arXiv subjects

Shuo Chen

Publications and source records attributed to Shuo Chen.

At least 181 records · Page 10Linked to original sources

arXiv2021

Contrastive Embedding for Generalized Zero-Shot Learning

Generalized zero-shot learning (GZSL) aims to recognize objects from both seen and unseen classes, when only the labeled examples from seen classes are provided. Recent feature generation methods learn a generative model that can synthesize the missing visual features of unseen classes to mitigate the data-imbalance problem in GZSL. However, the original visual feature space is suboptimal for GZSL classification since it lacks discriminative information. To tackle this issue, we propose to integrate the generation model with the embedding model, yielding a hybrid GZSL framework. The hybrid GZSL approach maps both the real and the synthetic samples produced by the generation model into an embedding space, where we perform the final GZSL classification. Specifically, we propose a contrastive embedding (CE) for our hybrid GZSL framework. The proposed contrastive embedding can leverage not only the class-wise supervision but also the instance-wise supervision, where the latter is usually neglected by existing GZSL researches. We evaluate our proposed hybrid GZSL framework with contrastive embedding, named CE-GZSL, on five benchmark datasets. The results show that our CEGZSL method can outperform the state-of-the-arts by a significant margin on three datasets. Our codes are available on https://github.com/Hanzy1996/CE-GZSL.

cs.CV↗

arXiv2020

Analytical prediction of electrowetting-induced jumping motion for droplets on textured hydrophobic substrates: Effects of the wetting states

Electric voltage applied in electrowetting can induce speading, sliding and even jumping of an individual droplet by changing the intrinsic balance of three-phase interfacial tensions, which has been widely used for droplet manipulating in microfluidics and lab-on-a-chip devices in over decades. In the present paper, we present an analytical prediction of jumping velocity for droplets electrowetting on textured hydrophobic surfaces with different wetting states. In particular, we consider a liquid droplet wetting on a textured hydrophobic substrate with a voltage applied between the droplet and the substrate. Once the voltage is turned off, the energy stored in the droplet during the electrowetting releases and could even result in the detachment of the droplet. The effects of the initial and electro-wetting states, i.e. Cassie-Baxter state and Wenzel state, on the jumping velocity of droplets are systematically discussed. Based on energy conservation, the energy conversion between the surface energy, internal viscous dissipation and the kinetic energy of droplets in different wetting states are analysed. The close-form formulas to predict the jumping velocity for different droplet wetting states are systematically derived. Finally, the unified form for predicting the electrowetting-induced jumping velocity of droplets on both flat and textured substrates with different wetting states is obtained, which can describe the jumping motion with various wetting conditions. This work provide theoretical insights on accurate control of the electrowetting-induced jumping motion of droplets on textured hydrophobic surfaces.

physics.flu-dyn↗

arXiv2020

Temperature-dependent properties of liquid-vapour coexistence system with many-body dissipative particle dynamics with energy conservation

The dynamic properties of fluid, including density, surface tension, diffusivity and viscosity, are temperature-dependent and can significantly influence the flow dynamics of mesoscopic non-isothermal systems. To capture the correct temperature-dependence of a fluid, a many-body dissipative particle dynamics model with energy conservation (mDPDe) is developed by combining the temperature-dependent coefficient of the conservative force and weighting terms of the dissipative and random forces. The momentum and thermal diffusivity, viscosity, and surface tension of liquid water at various temperatures ranging from 273 K to 373 K are used as examples for verifying the proposed model. Simulations of a periodic Poiseuille flow driven by body forces and heat sources are carried out to validate the diffusivity of the present model. Also, a steady case of heat conduction for reproducing the Fourier law is used to validate the thermal boundary conditions. By using this mDPDe simulations, the thermocapillary motion of liquid water nanodroplets on hydrophobic substrates with thermal gradients is investigated. The migration of the droplet is observed on flat substrates with gradient temperature. The velocity of the migration becomes larger for higher temperature difference, which is in agreement with the present theoretical analysis and DVDWT simulations. The results illustrate that the modified model can be used to study Marangoni effect on a nanodroplet and other heat and mass transfer problems with free interface.

physics.comp-ph↗

arXiv2020

Generalized Focal Loss: Learning Qualified and Distributed Bounding Boxes for Dense Object Detection

