结合稀疏编码的生物视觉特征提取方法

在分析视皮层标准模型的基础上,从S2层的生物视觉机理出发,提出一种结合稀疏编码的生物视觉特征提取方法。对原始标准模型中C1层的输出进行稀疏编码,生成S2层的特征,并在此基础上产生C2特征。将标准模型产生的特征和该方法提取的特征应用于图像分类中进行对比实验,实验结果表明,与标准模型相比,该方法可以更有效地提取生物视觉特征。     

面向自然语言处理任务的预训练模型综述

近年来,深度学习技术得到了快速发展.在自然语言处理(NLP)任务中,随着文本表征技术从词级上升到了文档级,利用大规模语料库进行无监督预训练的方式已被证明能够有效提高模型在下游任务中的性能.首先,根据文本特征提取技术的发展,从词级和文档级对典型的模型进行了分析;其次,从预训练目标任务和下游应用两个阶段,分析了当前预训练模...     

集装箱病媒生物视觉探寻系统

针对传统集装箱病媒生物检测局限于人工检测的问题,设计了一款基于机器视觉的集装箱病媒生物视觉探寻系统.系统通过可遥控智能车采集实时视频以及抓取病媒生物的活动,进而通过深度学习和隔帧检测的方法识别遥控车回传视频中的病媒生物.系统以YOLOv5模型为训练核心,采用模块化结构,实现了集装箱病媒生物的视觉检测.利用机器视觉提高了检测效率,为进一步利用机器人检测病媒生物奠定了基础.     

基于自编码算法的深度学习综述

深度学习是机器学习的一个分支,开创了神经网络发展的新纪元.自编码算法作为深度学习结构的重要组成部分,在无监督学习及非线性特征提取过程中起到了至关重要的作用.首先介绍自编码算法的基本概念及原理,然后介绍基于自编码算法的改进算法,最后列举了自编码算法在若干领域应用的知名案例和发展趋势.     

基于自编码神经网络的半监督联邦学习模型

联邦学习是一种新型的分布式机器学习方法,可以使得各客户端在不分享隐私数据的前提下共同建立共享模型。然而现有的联邦学习框架仅适用于监督学习,即默认所有客户端数据均带有标签。由于现实中标记数据难以获取,联邦学习模型训练的前提假设通常很难成立。为解决此问题,对原有联邦学习进行扩展,提出了一种基于自编码神经网络的半监督联邦学习模型ANN-SSFL,该模型允许无标记的客户端参与联邦学习。无标记数据利用自编码神经网络学习得到可被分类的潜在特征,从而在联邦学习中提供无标记数据的特征信息来作出自身贡献。在MNIST数据集上进行实验,实验结果表明,提出的ANN-SSFL模型实际可行,在监督客户端数量不变的情况下,增加无监督客户端可以提高原有联邦学习精度。     

基于循环卷积神经网络的单目视觉里程计

提出了一种基于卷积长短期记忆(LSTM)网络和卷积神经网络(CNN)的单目视觉里程计方法,命名为LSTMVO(LSTM visual odometry).LSTMVO采用无监督的端到端深度学习框架,对单目相机的6-DoF位姿以及场景深度进行同步估计.整个网络框架包含位姿估计网络以及深度估计网络,其中位姿估计网络是以端到端方式实现单目位姿估计的深度循环卷积神经网络(RCNN),由基于卷积神经网络的特征提取和基于循环神经网络(RNN)的时序建模组成,深度估计网络主要基于编码器和解码器架构生成稠密的深度图.同时本文还提出了一种新的损失函数进行网络训练,该损失函数由图像序列之间的时序损失、深度平滑度损失和前后一致性损失组成.基于KITTI数据集的实验结果表明,通过在原始单目RGB图像上进行训练,LSTMVO在位姿估计精度以及深度估计精度方面优于现有的主流单目视觉里程计方法,验证了本文提出的深度学习框架的有效性.     

