arXiv subjects

Yang Hu

Publications and source records attributed to Yang Hu.

At least 199 records · Page 11Linked to original sources

arXiv2020

Data Augmentation Imbalance For Imbalanced Attribute Classification

Pedestrian attribute recognition is an important multi-label classification problem. Although the convolutional neural networks are prominent in learning discriminative features from images, the data imbalance in multi-label setting for fine-grained tasks remains an open problem. In this paper, we propose a new re-sampling algorithm called: data augmentation imbalance (DAI) to explicitly enhance the ability to discriminate the fewer attributes via increasing the proportion of labels accounting for a small part. Fundamentally, by applying over-sampling and under-sampling on the multi-label dataset at the same time, the thought of robbing the rich attributes and helping the poor makes a significant contribution to DAI. Extensive empirical evidence shows that our DAI algorithm achieves state-of-the-art results, based on pedestrian attribute datasets, i.e. standard PA-100K and PETA datasets.

cs.CV↗

arXiv2020

Multiple Attentional Pyramid Networks for Chinese Herbal Recognition

Chinese herbs play a critical role in Traditional Chinese Medicine. Due to different recognition granularity, they can be recognized accurately only by professionals with much experience. It is expected that they can be recognized automatically using new techniques like machine learning. However, there is no Chinese herbal image dataset available. Simultaneously, there is no machine learning method which can deal with Chinese herbal image recognition well. Therefore, this paper begins with building a new standard Chinese-Herbs dataset. Subsequently, a new Attentional Pyramid Networks (APN) for Chinese herbal recognition is proposed, where both novel competitive attention and spatial collaborative attention are proposed and then applied. APN can adaptively model Chinese herbal images with different feature scales. Finally, a new framework for Chinese herbal recognition is proposed as a new application of APN. Experiments are conducted on our constructed dataset and validate the effectiveness of our methods.

cs.CV↗

arXiv2020

Some theoretical results on the second-order conservative phase field equation

In this paper, a theoretical research on the second-order conservative phase field (SOCPF) equation is presented. The theoretical results include the following three aspects. First, three new derivation methods for the SOCPF equation are given. The SOCPF equation can be viewed as the gradient flow, the special diffusion equation and the diffuse interface form of a sharp interface formulation for the piecewise constant function, respectively. These derivation methods help us to understand the SOCPF equation at different perspectives. Second, the conservation's properties of the solution of SOCPF equation are studied. Compared with the Cahn-Hilliard equation and the Allen-Cahn equation, it is found that the solution of SOCPF equation satisfies more conservation laws. Third, the wetting boundary condition for the SOCPF equation is investigated. We find that the no-flux boundary condition is equivalent to the wetting boundary condition for two-component phase field model. Moreover, applying the no-flux boundary conditions for $N$-component phase field model, we give a set of wetting boundary conditions for $N$ phase field parameters.

physics.flu-dyn↗

arXiv2020

Co-Optimizing Performance and Memory FootprintVia Integrated CPU/GPU Memory Management, anImplementation on Autonomous Driving Platform

Cutting-edge embedded system applications, such as self-driving cars and unmanned drone software, are reliant on integrated CPU/GPU platforms for their DNNs-driven workload, such as perception and other highly parallel components. In this work, we set out to explore the hidden performance implication of GPU memory management methods of integrated CPU/GPU architecture. Through a series of experiments on micro-benchmarks and real-world workloads, we find that the performance under different memory management methods may vary according to application characteristics. Based on this observation, we develop a performance model that can predict system overhead for each memory management method based on application characteristics. Guided by the performance model, we further propose a runtime scheduler. By conducting per-task memory management policy switching and kernel overlapping, the scheduler can significantly relieve the system memory pressure and reduce the multitasking co-run response time. We have implemented and extensively evaluated our system prototype on the NVIDIA Jetson TX2, Drive PX2, and Xavier AGX platforms, using both Rodinia benchmark suite and two real-world case studies of drone software and autonomous driving software.

cs.DC↗

arXiv2020

Disconnection-mediated twin embryo growth in Mg

While deformation twinning in hexagonal close-packed metals has been widely studied due to its substantial impact on mechanical properties, an understanding of the detailed atomic processes associated with twin embryo growth is still lacking. Conducting molecular dynamics simulations on Mg, we show that the propagation of twinning disconnections emitted by basal-prismatic interfaces controls the twin boundary motion and is the rate-limiting mechanism during the initial growth of the twin embryo. The time needed for disconnection propagation is related to the distance between the twin tips, with widely spaced twin tips requiring more time for a unit twin boundary migration event to be completed. Thus, a phenomenological model, which unifies the two processes of disconnection and twin tip propagation, is proposed here to provide a quantitative analysis of twin embryo growth. The model fits the simulation data well, with two key parameters (twin tip velocity and twinning disconnection velocity) being extracted. In addition, a linear relationship between the ratio of twinning disconnection velocity to twin tip velocity and the applied shear stress is observed. Using an example of twin growth in a nanoscale single crystal from the recent literature, we find that our molecular dynamics simulations and analytical model are in good agreement with experimental data.