One-stage detector basically formulates object detection as dense classification and localization. The classification is usually optimized by Focal Loss and the box location is commonly learned under Dirac delta distribution. A recent trend for one-stage detectors is to introduce an individual prediction branch to estimate the quality of localization, where the predicted quality facilitates the classification to improve detection performance. This paper delves into the representations of the above three fundamental elements: quality estimation, classification and localization. Two problems are discovered in existing practices, including (1) the inconsistent usage of the quality estimation and classification between training and inference and (2) the inflexible Dirac delta distribution for localization when there is ambiguity and uncertainty in complex scenes. To address the problems, we design new representations for these elements. Specifically, we merge the quality estimation into the class prediction vector to form a joint representation of localization quality and classification, and use a vector to represent arbitrary distribution of box locations. The improved representations eliminate the inconsistency risk and accurately depict the flexible distribution in real data, but contain continuous labels, which is beyond the scope of Focal Loss. We then propose Generalized Focal Loss (GFL) that generalizes Focal Loss from its discrete form to the continuous version for successful optimization. On COCO test-dev, GFL achieves 45.0\% AP using ResNet-101 backbone, surpassing state-of-the-art SAPD (43.5\%) and ATSS (43.6\%) with higher or comparable inference speed, under the same backbone and training settings. Notably, our best model can achieve a single-model single-scale AP of 48.2\%, at 10 FPS on a single 2080Ti GPU. Code and models are available at https://github.com/implus/GFocal.

cs.CV↗

arXiv2019

Formal Specification and Verification of Smart Contracts for Azure Blockchain

Ensuring correctness of smart contracts is paramount to ensuring trust in blockchain-based systems. This paper studies the safety and security of smart contracts in the \emph{Azure Blockchain Workbench}, an enterprise Blockchain-as-a-Service offering from Microsoft. As part of this study, we formalize \emph{semantic conformance} of smart contracts against a state machine model with access-control policy and develop a highly-automated formal verifier for Solidity that can produce proofs as well as counterexamples. We have applied our verifier {\sc VeriSol} to analyze {\it all} contracts shipped with the Azure Blockchain Workbench, which includes application samples as well as a governance contract for Proof of Authority (PoA). We have found previously unknown bugs in these published smart contracts. After fixing these bugs, {\sc VeriSol} was able to successfully perform full verification for all of these contracts.

cs.PL↗

arXiv2019

GANSynth: Adversarial Neural Audio Synthesis

Efficient audio synthesis is an inherently difficult machine learning task, as human perception is sensitive to both global structure and fine-scale waveform coherence. Autoregressive models, such as WaveNet, model local structure at the expense of global latent structure and slow iterative sampling, while Generative Adversarial Networks (GANs), have global latent conditioning and efficient parallel sampling, but struggle to generate locally-coherent audio waveforms. Herein, we demonstrate that GANs can in fact generate high-fidelity and locally-coherent audio by modeling log magnitudes and instantaneous frequencies with sufficient frequency resolution in the spectral domain. Through extensive empirical investigations on the NSynth dataset, we demonstrate that GANs are able to outperform strong WaveNet baselines on automated and human evaluation metrics, and efficiently generate audio several orders of magnitude faster than their autoregressive counterparts.

cs.SD↗

arXiv2019

Revealing the Origin of Luminescence Center in 0D Cs4PbBr6 Perovskite

Zero dimensional perovskite Cs4PbBr6 has attracted considerable attention recently not only because of its highly efficient green photoluminescence (PL), but also its two highly debated opposing mechanisms of the luminescence: embedded CsPbBr3 nanocrystals versus intrinsic Br vacancy states. After a brief discussion on the root cause of the controversy, we provide sensitive but non-invasive methods that can not only directly correlate luminescence with the underlying structure, but also distinguish point defects from embedded nanostructures. We first synthesized both emissive and non-emissive Cs4PbBr6 crystals, obtained the complete Raman spectrum of Cs4PbBr6 and assigned all Raman bands based on density functional theory simulations. We then used correlated Raman-PL as a passive structure-property method to identify the difference between emissive and non-emissive Cs4PbBr6 crystals and revealed the existence of CsPbBr3 nanocrystals in emissive Cs4PbBr6. We finally employed a diamond anvil cell to probe the response of luminescence centers to hydrostatic pressure. The observations of fast red-shifting, diminishing and eventual disappearance of both green emission and Raman below Cs4PbBr6 phase transition pressure of ~3 GPa is compatible with CsPbBr3 nanocrystal inclusions as green PL emitters and cannot be explained by Br vacancies. The resolution of this long-lasting controversy paves the way for further device applications of low dimensional perovskites, and our comprehensive optical technique integrating structure-property with dynamic pressure response is generic and can be applied to other emerging optical materials to understand the nature of their luminescent centers.

