您当前所在位置: 首页 > 首发论文
筛选条件

时间

领域

全部

计算机科学技术(32)

电子、通信与自动控制技术(10)

数学(8) 显示更多>>

管理学(3) 信息科学与系统科学(2) 动力与电气工程(1) 机械工程(1) 物理学(1) 经济学(1) 中医学与中药学(0) 临床医学(0) 交通运输工程(0) 体育科学(0) 农学(0) 冶金工程技术(0) 力学(0) 化学(0) 化学工程(0) 图书馆、情报与文献学(0) 土木建筑工程(0) 地球科学(0) 基础医学(0) 天文学(0) 安全科学技术(0) 工程与技术科学基础学科(0) 心理学(0) 教育学(0) 材料科学(0) 林学(0) 核科学技术(0) 水产学(0) 水利工程(0) 测绘科学技术(0) 环境科学技术(0) 生物学(0) 畜牧科学、动物医学(0) 矿山工程技术(0) 纺织科学技术(0) 能源科学技术(0) 航空航天科学技术(0) 药学(0) 预防医学与卫生学(0) 食品科学技术(0)

学术评议

实时热搜榜

我的筛选 >
2003-2020 全部
为您找到包含“损失函数”的内容共59

ZHANG Jian-Wei,GUO Qiu-Shan,DONG Yuan,XIONG Feng-Ye,BAI Hong-Liang

Face recognition has achieved great success due to the development of Deep convolutional neural networks (DCNN). Loss functions with angular margin have been proposed to supervise DCNN for better feature representation. However, these methods would suffer from sensitivity of hyperparameters setting. In this paper, we propose an Adaptive Parameters Softmax Loss function with different scale parameters for target logits and non-target logits and dynamically adaptive margin parameter. Extensive experiments on MegaFace and IJB-C demonstrate the effectiveness of our method.

2019-09-24

National Natural Science Foundation (61532018

School of Information and Communication Engineering, Beijing University of Posts and Telecommunications, Beijing 100876,School of Information and Communication Engineering, Beijing University of Posts and Telecommunications, Beijing 100876,School of Information and Communication Engineering, Beijing University of Posts and Telecommunications, Beijing 100876,Beijing FaceALL Technology Ltd., Beijing 100081,Beijing FaceALL Technology Ltd., Beijing 100081

#Computer Science and Technology#

袁玉萍,安增龙,张宏礼

2013-07-15

支持向量回归机模型的性能与所选的损失函数有很大关系。提出一种基于不对称形式的二次不敏感控制型Ramp损失函数的支持向量回归机,采用凹凸过程优化和光滑技术算法,将非凸优化问题转化为连续、二次可微凸优化

高等学校博士学科点专项科研基金博导类资助课题项目(20112305110002

黑龙江省农垦总局科研资助项目(HNK11A-14-07

黑龙江八一农垦大学理学院,黑龙江 大庆 163319,黑龙江八一农垦大学经济管理学院,黑龙江八一农垦大学理学院

#信息科学与系统科学#

钱鹰,叶青青

2018-02-14

现在存在的大部分监督哈希是将手工提取的特征转换为哈希值,然后根据图像标签为监督信息得到损失函数,但是手工提取特征以及不完全考虑所有损失的损失函数会降低检索精度。监督哈希算法主要目的是通过训练数据

Chongqing University of Posts and Telecommunications,Image and multimedia laboratory,Chongqing 400065,Chongqing University of Posts and Telecommunications,Image and multimedia laboratory,Chongqing 400065

#计算机科学技术#

0评论(0 分享(0)

郭尧,宋晴

2020-04-17

场景行人数据集上达到了识别平均准确率95%以上,mAP达到72.16%,且单张图的识别时间仅0.04秒。在此基础上通过对检测失败样本进行分析,归纳出行人检测中的常见问题,设计了一种带有惩罚项的损失函数

School of Automation,Beijing University of Posts and Telecommunications,Beijing,100876,School of Automation,Beijing University of Posts and Telecommunications,Beijing,100876

#计算机科学技术#

0评论(0 分享(0)

汪建均,马义中

2014-06-05

函数与贝叶斯后验概率方法提出了一种多响应稳健参数设计的新方法。实例研究表明:与以往的研究方法相比,新方法在统一的贝叶斯模型框架下不仅通过多元质量损失函数考察了多元过程的稳健性,而且还结合贝叶斯后验概率

