YOLSO: You Only Look Small Object

Small object detection is challenging and far from satisfactory. Most general object detectors suffer from two critical issues with small objects: (1) Feature extractor based on classification network cannot express the characteristics of small objects reasonably due to insufficient appearance information of targets and a large amount of background interference around them. (2) The detector requires a much higher location accuracy for small objects than for general objects. This paper proposes an effective and efficient small object detector YOLSO to address the above problems. For feature representation, we analyze the drawbacks in previous backbones and present a Half-Space Shortcut(HSSC) module to build a background-aware backbone. Furthermore, a coarse-to-fine Feature Pyramid Enhancement(FPE) module is introduced for layer-wise aggregation at a granular level to enhance the semantic discriminability. For loss function, we propose an exponential L1 loss to promote the convergence of regression, and a focal IOU loss to focus on prime samples with high classification confidence and high IOU. Both of them significantly improves the location accuracy of small objects. The proposed YOLSO sets state-of-the-art results on two typical small object datasets, MOCOD and VeDAI, at a speed of over 200 FPS. In the meantime, it also outperforms the baseline YOLOv3 by a wide margin on the common COCO dataset.     

Feature selection methods for root-cause analysis among top-level product attributes

Manufacturing companies not only strive to deliver flawless products but also monitor product failures in the field to identify potential quality issues. When product failures occur, quality engineers must identify the root cause to improve any affected product and process. This root-cause analysis can be supported by feature selection methods that identify relevant product attributes, such as manufacturing dates with an increased number of product failures. In this paper, we present different methods for feature selection and evaluate their ability to identify relevant product attributes in a root-cause analysis. First, we compile a list of feature selection methods. Then, we summarize the properties of product attributes in warranty case data and discuss these properties regarding the challenges they pose for machine learning algorithms. Next, we simulate datasets of warranty cases, which emulate these product properties. Finally, we compare the feature selection methods based on these simulated datasets. In the end, the univariate filter information gain is determined to be a suitable method for a wide range of applications. The comparison based on simulated data provides a more general result than other publications, which only focus on a single use case. Due to the generic nature of the simulated datasets, the results can be applied to various root-cause analysis processes in different quality management applications and provide a guideline for readers who wish to explore machine learning methods for their analysis of quality data.     

Display illumination with modulated directional backlight

Illumination is essential for modern life as colorful world is perceived by human visionary system. Display technology has been developing rapidly in recent decades, and the basic principle is related to the way that the image is illuminated and light is emanated. Traditional illumination is provided by different types of light sources, and the display image is visible in large viewing space until the emanating light decays to zero. This work proposes and demonstrates a novel illumination scheme for a display in which the displaying images are visible only in specific spatial regions. The directional backlight ensures the image propagating to specific direction while imaging visibility can be controlled to terminate abruptly at certain distance from the display screen while exerting no influence to nearby regions. The working principle for such an illumination scheme is the use of the modulated coherent directional backlight through an axicon lens. It is shown that the illumination scheme can robustly deliver carried image information to the designated viewing region. This new illumination scheme has many advantages over conventional illumination, including its usage for personal display, very lower energy consumption, as well as minimizing light hazard pollution.     

Understanding the asymmetric perceptions of smartphone security from security feature perspective: A comparative study

Smartphones are being used and relied on by people more than ever before. The open connectivity brings with it great convenience and leads to a variety of risks that cannot be overlooked. Smartphone vendors, security policy designers, and security application providers have put a variety of practical efforts to secure smartphones, and researchers have conducted extensive research on threat sources, security techniques, and user security behaviors. Regrettably, smartphone users do not pay enough attention to mobile security, making many efforts futile. This study identifies this gap between technology affordance and user requirements, and attempts to investigate the asymmetric perceptions toward security features between developers and users, between users and users, as well as between different security features. These asymmetric perceptions include perceptions of quality, perceptions of importance, and perceptions of satisfaction. After scoping the range of smartphone security features, this study conducts an improved Kano-based method and exhaustively analyzes the 245 collected samples using correspondence analysis and importance satisfaction analysis. The 14 security features of the smartphone are divided into four Kano quality types and the perceived quality differences between developers and users are compared. Correspondence analysis is utilized to capture the relationship between the perceived importance of security features across different groups of respondents, and results of importance-satisfaction analysis provide the basis for the developmental path and resource reallocation strategy of security features. This article offers new insights for researchers as well as practitioners of smartphone security.     