cond-mat.mtrl-sci↗

arXiv2018

Self-cleaning of hydrophobic rough surfaces by coalescence-induced wetting transition

The superhydrophobic leaves of a lotus plant and other natural surfaces with self-cleaning function have been studied intensively for the development of artificial biomimetic surfaces. Surface roughness generated by hierarchical structures is a crucial property required for superhydrophobicity and self-cleaning. Here, we demonstrate a novel self-cleaning mechanism of textured surfaces attributed to a spontaneous coalescence-induced wetting transition. We focus on the wetting transition as it represents a new mechanism, which can explain why droplets on rough surfaces are able to change from the highly adhesive Wenzel state to the low-adhesion Cassie-Baxter state and achieve self-cleaning. In particular, we perform many-body dissipative particle dynamics simulations of liquid droplets sitting on mechanically textured substrates. We quantitatively investigate the wetting behavior of an isolated droplet as well as coalescence of droplets for both Cassie-Baxter and Wenzel states. Our simulation results reveal that droplets in the Cassie-Baxter state have much lower contact angle hysteresis and smaller hydrodynamic resistance than droplets in the Wenzel state. When small neighboring droplets coalesce into bigger ones on textured hydrophobic substrates, we observe a spontaneous wetting transition from a Wenzel state to a Cassie-Baxter state, which is powered by the surface energy released upon coalescence of the droplets. For superhydrophobic surfaces, the released surface energy may be sufficient to cause a jumping motion of droplets off the surface, in which case adding one more droplet to coalescence may increase the jumping velocity by one order of magnitude. When multiple droplets are involved, we find that the spatial distribution of liquid components in the coalesced droplet can be controlled by properly designing the overall arrangement of droplets and the distance between them.

physics.comp-ph↗

arXiv2018

Bright Luminescent Surface States on the Edges of Wide-bandgap Two-dimensional Lead Halide Perovskite

Three-dimensional lead halide perovskites have surprised people for their defect-tolerant electronic and optical properties, two-dimensional lead halide layered structures exhibit even more puzzling phenomena: luminescent edge states in Ruddlesden-Popper perovskites and conflicting reports of highly luminescent versus non-emissive CsPb$_{\text{2}}$Br$_{\text{5}}$. In this work, we report the observation of bright luminescent surface states on the edges of CsPb$_{\text{2}}$Br$_{\text{5}}$ microplatelets. We prove that green surface emission makes wide-bandgap single crystal CsPb$_{\text{2}}$Br$_{\text{5}}$ highly luminescent. Using polarized Raman spectroscopy and atomic-resolution transmission electron microscopy, we further prove that polycrystalline CsPb$_{\text{2}}$Br$_{\text{5}}$ is responsible for the bright luminescence. We propose that these bright edge states originate from corner-sharing clusters of PbBr$_{\text{6}}$ in the distorted regions between CsPb$_{\text{2}}$Br$_{\text{5}}$ nanocrystals. Because metal halide octahedrons are building blocks of perovskites, our discoveries settle a long-standing controversy over the basic property of CsPb$_{\text{2}}$Br$_{\text{5}}$ and open new opportunities to understand, design and engineer perovskite solar cells and other optoelectronic devices.

