Searcharxiv⌕ Search

arXiv subjects

Lei Wang

Publications and source records attributed to Lei Wang.

At least 883 records · Page 49Linked to original sources
arXiv2021

Robust Retinal Vessel Segmentation from a Data Augmentation Perspective

Retinal vessel segmentation is a fundamental step in screening, diagnosis, and treatment of various cardiovascular and ophthalmic diseases. Robustness is one of the most critical requirements for practical utilization, since the test images may be captured using different fundus cameras, or be affected by various pathological changes. We investigate this problem from a data augmentation perspective, with the merits of no additional training data or inference time. In this paper, we propose two new data augmentation modules, namely, channel-wise random Gamma correction and channel-wise random vessel augmentation. Given a training color fundus image, the former applies random gamma correction on each color channel of the entire image, while the latter intentionally enhances or decreases only the fine-grained blood vessel regions using morphological transformations. With the additional training samples generated by applying these two modules sequentially, a model could learn more invariant and discriminating features against both global and local disturbances. Experimental results on both real-world and synthetic datasets demonstrate that our method can improve the performance and robustness of a classic convolutional neural network architecture. The source code is available at \url{https://github.com/PaddlePaddle/Research/tree/master/CV/robust_vessel_segmentation}.

eess.IV↗
arXiv2021

Multiscale analysis of crystal defect formation in rapid solidification of pure aluminium and aluminium-copper alloys

Rapid solidification leads to unique microstructural features, where a less studied topic is the formation of various crystalline defects, including high dislocation densities, as well as gradients and splitting of the crystalline orientation. As these defects critically affect the material's mechanical properties and performance features, it is important to understand the defect formation mechanisms, and how they depend on the solidification conditions and alloying. To illuminate the formation mechanisms of the rapid solidification induced crystalline defects, we conduct a multiscale modeling analysis consisting of bond-order potential based molecular dynamics (MD), phase field crystal based amplitude expansion (PFC-AE) simulations, and sequentially coupled phase field -- crystal plasticity (PF--CP) simulations. The resulting dislocation densities are quantified and compared to past experiments. The atomistic approaches (MD, PFC) can be used to calibrate continuum level crystal plasticity models, and the framework adds mechanistic insights arising from the multiscale analysis.

cond-mat.mtrl-sci↗
arXiv2021

MWPToolkit: An Open-Source Framework for Deep Learning-Based Math Word Problem Solvers

Developing automatic Math Word Problem (MWP) solvers has been an interest of NLP researchers since the 1960s. Over the last few years, there are a growing number of datasets and deep learning-based methods proposed for effectively solving MWPs. However, most existing methods are benchmarked soly on one or two datasets, varying in different configurations, which leads to a lack of unified, standardized, fair, and comprehensive comparison between methods. This paper presents MWPToolkit, the first open-source framework for solving MWPs. In MWPToolkit, we decompose the procedure of existing MWP solvers into multiple core components and decouple their models into highly reusable modules. We also provide a hyper-parameter search function to boost the performance. In total, we implement and compare 17 MWP solvers on 4 widely-used single equation generation benchmarks and 2 multiple equations generation benchmarks. These features enable our MWPToolkit to be suitable for researchers to reproduce advanced baseline models and develop new MWP solvers quickly. Code and documents are available at https://github.com/LYH-YF/MWPToolkit.

cs.CL↗
arXiv2021

AIBench Scenario: Scenario-distilling AI Benchmarking

Modern real-world application scenarios like Internet services consist of a diversity of AI and non-AI modules with huge code sizes and long and complicated execution paths, which raises serious benchmarking or evaluating challenges. Using AI components or micro benchmarks alone can lead to error-prone conclusions. This paper presents a methodology to attack the above challenge. We formalize a real-world application scenario as a Directed Acyclic Graph-based model and propose the rules to distill it into a permutation of essential AI and non-AI tasks, which we call a scenario benchmark. Together with seventeen industry partners, we extract nine typical scenario benchmarks. We design and implement an extensible, configurable, and flexible benchmark framework. We implement two Internet service AI scenario benchmarks based on the framework as proxies to two real-world application scenarios. We consider scenario, component, and micro benchmarks as three indispensable parts for evaluating. Our evaluation shows the advantage of our methodology against using component or micro AI benchmarks alone. The specifications, source code, testbed, and results are publicly available from \url{https://www.benchcouncil.org/aibench/scenario/}.