教育部高等学校博士学科点专项科研基金(20123219120032

中国博士后基金面上资助项目(2013M531366)

国家自然科学基金面上项目(71371099

南京理工大学经济管理学院,南京 210094,南京理工大学经济管理学院,南京 210094

#管理学#

0评论(0 分享(0)

Shi Cong-Cong,TIAN Mei,TIAN

Over the past few years, Convolutional Neural Networks (CNNs) have shown effective performance on facial expression recognition. However, it is still a challenge problem for facial expression in the wild. The facial expression recognition dataset in the wild usually has the problem that imbalanced distribution of facial expression data and large intra-class differences caused by factors such as pose, lighting and gender. In order to solve this problem, this paper presents a novel loss function -- CALM Loss (Class-balanced and Local Median Loss). CALM Loss contains two parts. The first part is the class-balanced softmax loss function, which is uesd to solve the problem of data imbalance. The data set is divided into two classes, with two expressions with less data as one class and the other five as one class. During the network training process, the weight of the class with less data is adaptively increased. The second part is the local median loss function, which uses the median of serveral neatest neighbors in the same class as the center of class, weakens the influence of difficult samples on the selection of class center. Finally, the CALM Loss training network was adopted in this paper. The average recognition accuracy on the RAF dataset reaches 77.34$\%$, which proves the effectiveness of the proposed method.

2020-02-14

The Fundamental Research Funds for the Central Universities (2019JBM019

Beijing Key Laboratory of Traffic Data Analysis and Mining, Beijing Jiaotong University,Brijing 100044,Beijing Key Laboratory of Traffic Data Analysis and Mining, Beijing Jiaotong University,Brijing 100044,Beijing Key Laboratory of Traffic Data Analysis and Mining, Beijing Jiaotong University,Brijing 100044

#Computer Science and Technology#

0评论(0 分享(0)

赵金伟,王宇飞,柳宇,黑新宏

2018-05-18

经验风险是训练样本预测误差的平均值。然而,当损失函数确定后,对于给定的样本数据集来说,训练样本的预测误差在样本空间中并不全是大概率事件,那么在经验风险中平等对待这些样本是不正确的,所以在分析无界损失

国家自然科学基金(61672027; 61773314; 61773313

高等学校博士学科点专项科研基金资助课题(20136118120011

陕西省自然科学基础研究计划项目(2017JM6080

国家重点研发计划资助(2017YFB1201500

School of Computer Science and Engineering, Xi’an University of Technology, Xi’an 710048,School of Computer Science and Engineering, Xi’an University of Technology, Xi’an 710048,School of Computer Science and Engineering, Xi’an University of Technology, Xi’an 710048,School of Computer Science and Engineering, Xi’an University of Technology, Xi’an 710048

#计算机科学技术#

本文收录在中国科技论文在线精品论文,2018,11(16):1586-1598.

0评论(0 分享(0)

毛昭勇

2012-09-28

广义指数分布是可靠性研究中一类重要的寿命分布,在航空,生物等诸多领域有着广泛的应用。本文在熵损失函数下,基于共轭先验分布,给出了广义指数分布形状参数贝叶斯估计和经验贝叶斯估计,并证明了经验贝叶斯估计

高等学校博士学科点专项科研基金(20106102120012

西北工业大学航海学院,西安 710072

#信息科学与系统科学#

0评论(0 分享(0)

张翠华,邢鹏

2015-11-06

研究了需求不确定条件下具有风险偏好的两条供应链产品质量改进问题。引入了企业风险偏好因子和价值损失函数,通过分析集成供应链与分散供应链的质量改进活动,将两条供应链划分为七种战略组合:NN、OII

教育部高等学校博士学科点专项科研基金资助项目(20130042110031

辽宁省百千万人才工程项目(2013921072

中央高校基本业务费专项资金资助项目(N130206001

国家自然科学基金资助项目(71371043

辽宁省社科规划基金资助项目(L13BJY023

东北大学工商管理学院,沈阳 110819,东北大学工商管理学院,沈阳 110819

#管理学#

0评论(0 分享(0)