cond-mat.mtrl-sci↗

arXiv2018

Adversarial Metric Learning

In the past decades, intensive efforts have been put to design various loss functions and metric forms for metric learning problem. These improvements have shown promising results when the test data is similar to the training data. However, the trained models often fail to produce reliable distances on the ambiguous test pairs due to the distribution bias between training set and test set. To address this problem, the Adversarial Metric Learning (AML) is proposed in this paper, which automatically generates adversarial pairs to remedy the distribution bias and facilitate robust metric learning. Specifically, AML consists of two adversarial stages, i.e. confusion and distinguishment. In confusion stage, the ambiguous but critical adversarial data pairs are adaptively generated to mislead the learned metric. In distinguishment stage, a metric is exhaustively learned to try its best to distinguish both the adversarial pairs and the original training pairs. Thanks to the challenges posed by the confusion stage in such competing process, the AML model is able to grasp plentiful difficult knowledge that has not been contained by the original training pairs, so the discriminability of AML can be significantly improved. The entire model is formulated into optimization framework, of which the global convergence is theoretically proved. The experimental results on toy data and practical datasets clearly demonstrate the superiority of AML to the representative state-of-the-art metric learning methodologies.

cs.LG↗

arXiv2018

Understanding the Disharmony between Dropout and Batch Normalization by Variance Shift

This paper first answers the question "why do the two most powerful techniques Dropout and Batch Normalization (BN) often lead to a worse performance when they are combined together?" in both theoretical and statistical aspects. Theoretically, we find that Dropout would shift the variance of a specific neural unit when we transfer the state of that network from train to test. However, BN would maintain its statistical variance, which is accumulated from the entire learning procedure, in the test phase. The inconsistency of that variance (we name this scheme as "variance shift") causes the unstable numerical behavior in inference that leads to more erroneous predictions finally, when applying Dropout before BN. Thorough experiments on DenseNet, ResNet, ResNeXt and Wide ResNet confirm our findings. According to the uncovered mechanism, we next explore several strategies that modifies Dropout and try to overcome the limitations of their combination by avoiding the variance shift risks.

cs.LG↗

arXiv2017

Investigation on the reported superconductivity in intercalated black phosphorus

Superconductivity intrinsic to the intercalated black phosphorus (BP) with a transition temperature Tc of 3.8 K, independent of the intercalant, whether an alkali or an alkaline earth element, has been reported recently by R. Zhang et al. (2017). However, the reported Tc and the field effect on the superconducting (SC) transition both bear great similarities to those for the pure Sn, which is commonly used for BP synthesis under the vapor transport method. We have therefore decided to determine whether a minute amount of Sn is present in the starting high purity BP crystals and whether it is the culprit for the small SC signal detected. Energy-dispersive X-ray spectroscopy results confirmed the existence of Sn in the starting high purity BP crystals purchased from the same company as in R. Zhang et al. (2017). We have reproduced the SC transition at 3.8 K in Li- and Na-intercalated BP crystals that contain minute amounts of Sn when prepared by the vapor transport method but not in BP crystals that are free of Sn when prepared by the high-pressure method. We have therefore concluded that the SC transition reported by R. Zhang et al. (2017) is associated with the Sn but not intrinsic to the intercalated BP crystals.

cond-mat.supr-con↗

arXiv2017

New strategy for black phosphorus crystal growth through ternary clathrate

We are reporting a new synthetic strategy to grow large size black phosphorus (Black-P) crystals through a ternary clathrate Sn$_{24}$P$_{22-x}$I$_8$, under lower synthetic temperature and pressure. The Black-P crystals are found grown in situ at the site where the solid clathrate originally resides, which suggests chemical vapor mineralizer does not play a critical role for the Black-P formation. More detailed systematical studies has indicated the P vacancies in the framework of ternary clathrate Sn$_{24}$P$_{22-x}$I$_8$ is important for the subsequent Black-P from phosphorus vapors, and a likely Vapor-Solid-Solid (VSS) model is responsible for the Black-P crystal growth. The obtained room temperature mobility μ is ~ 350 $cm^2/Vs$ from Hall measurements at mechanically-cleaved flake, where noticeable micro-cracks are visible. The obtained high mobility value further suggest the high quality of the Black-P crystals synthesized through this route.

cond-mat.mtrl-sci↗

arXiv2017

An Efficient Fog-Assisted Unstable Sensor Detection Scheme with Privacy Preserved