cs.PF↗
arXiv2021

Large-Scale Secure XGB for Vertical Federated Learning

Privacy-preserving machine learning has drawn increasingly attention recently, especially with kinds of privacy regulations come into force. Under such situation, Federated Learning (FL) appears to facilitate privacy-preserving joint modeling among multiple parties. Although many federated algorithms have been extensively studied, there is still a lack of secure and practical gradient tree boosting models (e.g., XGB) in literature. In this paper, we aim to build large-scale secure XGB under vertically federated learning setting. We guarantee data privacy from three aspects. Specifically, (i) we employ secure multi-party computation techniques to avoid leaking intermediate information during training, (ii) we store the output model in a distributed manner in order to minimize information release, and (iii) we provide a novel algorithm for secure XGB predict with the distributed model. Furthermore, by proposing secure permutation protocols, we can improve the training efficiency and make the framework scale to large dataset. We conduct extensive experiments on both public datasets and real-world datasets, and the results demonstrate that our proposed XGB models provide not only competitive accuracy but also practical performance.

cs.LG↗
arXiv2021

Ultrahigh-Efficiency Second Harmonic Generation in a Reverse-Polarization Dual-Layer Crystalline Thin Film Nanophotonic Waveguide

Second harmonic generation (SHG), as one of the most significant \c{hi}(2) nonlinear optical processes, plays crucial roles in a broad variety of optical and photonic applications. Designing various delicate schemes to achieve highly efficient SHG has become a long standing and challenging topic in field of nonlinear optics. Despite numerous success on SHG based on birefringent phase matching and quasi-phase matching, so far, modal phase matching (MPM) for SHG in tightly light-confined structures has still in its infancy. Here, we propose a new scheme to realize highly-efficient SHG via MPM by using a nanophotonic LiNbO3 thin-film waveguide consists of two bonded layers with internally reversed polarizations. In such a dual-layer ridge waveguide based on lithium niobate on insulator, upon optical excitation at 1574.6 nm, we observe SHG at 787.3 nm with ultrahigh conversion efficiency of 5,540% /W/cm/cm experimentally. This work advances our understanding on modal-phase-matched SHG and other quadratic optical nonlinear process, offering additional strategies for development of high-performance nonlinear photonic devices in on-chip platforms.

physics.optics↗
arXiv2021

Tensor Representations for Action Recognition

Human actions in video sequences are characterized by the complex interplay between spatial features and their temporal dynamics. In this paper, we propose novel tensor representations for compactly capturing such higher-order relationships between visual features for the task of action recognition. We propose two tensor-based feature representations, viz. (i) sequence compatibility kernel (SCK) and (ii) dynamics compatibility kernel (DCK). SCK builds on the spatio-temporal correlations between features, whereas DCK explicitly models the action dynamics of a sequence. We also explore generalization of SCK, coined SCK(+), that operates on subsequences to capture the local-global interplay of correlations, which can incorporate multi-modal inputs e.g., skeleton 3D body-joints and per-frame classifier scores obtained from deep learning models trained on videos. We introduce linearization of these kernels that lead to compact and fast descriptors. We provide experiments on (i) 3D skeleton action sequences, (ii) fine-grained video sequences, and (iii) standard non-fine-grained videos. As our final representations are tensors that capture higher-order relationships of features, they relate to co-occurrences for robust fine-grained recognition. We use higher-order tensors and so-called Eigenvalue Power Normalization (EPN) which have been long speculated to perform spectral detection of higher-order occurrences, thus detecting fine-grained relationships of features rather than merely count features in action sequences. We prove that a tensor of order r, built from Z* dimensional features, coupled with EPN indeed detects if at least one higher-order occurrence is `projected' into one of its binom(Z*,r) subspaces of dim. r represented by the tensor, thus forming a Tensor Power Normalization metric endowed with binom(Z*,r) such `detectors'.