cond-mat.mtrl-sci↗

arXiv2020

Neural Architecture Search For Fault Diagnosis

Data-driven methods have made great progress in fault diagnosis, especially deep learning method. Deep learning is suitable for processing big data, and has a strong feature extraction ability to realize end-to-end fault diagnosis systems. However, designing neural network architecture requires rich professional knowledge and debugging experience, and a lot of experiments are needed to screen models and hyperparameters, increasing the difficulty of developing deep learning models. Frortunately, neural architecture search (NAS) is developing rapidly, and is becoming one of the next directions for deep learning. In this paper, we proposed a NAS method for fault diagnosis using reinforcement learning. A recurrent neural network is used as an agent to generate network architecture. The accuracy of the generated network on the validation dataset is fed back to the agent as a reward, and the parameters of the agent are updated through the strategy gradient algorithm. We use PHM 2009 Data Challenge gearbox dataset to prove the effectiveness of proposed method, and obtain state-of-the-art results compared with other artificial designed network structures. To author's best knowledge, it's the first time that NAS has been applied in fault diagnosis.

cs.LG↗

arXiv2019

A Multi-Scale Mapping Approach Based on a Deep Learning CNN Model for Reconstructing High-Resolution Urban DEMs

The shortage of high-resolution urban digital elevation model (DEM) datasets has been a challenge for modelling urban flood and managing its risk. A solution is to develop effective approaches to reconstruct high-resolution DEMs from their low-resolution equivalents that are more widely available. However, the current high-resolution DEM reconstruction approaches mainly focus on natural topography. Few attempts have been made for urban topography which is typically an integration of complex man-made and natural features. This study proposes a novel multi-scale mapping approach based on convolutional neural network (CNN) to deal with the complex characteristics of urban topography and reconstruct high-resolution urban DEMs. The proposed multi-scale CNN model is firstly trained using urban DEMs that contain topographic features at different resolutions, and then used to reconstruct the urban DEM at a specified (high) resolution from a low-resolution equivalent. A two-level accuracy assessment approach is also designed to evaluate the performance of the proposed urban DEM reconstruction method, in terms of numerical accuracy and morphological accuracy. The proposed DEM reconstruction approach is applied to a 121 km2 urbanized area in London, UK. Compared with other commonly used methods, the current CNN based approach produces superior results, providing a cost-effective innovative method to acquire high-resolution DEMs in other data-scarce environments.

cs.CV↗

arXiv2019

Skill Transfer in Deep Reinforcement Learning under Morphological Heterogeneity

Transfer learning methods for reinforcement learning (RL) domains facilitate the acquisition of new skills using previously acquired knowledge. The vast majority of existing approaches assume that the agents have the same design, e.g. same shape and action spaces. In this paper we address the problem of transferring previously acquired skills amongst morphologically different agents (MDAs). For instance, assuming that a bipedal agent has been trained to move forward, could this skill be transferred on to a one-leg hopper so as to make its training process for the same task more sample efficient? We frame this problem as one of subspace learning whereby we aim to infer latent factors representing the control mechanism that is common between MDAs. We propose a novel paired variational encoder-decoder model, PVED, that disentangles the control of MDAs into shared and agent-specific factors. The shared factors are then leveraged for skill transfer using RL. Theoretically, we derive a theorem indicating how the performance of PVED depends on the shared factors and agent morphologies. Experimentally, PVED has been extensively validated on four MuJoCo environments. We demonstrate its performance compared to a state-of-the-art approach and several ablation cases, visualize and interpret the hidden factors, and identify avenues for future improvements.

cs.LG↗

arXiv2019

Feature Learning for Fault Detection in High-Dimensional Condition-Monitoring Signals

Complex industrial systems are continuously monitored by a large number of heterogeneous sensors. The diversity of their operating conditions and the possible fault types make it impossible to collect enough data for learning all the possible fault patterns. The paper proposes an integrated automatic unsupervised feature learning and one-class classification for fault detection that uses data on healthy conditions only for its training. The approach is based on stacked Extreme Learning Machines (namely Hierarchical, or HELM) and comprises an autoencoder, performing unsupervised feature learning, stacked with a one-class classifier monitoring the distance of the test data to the training healthy class, thereby assessing the health of the system. This study provides a comprehensive evaluation of HELM fault detection capability compared to other machine learning approaches, such as stand-alone one-class classifiers (ELM and SVM), these same one-class classifiers combined with traditional dimensionality reduction methods (PCA) and a Deep Belief Network. The performance is first evaluated on a synthetic dataset that encompasses typical characteristics of condition monitoring data. Subsequently, the approach is evaluated on a real case study of a power plant fault. The proposed algorithm for fault detection, combining feature learning with the one-class classifier, demonstrates a better performance, particularly in cases where condition monitoring data contain several non-informative signals.