The Internet of Thing (IoT) has been a hot topic in both research community and industry. It is anticipated that in future IoT, an enormous number of sensors will collect the physical information every moment to enable the control center making better decisions to improve the quality of service (QoS). However, the sensors maybe faulty and thus generate inaccurate data which would compromise the decision making. To guarantee the QoS, the system should be able to detect faulty sensors so as to eliminate the damages of inaccurate data. Various faulty sensor detection mechanisms have been developed in the context of wireless sensor network (WSN). Some of them are only fit for WSN while the others would bring a communication burden to control center. To detect the faulty sensors for general IoT applications and save the communication resource at the same time, an efficient faulty sensor detection scheme is proposed in this paper. The proposed scheme takes advantage of fog computing to save the computation and communication resource of control center. To preserve the privacy of sensor data, the Paillier Cryptosystem is adopted in the fog computing. The batch verification technique is applied to achieve efficient authentication. The performance analyses are presented to demonstrate that the proposed detection scheme is able to conserve the communication resource of control center and achieve a high true positive ratio while maintaining an acceptable false positive ratio. The scheme could also withstand various security attacks and preserve data privacy.

cs.CR↗

arXiv2017

Network induced large correlation matrix estimation

The correlation matrix of massive biomedical data (e.g. gene expression or neuroimaging data) often exhibits a complex and organized, yet latent graph topological structure. We propose a two step procedure that first detects the latent graph topology with parsimony from the sample correlation matrix and then regularizes the correlation matrix by leveraging the detected graph topological information. We show that the graph topological information guided thresholding can reduce false positive and false negative rates simultaneously because it allows edges to borrow strengths from each other precisely. Several examples illustrate that the parsimoniously detected latent graph topological structures may reveal underlying biological networks and guide correlation matrix estimation.

stat.AP↗

arXiv2017

A Flexible Privacy-preserving Framework for Singular Value Decomposition under Internet of Things Environment

The singular value decomposition (SVD) is a widely used matrix factorization tool which underlies plenty of useful applications, e.g. recommendation system, abnormal detection and data compression. Under the environment of emerging Internet of Things (IoT), there would be an increasing demand for data analysis to better human's lives and create new economic growth points. Moreover, due to the large scope of IoT, most of the data analysis work should be done in the network edge, i.e. handled by fog computing. However, the devices which provide fog computing may not be trustable while the data privacy is often the significant concern of the IoT application users. Thus, when performing SVD for data analysis purpose, the privacy of user data should be preserved. Based on the above reasons, in this paper, we propose a privacy-preserving fog computing framework for SVD computation. The security and performance analysis shows the practicability of the proposed framework. Furthermore, since different applications may utilize the result of SVD operation in different ways, three applications with different objectives are introduced to show how the framework could flexibly achieve the purposes of different applications, which indicates the flexibility of the design.

cs.DC↗

arXiv2017

Deep Multi-Species Embedding

Understanding how species are distributed across landscapes over time is a fundamental question in biodiversity research. Unfortunately, most species distribution models only target a single species at a time, despite strong ecological evidence that species are not independently distributed. We propose Deep Multi-Species Embedding (DMSE), which jointly embeds vectors corresponding to multiple species as well as vectors representing environmental covariates into a common high-dimensional feature space via a deep neural network. Applied to bird observational data from the citizen science project \textit{eBird}, we demonstrate how the DMSE model discovers inter-species relationships to outperform single-species distribution models (random forests and SVMs) as well as competing multi-label models. Additionally, we demonstrate the benefit of using a deep neural network to extract features within the embedding and show how they improve the predictive performance of species distribution modelling. An important domain contribution of the DMSE model is the ability to discover and describe species interactions while simultaneously learning the shared habitat preferences among species. As an additional contribution, we provide a graphical embedding of hundreds of bird species in the Northeast US.

cs.LG↗

arXiv2017

A Network Object Method to Uncover Hidden Disorder-Related Brain Connectome

Neuropsychiatric disorders impact functional connectivity of the brain at the network level. The identification and statistical testing of disorder-related networks remains challenging. We propose novel methods to streamline the detection and testing of the hidden, disorder-related connectivity patterns as network-objects. We define an abnormal connectome subnetwork as a network-object that includes three classes: nodes of brain areas, edges representing brain connectomic features, and an organized graph topology formed by these nodes and edges. Comparing to the conventional statistical methods, the proposed approach simultaneously reduces false positive and negative discovery rates by letting edges borrow strengths precisely with the guidance of graph topological information, which effectively improves the reproducibility of findings across brain connectome studies. The network-object analyses may provide insights into how brain connectome is systematically impaired by brain illnesses.

stat.AP↗