cs.CV↗
arXiv2021

Observability is Sufficient for the Design of Globally Exponentially Convergent State Observers for State-affine Nonlinear Systems

In this paper we are interested in the problem of state observation of state-affine nonlinear systems. Our main contribution is to propose a globally exponentially convergent observer that requires only the necessary assumption of observability of the system. To the best of the authors' knowledge this is the first time such a result is reported in the literature.

eess.SY↗
arXiv2021

Identifiability Implies Robust, Globally Exponentially Convergent On-line Parameter Estimation: Application to Model Reference Adaptive Control

In this paper we propose a new parameter estimator that ensures global exponential convergence of linear regression models requiring only the necessary assumption of identifiability of the regression equation,which we show is equivalent to interval excitation of the regressor vector. Continuous and discrete-time versions of the estimators are given. An extension to--separable and monotonic--non-linear parameterizations is also given. The estimators are shown to be robust to additive measurement noise and--not necessarily slow--parameter variations. Moreover, a version of the continuous-time estimator that rejects sinusoidal disturbances with unknown internal model is given. The estimator is shown to be applicable to the classical model reference adaptive control problem relaxing the conspicuous assumption of known sign of the high-frequency gain. Simulation results that illustrate the performance of the estimator are given.

eess.SY↗
arXiv2021

Cascade Bagging for Accuracy Prediction with Few Training Samples

Accuracy predictor is trained to predict the validation accuracy of an network from its architecture encoding. It can effectively assist in designing networks and improving Neural Architecture Search(NAS) efficiency. However, a high-performance predictor depends on adequate trainning samples, which requires unaffordable computation overhead. To alleviate this problem, we propose a novel framework to train an accuracy predictor under few training samples. The framework consists ofdata augmentation methods and an ensemble learning algorithm. The data augmentation methods calibrate weak labels and inject noise to feature space. The ensemble learning algorithm, termed cascade bagging, trains two-level models by sampling data and features. In the end, the advantages of above methods are proved in the Performance Prediciton Track of CVPR2021 1st Lightweight NAS Challenge. Our code is made public at: https://github.com/dlongry/Solutionto-CVPR2021-NAS-Track2.

cs.CV↗
arXiv2021

Improving Ranking Correlation of Supernet with Candidates Enhancement and Progressive Training

One-shot neural architecture search (NAS) applies weight-sharing supernet to reduce the unaffordable computation overhead of automated architecture designing. However, the weight-sharing technique worsens the ranking consistency of performance due to the interferences between different candidate networks. To address this issue, we propose a candidates enhancement method and progressive training pipeline to improve the ranking correlation of supernet. Specifically, we carefully redesign the sub-networks in the supernet and map the original supernet to a new one of high capacity. In addition, we gradually add narrow branches of supernet to reduce the degree of weight sharing which effectively alleviates the mutual interference between sub-networks. Finally, our method ranks the 1st place in the Supernet Track of CVPR2021 1st Lightweight NAS Challenge.

cs.CV↗
arXiv2021

Novel Two-Dimensional Layered MSi$_2$N$_4$ (M = Mo, W): New Promising Thermal Management Materials

With the miniaturization and integration of nanoelectronic devices, efficient heat removal becomes a key factor affecting the reliable operation of the nanoelectronic device. With the high intrinsic thermal conductivity, good mechanical flexibility, and precisely controlled growth, two-dimensional (2D) materials are widely accepted as ideal candidates for thermal management materials. In this work, by solving the phonon Boltzmann transport equation (BTE) based on first-principles calculations, we comprehensively investigated the thermal conductivity of novel 2D layered MSi$_2$N$_4$ (M = Mo, W). Our results point to competitive thermal conductivities (162 W/mK) of monolayer MoSi$_2$N$_4$, which is around two times larger than that of WSi$_2$N$_4$ and seven times larger than that of silicene despite their similar non-planar structures. It is revealed that the high thermal conductivity arises mainly from its large group velocity and low anharmonicity. Our result suggests that MoSi$_2$N$_4$ could be a potential candidate for 2D thermal management materials.