On optical flow techniques applied to breaking surges

Surface wave breaking is a challenging two-phase flow process which plays an important role in numerous physical processes. A highly-turbulent unsteady breaking surge was investigated experimentally in a large facility, and substantial aeration occurred in the roller. The application of three optical flow techniques (Lucas-Kanade, Horn-Schunck and Farnback) to the air-water region was tested. The results indicated that the Farnback technique provided most accurate results, although some misleading results could be obtained near the air-water boundaries of the roller. The bore generation by a rapid gate closure showed a highly-unsteady complicated velocity field, with substantial free-surface deformations, wave breaking and formation of large coherent structures before the surge detached from the gate. Further upstream, the surge propagated as a hydraulic jump in translation and the data showed a marked shear region with a recirculation zone above, showing air-water flow features comparable to stationary hydraulic jumps. The upper and lower bounds of air-water flow region yielded data implying an air-to-water velocity ratio about 4–5 for a Froude number Fr₁ = 2.1.     

基于梯度提升决策树的车轮轮缘厚度磨耗预测

轮对在列车走行过程中起着导向、承受以及传递载荷的作用，其踏面及轮缘磨耗对地铁列车运行安全性和钢轨的寿命都将产生重要影响。根据地铁列车车轮磨耗机理，分析车轮尺寸数据特点，针对轮缘厚度这一型面参数，基于梯度提升决策树算法构建轮缘厚度磨耗预测模型。在该模型的基础上，任意选取某轮对数据进行验证分析，结果表明：基于梯度提升决策树的轮对磨耗预测模型具有较好的预测精度，可预测出1~6个月的轮缘厚度变化趋势范围，预测时间范围较长，可为地铁维保部门对轮对的维修方式由状态修转为预防修提供指导性建议。     

基于深度学习的秀丽隐杆线虫显微图像分割方法

利用计算机实现自动、准确的秀丽隐杆线虫(C.elegans)的各项形态学参数分析,至关重要的是从显微图像上分割出线虫体态,但由于显微镜下的图像噪声较多,线虫边缘像素与周围环境相似,而且线虫的体态具有鞭毛和其他附着物需要分离,多方面因素导致设计一个鲁棒性的C.elegans分割算法仍然面临着挑战。针对这些问题,提出了一种基于深度学习的线虫分割方法,通过训练掩模区域卷积神经网络(Mask R-CNN)学习线虫形态特征实现自动分割。首先,通过改进多级特征池化将高级语义特征与低级边缘特征融合,结合大幅度软最大损失(LMSL)损失算法改进损失计算;然后,改进非极大值抑制;最后,引入全连接融合分支等方法对分割结果进行进一步优化。实验结果表明,相比原始的Mask R-CNN,该方法平均精确率(AP)提升了4.3个百分点,平均交并比(mIOU)提升了4个百分点。表明所提出的深度学习分割方法能够有效提高分割准确率,在显微图像中更加精确地分割出线虫体。     

THE effect of Srandom DOPANT fluctuation on threshold voltage and drain current variation in junctionless nanotransistors

We investigate the effect of dopant random fluctuation on threshold voltage and drain current variation in a two-gate nanoscale transistor. We used a quantum-corrected technology computer aided design simulation to run the simulation (10000 randomizations). With this simulation, we could study the effects of varying the dimensions (length and width), and thicknesses of oxide and dopant factors of a transistor on the threshold voltage and drain current in subthreshold region (off) and overthreshold (on). It was found that in the subthreshold region the variability of the drain current and threshold voltage is relatively fixed while in the overthreshold region the variability of the threshold voltage and drain current decreases remarkably, despite the slight reduction of gate voltage diffusion (compared with that of the subthreshold). These results have been interpreted by using previously reported models for threshold current variability, load displacement, and simple analytical calculations. Scaling analysis shows that the variability of the characteristics of this semiconductor increases as the effects of the short channel increases. Therefore, with a slight increase of length and a reduction of width, oxide thickness, and dopant factor, we could correct the effect of the short channel.     

面部运动单元检测研究综述

面部运动单元检测旨在让计算机从给定的人脸图像或视频中自动检测需要关注的运动单元目标。经过二十多年的研究，尤其是近年来越来越多的面部运动单元数据库的建立和深度学习的兴起，面部运动单元检测技术发展迅速。首先，阐述了面部运动单元的基本概念，介绍了已有的常用面部运动单元检测数据库，概括了包括预处理、特征提取、分类器学习等步骤在内的传统检测方法；然后针对区域学习、面部运动单元关联学习、弱监督学习等几个关键研究方向进行了系统性的回顾梳理与分析；最后讨论了目前面部运动单元检测研究存在的不足以及未来潜在的发展方向。