensurate superlattice pattern plays an important role in vdWHs for modulating the band structures and generating new electronic states. In this article, we review a series of novel quantum states discovered in two model vdWH systems -- graphene/hexagonal boron nitride (hBN) hetero-bilayer and twisted bilayer graphene (tBLG), and discuss how the electronic structures are modified by such stacking and twisting. We also provide perspectives for future studies on hetero-bilayer materials, from which an expansion of 2D material phase library is expected.

cond-mat.mtrl-sci↗
arXiv2019

Water harvesting from Soils by Solar-to-Heat Induced Evaporation and Capillary Water Migration

Fresh water scarcity is one of the critical challenges for global sustainable development. Several novel water resources such as passive seawater solar desalination and atmospheric water harvesting have made some progress in recent years. However, no investigation has referred to harvesting water from shallow subsurface soils, which are potential huge water reservoirs. Here, we introduce a method of solar-driven water harvesting from soils, which can provide cheap fresh water in impoverished, arid and decentralized areas. The concentrated solar energy is used to heat the soils to evaporate the soil moisture. Then vapors flow to the condenser through tubes and condense as freshwater. Sustainable water harvesting is realized by water migration due to capillary pumping effect within soils. In the laboratory condition, an experimental setup is designed and its water-harvesting ability from soils is investigated. The maximum water mass harvesting rate was 99.8 g h-1. In about 12 h, the total harvesting water could be as high as about 900 ml. The whole process is solar-driven and spontaneous without other mechanical or electrical ancillaries. The water harvesting rate under one sun energy flux (1 kW m-2) is estimated to be about 360 g h-1 with a 1 m2 solar concentrator. Our proposal provides a potential onsite and sustainable fresh water supply solution to deal with the water scarcity problem.

physics.app-ph↗
arXiv2019

Electronic structure of molecular beam epitaxy grown 1T$^\prime$-MoTe$_2$ film and strain effect

Atomically thin transition metal dichalcogenide films with distorted trigonal (1T$^\prime$) phase have been predicted to be candidates for realizing quantum spin Hall effect. Growth of 1T$^\prime$ film and experimental investigation of its electronic structure are critical. Here we report the electronic structure of 1T$^\prime$-MoTe$_2$ films grown by molecular beam epitaxy (MBE). Growth of the 1T$^\prime$-MoTe$_2$ film depends critically on the substrate temperature, and successful growth of the film is indicated by streaky stripes in the reflection high energy electron diffraction and sharp diffraction spots in low energy electron diffraction. Angle-resolved photoemission spectroscopy measurements reveal a metallic behavior in the as-grown film with an overlap between the conduction and valence bands. First principles calculation suggests that a suitable tensile strain along the a-axis direction is needed to induce a gap to make it an insulator. Our work not only reports the electronic structure of MBE grown 1T$^\prime$-MoTe$_2$ films, but also provides insights for strain engineering to make it possible for quantum spin Hall effect.

cond-mat.mtrl-sci↗
arXiv2019

Disorder induced multifractal superconductivity in monolayer niobium dichalcogenides

The interplay between disorder and superconductivity is a subtle and fascinating phenomenon in quantum many body physics. The conventional superconductors are insensitive to dilute nonmagnetic impurities, known as the Anderson's theorem. Destruction of superconductivity and even superconductor-insulator transitions occur in the regime of strong disorder. Hence disorder-enhanced superconductivity is rare and has only been observed in some alloys or granular states. Because of the entanglement of various effects, the mechanism of enhancement is still under debate. Here we report well-controlled disorder effect in the recently discovered monolayer NbSe$_2$ superconductor. The superconducting transition temperatures of NbSe$_2$ monolayers are substantially increased by disorder. Realistic theoretical modeling shows that the unusual enhancement possibly arises from the multifractality of electron wave functions. This work provides the first experimental evidence of the multifractal superconducting state.

cond-mat.supr-con↗
arXiv2019

Deep Clustering With Intra-class Distance Constraint for Hyperspectral Images

The high dimensionality of hyperspectral images often results in the degradation of clustering performance. Due to the powerful ability of deep feature extraction and non-linear feature representation, the clustering algorithm based on deep learning has become a hot research topic in the field of hyperspectral remote sensing. However, most deep clustering algorithms for hyperspectral images utilize deep neural networks as feature extractor without considering prior knowledge constraints that are suitable for clustering. To solve this problem, we propose an intra-class distance constrained deep clustering algorithm for high-dimensional hyperspectral images. The proposed algorithm constrains the feature mapping procedure of the auto-encoder network by intra-class distance so that raw images are transformed from the original high-dimensional space to the low-dimensional feature space that is more conducive to clustering. Furthermore, the related learning process is treated as a joint optimization problem of deep feature extraction and clustering. Experimental results demonstrate the intense competitiveness of the proposed algorithm in comparison with state-of-the-art clustering methods of hyperspectral images.

cs.LG↗