cond-mat.mtrl-sci↗
arXiv2021

Few-shot Unsupervised Domain Adaptation with Image-to-class Sparse Similarity Encoding

This paper investigates a valuable setting called few-shot unsupervised domain adaptation (FS-UDA), which has not been sufficiently studied in the literature. In this setting, the source domain data are labelled, but with few-shot per category, while the target domain data are unlabelled. To address the FS-UDA setting, we develop a general UDA model to solve the following two key issues: the few-shot labeled data per category and the domain adaptation between support and query sets. Our model is general in that once trained it will be able to be applied to various FS-UDA tasks from the same source and target domains. Inspired by the recent local descriptor based few-shot learning (FSL), our general UDA model is fully built upon local descriptors (LDs) for image classification and domain adaptation. By proposing a novel concept called similarity patterns (SPs), our model not only effectively considers the spatial relationship of LDs that was ignored in previous FSL methods, but also makes the learned image similarity better serve the required domain alignment. Specifically, we propose a novel IMage-to-class sparse Similarity Encoding (IMSE) method. It learns SPs to extract the local discriminative information for classification and meanwhile aligns the covariance matrix of the SPs for domain adaptation. Also, domain adversarial training and multi-scale local feature matching are performed upon LDs. Extensive experiments conducted on a multi-domain benchmark dataset DomainNet demonstrates the state-of-the-art performance of our IMSE for the novel setting of FS-UDA. In addition, for FSL, our IMSE can also show better performance than most of recent FSL methods on miniImageNet.

cs.CV↗
arXiv2021

Self-supervising Action Recognition by Statistical Moment and Subspace Descriptors

In this paper, we build on a concept of self-supervision by taking RGB frames as input to learn to predict both action concepts and auxiliary descriptors e.g., object descriptors. So-called hallucination streams are trained to predict auxiliary cues, simultaneously fed into classification layers, and then hallucinated at the testing stage to aid network. We design and hallucinate two descriptors, one leveraging four popular object detectors applied to training videos, and the other leveraging image- and video-level saliency detectors. The first descriptor encodes the detector- and ImageNet-wise class prediction scores, confidence scores, and spatial locations of bounding boxes and frame indexes to capture the spatio-temporal distribution of features per video. Another descriptor encodes spatio-angular gradient distributions of saliency maps and intensity patterns. Inspired by the characteristic function of the probability distribution, we capture four statistical moments on the above intermediate descriptors. As numbers of coefficients in the mean, covariance, coskewness and cokurtotsis grow linearly, quadratically, cubically and quartically w.r.t. the dimension of feature vectors, we describe the covariance matrix by its leading n' eigenvectors (so-called subspace) and we capture skewness/kurtosis rather than costly coskewness/cokurtosis. We obtain state of the art on five popular datasets such as Charades and EPIC-Kitchens.

cs.CV↗
arXiv2021

Factorizations of almost simple unitary groups

This is the second one in a series of papers classifying the factorizations of almost simple groups with nonsolvable factors. In this paper we deal with almost simple unitary groups.

math.GR↗
arXiv2021

Hand Image Understanding via Deep Multi-Task Learning

Analyzing and understanding hand information from multimedia materials like images or videos is important for many real world applications and remains active in research community. There are various works focusing on recovering hand information from single image, however, they usually solve a single task, for example, hand mask segmentation, 2D/3D hand pose estimation, or hand mesh reconstruction and perform not well in challenging scenarios. To further improve the performance of these tasks, we propose a novel Hand Image Understanding (HIU) framework to extract comprehensive information of the hand object from a single RGB image, by jointly considering the relationships between these tasks. To achieve this goal, a cascaded multi-task learning (MTL) backbone is designed to estimate the 2D heat maps, to learn the segmentation mask, and to generate the intermediate 3D information encoding, followed by a coarse-to-fine learning paradigm and a self-supervised learning strategy. Qualitative experiments demonstrate that our approach is capable of recovering reasonable mesh representations even in challenging situations. Quantitatively, our method significantly outperforms the state-of-the-art approaches on various widely-used datasets, in terms of diverse evaluation metrics.

cs.CV↗