fMRI的视觉神经信息编解码方法综述

视觉神经信息编解码旨在利用功能磁共振成像(functional magnetic resonance imaging,fMRI)等神经影像数据研究视觉刺激与大脑神经活动之间的关系。编码研究可以对神经活动模式进行建模和预测,有助于脑科学与类脑智能的发展;解码研究可以对人的视知觉状态进行解译,能够促进脑机接口领域的发展。因此,基于fMRI的视觉神经信息编解码方法研究具有重要的科学意义和工程价值。本文在总结基于fMRI的视觉神经信息编解码关键技术与研究进展的基础上,分析现有视觉神经信息编解码方法的局限。在视觉神经信息编码方面,详细介绍了基于群体感受野估计方法的发展过程;在视觉神经信息解码方面,首先,按照任务类型将其划分为语义分类、图像辨识和图像重建3个部分,并深入阐述了每个部分的代表性研究工作和所用的方法。特别地,在图像重建部分着重介绍了基于深度生成模型(主要包括变分自编码器和生成对抗网络)的简单图像、人脸图像和复杂自然图像的重建技术。其次,统计整理了该领域常用的10个开源数据集,并对数据集的样本规模、被试个数、刺激类型、研究用途及下载地址进行了详细归纳。最后,详细介绍了视觉神经信息编解码模...     

High performance accelerators for deep neural networks: A review

The availability of huge structured and unstructured data, advanced highly dense memory and high performance computing machines have provided a strong push for the development in artificial intelligence (AI) and machine learning (ML) domains. AI and machine learning has rekindled the hope of efficiently solving complex problems which was not possible in the recent past. The generation and availability of big-data is a strong driving force for the development of AI/ML applications, however, several challenges need to be addressed, like processing speed, memory requirement, high bandwidth, low latency memory access, and highly conductive and flexible connections between processing units and memory blocks. The conventional computing platforms are unable to address these issues with machine learning and AI. Deep neural networks (DNNs) are widely employed for machine learning and AI applications, like speech recognition, computer vison, robotics, and so forth, efficiently and accurately. However, accuracy is achieved at the cost of high computational complexity, sacrificing energy efficiency and throughput like performance measuring parameters along with high latency. To address the problems of latency, energy efficiency, complexity, power consumption, and so forth, a lot of state of the art DNN accelerators have been designed and implemented in the form of application specific integrated circuits (ASICs) and field programmable gate arrays (FPGAs). This work provides the state of the art of all these DNN accelerators which have been developed recently. Various DNN architectures, their computing units, emerging technologies used in improving the performance of DNN accelerators will be discussed. Finally, we will try to explore the scope for further improvement in these accelerator designs, various opportunities and challenges for the future research.     

轨道视觉检测系统中行程编码的应用研究

利用行程编码针对背景冗余计算的优化特性与交、并简便运算特点对二值图像形态学膨胀算法进行优化,并提出基于行程编码优化的形态学膨胀算法。利用算法对轨道轮廓二值图像进行形态学膨胀处理;依据优化前后的图像处理结果和速度进行对比分析。该算法能去除边缘毛刺与断线现象;轨道轮廓单帧图像经过优化处理后的速度提高5倍,轨道视觉检测系统的检测精度可提高到20点/m。     

On the use of convolutional neural networks for robust classification of multiple fingerprint captures

Fingerprint classification is one of the most common approaches to accelerate the identification in large databases of fingerprints. Fingerprints are grouped into disjoint classes, so that an input fingerprint is compared only with those belonging to the predicted class, reducing the penetration rate of the search. The classification procedure usually starts by the extraction of features from the fingerprint image, frequently based on visual characteristics. In this work, we propose an approach to fingerprint classification using convolutional neural networks, which avoid the necessity of an explicit feature extraction process by incorporating the image processing within the training of the classifier. Furthermore, such an approach is able to predict a class even for low‐quality fingerprints that are rejected by commonly used algorithms, such as FingerCode. The study gives special importance to the robustness of the classification for different impressions of the same fingerprint, aiming to minimize the penetration in the database. In our experiments, convolutional neural networks yielded better accuracy and penetration rate than state‐of‐the‐art classifiers based on explicit feature extraction. The tested networks also improved on the runtime, as a result of the joint optimization of both feature extraction and classification.     

3D computer vision based on machine learning with deep neural networks: A review

Recent advances in the field of computer vision can be attributed to the emergence of deep learning techniques, in particular convolutional neural networks. Neural networks, partially inspired by the brain's visual cortex, enable a computer to “learn” the most important features of the images it is shown in relation to a specific, specified task. Given sufficient data and time, (deep) convolutional neural networks offer more easily designed, more generalizable, and significantly more accurate end‐to‐end systems than is possible with previously employed computer vision techniques. This review paper seeks to provide an overview of deep learning in the field of computer vision with an emphasis on recent progress in tasks involving 3D visual data. Through a backdrop of the mammalian visual processing system, we hope to also provide inspiration for future advances in automated visual processing.     