cs.AI↗

arXiv2019

Automatic construction of Chinese herbal prescription from tongue image via CNNs and auxiliary latent therapy topics

The tongue image provides important physical information of humans. It is of great importance for diagnoses and treatments in clinical medicine. Herbal prescriptions are simple, noninvasive and have low side effects. Thus, they are widely applied in China. Studies on the automatic construction technology of herbal prescriptions based on tongue images have great significance for deep learning to explore the relevance of tongue images for herbal prescriptions, it can be applied to healthcare services in mobile medical systems. In order to adapt to the tongue image in a variety of photographic environments and construct herbal prescriptions, a neural network framework for prescription construction is designed. It includes single/double convolution channels and fully connected layers. Furthermore, it proposes the auxiliary therapy topic loss mechanism to model the therapy of Chinese doctors and alleviate the interference of sparse output labels on the diversity of results. The experiment use the real world tongue images and the corresponding prescriptions and the results can generate prescriptions that are close to the real samples, which verifies the feasibility of the proposed method for the automatic construction of herbal prescriptions from tongue images. Also, it provides a reference for automatic herbal prescription construction from more physical information.

cs.CV↗

arXiv2019

Stochastic Region Pooling: Make Attention More Expressive

Global Average Pooling (GAP) is used by default on the channel-wise attention mechanism to extract channel descriptors. However, the simple global aggregation method of GAP is easy to make the channel descriptors have homogeneity, which weakens the detail distinction between feature maps, thus affecting the performance of the attention mechanism. In this work, we propose a novel method for channel-wise attention network, called Stochastic Region Pooling (SRP), which makes the channel descriptors more representative and diversity by encouraging the feature map to have more or wider important feature responses. Also, SRP is the general method for the attention mechanisms without any additional parameters or computation. It can be widely applied to attention networks without modifying the network structure. Experimental results on image recognition datasets including CIAFR-10/100, ImageNet and three Fine-grained datasets (CUB-200-2011, Stanford Cars and Stanford Dogs) show that SRP brings the significant improvements of the performance over efficient CNNs and achieves the state-of-the-art results.

cs.CV↗

arXiv2019

Reconfigurable edge-state engineering in graphene using LaAlO$_3$/SrTiO$_3$ nanostructures

The properties of graphene depend sensitively on doping with respect to the charge-neutrality point (CNP). Tuning the CNP usually requires electrical gating or chemical doping. Here, we describe a technique to reversibly control the CNP in graphene with nanoscale precision, utilizing LaAlO$_3$/SrTiO$_3$ (LAO/STO) heterostructures and conductive atomic force microscope (c-AFM) lithography. The local electron density and resulting conductivity of the LAO/STO interface can be patterned with a conductive AFM tip, and placed within two nanometers of an active graphene device. The proximal LAO/STO nanostructures shift the position of graphene CNP by ~ $10^{12}$ cm$^{-2}$, and are also gateable. Here we use this effect to create reconfigurable edge states in graphene, which are probed using the quantum Hall effect. Quantized resistance plateaus at $h/e^2$ and $h/3e^2$ are observed in a split Hall device, demonstrating edge transport along the c-AFM written edge that depends on the polarity of both the magnetic field and direction of currents. This technique can be readily extended to other device geometries.

cond-mat.mes-hall↗

arXiv2019

The Paracrystalline Nature of Lattice Distortion in a High Entropy Alloy

Severe lattice distortion is suggested for high entropy alloys (HEAs), however, evidence for such effect so far is lacking, and the nature of distortion is yet to be understood. Here, we reveal the distortion in an fcc HEA, Al0.1CrFeCoNi, by direct imaging using electron nanodiffraction. Information about crystal symmetry, lattice strain and atomic distortion are data-mined and mapped from many (~10^4) diffraction patterns. Application to the HEA reveals two embodiments of distortion, nm-sized mosaic blocks of paracrystals and strained nano-clusters. Their interaction gives rise to fractal strain field across nanoscopic to mesoscopic scales. As lattice distortion impedes dislocation motion and contributes to strengthening, results here thus provide critical insights about the complex nature of distortion in a HEA.

cond-mat.mtrl-sci↗

arXiv2018

Competitive Inner-Imaging Squeeze and Excitation for Residual Network

Residual networks, which use a residual unit to supplement the identity mappings, enable very deep convolutional architecture to operate well, however, the residual architecture has been proved to be diverse and redundant, which may leads to low-efficient modeling. In this work, we propose a competitive squeeze-excitation (SE) mechanism for the residual network. Re-scaling the value for each channel in this structure will be determined by the residual and identity mappings jointly, and this design enables us to expand the meaning of channel relationship modeling in residual blocks. Modeling of the competition between residual and identity mappings cause the identity flow to control the complement of the residual feature maps for itself. Furthermore, we design a novel inner-imaging competitive SE block to shrink the consumption and re-image the global features of intermediate network structure, by using the inner-imaging mechanism, we can model the channel-wise relations with convolution in spatial. We carry out experiments on the CIFAR, SVHN, and ImageNet datasets, and the proposed method can challenge state-of-the-art results.

cs.CV↗

arXiv2018

Chinese Herbal Recognition based on Competitive Attentional Fusion of Multi-hierarchies Pyramid Features

Convolution neural netwotks (CNNs) are successfully applied in image recognition task. In this study, we explore the approach of automatic herbal recognition with CNNs and build the standard Chinese herbs datasets firstly. According to the characteristics of herbal images, we proposed the competitive attentional fusion pyramid networks to model the features of herbal image, which mdoels the relationship of feature maps from different levels, and re-weights multi-level channels with channel-wise attention mechanism. In this way, we can dynamically adjust the weight of feature maps from various layers, according to the visual characteristics of each herbal image. Moreover, we also introduce the spatial attention to recalibrate the misaligned features caused by sampling in features amalgamation. Extensive experiments are conducted on our proposed datasets and validate the superior performance of our proposed models. The Chinese herbs datasets will be released upon acceptance to facilitate the research of Chinese herbal recognition.

cs.CV↗

arXiv2018

Convolutional herbal prescription building method from multi-scale facial features

In Traditional Chinese Medicine (TCM), facial features are important basis for diagnosis and treatment. A doctor of TCM can prescribe according to a patient's physical indicators such as face, tongue, voice, symptoms, pulse. Previous works analyze and generate prescription according to symptoms. However, research work to mine the association between facial features and prescriptions has not been found for the time being. In this work, we try to use deep learning methods to mine the relationship between the patient's face and herbal prescriptions (TCM prescriptions), and propose to construct convolutional neural networks that generate TCM prescriptions according to the patient's face image. It is a novel and challenging job. In order to mine features from different granularities of faces, we design a multi-scale convolutional neural network based on three-grained face, which mines the patient's face information from the organs, local regions, and the entire face. Our experiments show that convolutional neural networks can learn relevant information from face to prescribe, and the multi-scale convolutional neural networks based on three-grained face perform better.

cs.CV↗

arXiv2018

Atomistic modeling of interfacial segregation and structural transitions in ternary alloys

Grain boundary engineering via dopant segregation can dramatically change the properties of a material. For metallic systems, most current studies concerning interfacial segregation and subsequent transitions of grain boundary structure are limited to binary alloys, yet many important alloy systems contain more than one type of dopant. In this work, hybrid Monte Carlo/molecular dynamics simulations are performed to investigate the behavior of dopants at interfaces in two model ternary alloy systems: Cu-Zr-Ag and Al-Zr-Cu. Trends in boundary segregation are studied, as well as the propensity for the grain boundary structure to become disordered at high temperature and doping concentration. For Al-Zr-Cu, we find that the two solutes prefer to occupy different sites at the grain boundary, leading to a synergistic doping effect. Alternatively, for Cu-Zr-Ag, there is site competition because the preferred segregation sites are the same. Finally, we find that thicker amorphous intergranular films can be formed in ternary systems by controlling the concentration ratio of different solute elements.

cond-mat.mtrl-sci↗

arXiv2018

Solution for Large-Scale Hierarchical Object Detection Datasets with Incomplete Annotation and Data Imbalance

This report demonstrates our solution for the Open Images 2018 Challenge. Based on our detailed analysis on the Open Images Datasets (OID), it is found that there are four typical features: large-scale, hierarchical tag system, severe annotation incompleteness and data imbalance. Considering these characteristics, an amount of strategies are employed, including SNIPER, soft sampling, class-aware sampling (CAS), hierarchical non-maximum suppression (HNMS) and so on. In virtue of these effective strategies, and further using the powerful SENet154 armed with feature pyramid module and deformable ROIalign as the backbone, our best single model could achieve a mAP of 56.9%. After a further ensemble with 9 models, the final mAP is boosted to 62.2% in the public leaderboard (ranked the 2nd place) and 58.6% in the private leaderboard (ranked the 3rd place, slightly inferior to the 1st place by only 0.04 point).

cs.CV↗