基于自注意力机制的多域卷积神经网络的视觉追踪

为了解决多域卷积神经网络（MDNet）在目标快速移动和外观剧烈变化时发生的模型漂移问题,提出了自注意力多域卷积神经网络（SAMDNet）,通过引入自注意力机制从通道和空间两个维度来提升追踪网络的性能。首先,利用空间注意力模块将所有位置上的特征的加权总和选择性地聚合到特征图中的所有位置上,使得相似的特征彼此相关;然后,利用通道注意力模块整合所有特征图来选择性地强调互相关联的通道的重要性;最后,融合得到最终的特征图。此外,针对MDNet算法因训练数据中存在较多相似但属性不同的序列所造成的网络模型分类不准的问题,构造了复合损失函数。该复合损失函数由分类损失函数和实例判别损失函数组成,首先,用分类损失函数来统计分类的损失值;然后,利用实例判别损失函数来提高目标在当前视频序列中的权重,抑制其在其他序列中的权重;最后,融合两项损失作为模型的最终损失。在目前广泛采用的测试基准数据集OTB50和OTB2015上进行实验,结果表明所提出的算法在成功率指标上相比2015年视觉目标跟踪挑战（VOT2015）的冠军算法MDNet分别提高了1.6个百分点和1.4个百分点,在精确率和成功率指标上优于连续域卷积相关滤波（CCOT）算法,在OTB50上的精确率指标优于高效卷积操作（ECO）算法,验证了该算法的有效性。     

Linear correlation-based learning models require a two-stage process for the development of orientation and ocular dominance

In our contribution we demonstrate, that orientation (OR) and ocular dominance (OD) cannot develop simultaneously in linear correlation-based learning (CBL) models, because OR and OD occupy separate domains in parameter space. We then analyse the conditions under which waves of spontaneous activity — as have been observed in the developing retina — may give rise at least to OR or OD. We find that in linear CBL models there must be subcortical convergence of ON/OFF as well as left eye/right eye pathways. We present a biologically plausible scenario in which the subcortical connectivity patterns resemble a competitive neural network and argue that OR and OD can robustly emerge, if a two-stage developmental process is assumed.     

Comparison of proportional hazards models and neural networks for reliability estimation

Because of increased manufacturing competitiveness, new methods for reliability estimation are being developed. Intelligent manufacturing relies upon accurate component and product reliability estimates for determining warranty costs, as well as optimal maintenance, inspection, and replacement schedules. Accelerated life testing is one approach that is used for shortening the life of products or components or hastening their performance degradation with the purpose of obtaining data that may be used to predict device life or performance under normal operating conditions. The proportional hazards (PH) model is a non-parametric multiple regression approach for reliability estimation, in which a baseline hazard function is modified multiplicatively by covariates (i.e. applied stresses). While the PH model is a distribution-free approach, specific assumptions need to be made about the time behavior of the hazard rates. A neural network (NN) is particularly useful in pattern recognition problems that involve capturing and learning complex underlying (but consistent) trends in the data. Neural networks are highly non-linear, and in some cases are capable of producing better approximations than multiple regression. This paper reports on the comparison of PH and NN models for the analysis of time-dependent dielectric breakdown data for a metal-oxide-semiconductor integrated circuit. In this case, the NN model results in a better fit to the data based upon minimizing the mean square error of the predictions when using failure data from an elevated temperature and voltage to predict reliability at a lower temperature and voltage.     

深度对抗视觉生成综述

深度视觉生成是计算机视觉领域的热门方向,旨在使计算机能够根据输入数据自动生成预期的视觉内容。深度视觉生成使用人工智能技术赋能相关产业,推动产业自动化、智能化改革与转型。生成对抗网络（generative adversarial networks,GANs）是深度视觉生成的有效工具,近年来受到极大关注,成为快速发展的研究方向。GANs能够接收多种模态的输入数据,包括噪声、图像、文本和视频,以对抗博弈的模式进行图像生成和视频生成,已成功应用于多项视觉生成任务。利用GANs实现真实的、多样化和可控的视觉生成具有重要的研究意义。本文对近年来深度对抗视觉生成的相关工作进行综述。首先介绍深度视觉生成背景及典型生成模型,然后根据深度对抗视觉生成的主流任务概述相关算法,总结深度对抗视觉生成目前面临的痛点问题,在此基础上分析深度对抗视觉生成的未来发展趋势。