年糕糕糕-CSDN博客

原创 [论文解读]Deep Active Learning for Efficient Training of a LiDAR 3D Object Detector

Deep Active Learning for Efficient Training of a LiDAR 3D Object Detector文章目录Deep Active Learning for Efficient Training of a LiDAR 3D Object Detector简介摘要初步相关工作基于激光雷达测点的自动驾驶目标检测深度主动学习方法论Process3D物体探测器不确定度估计和查询功能实验结果实验设计“完美”RGB图像探测器的评价利用预先训练的RGB图像探测器进行评估讨论

2021-09-24 14:56:55 544

原创 [论文解读]Active Learning for Deep Object Detection via Probabilistic Modeling

Active Learning for Deep Object Detection via Probabilistic Modeling文章目录Active Learning for Deep Object Detection via Probabilistic Modeling简介摘要初步相关工作主动学习在目标检测中的应用基于概率建模的目标检测提高参数效率计分函数实验基于概率建模的目标检测主动学习评价可扩展性和数据集可传输性结论结论简介论文标题Active Learning for Deep O

2021-09-24 14:52:37 1819 1

原创 [论文解读]Deep active learning for object detection

Deep active learning for object detection文章目录Deep active learning for object detection简介摘要初步以前的工作Method黑箱主动学习3.1.1 Minmax (mm)3.1.2 Maximum Entropy (ent)3.1.3 Sum Entropy (ent-sum)白盒主动学习勘探/开发框架结果PASCAL VOC不同口味白盒的比较与黑箱方法的比较勘探/开发方法比较使用35%图像的不同方法的mapKitti模型分

2021-09-22 22:45:58 1118

原创 [论文解读] Metamorphic Object Insertion for Testing Object Detection Systems

Metamorphic Object Insertion for Testing Object Detection Systems文章目录Metamorphic Object Insertion for Testing Object Detection Systems简介摘要初步目标检测技术背景方法概述Equality CriteriaOD故障案例分析适用范围设计对象提取对象细化和选择对象插入实现实验评估概述对象位置调整的效率合成图像的自然度使用错误触发图像进行再培训研讨与未来工作Related Work

2021-09-22 13:55:36 971

原创 [论文解读]A Quantitative Analysis Framework for Recurrent Neural Network

A Quantitative Analysis Framework for Recurrent Neural Network文章目录A Quantitative Analysis Framework for Recurrent Neural Network简介摘要动机THE DeepStellar FRAMEWORK抽象模型构建应用实施和功能评估相关工作总结与下一步工作简介论文标题A Quantitative Analysis Framework for Recurrent Neural Netw

2020-10-22 21:27:06 573

原创 [论文解读]A Survey of Methods for Explaining Black Box Models

A Survey of Methods for Explaining Black Box Models文章目录A Survey of Methods for Explaining Black Box Models简介摘要可解释、可解释和可理解的模型可解释性的维度对可解释模型的渴求打开黑匣子问题问题与基于解释器的分类解决模型解释问题解决结果解释问题基于显著性掩码的深度神经网络解释解决模型检验问题通过敏感性分析进行检查通过部分依赖进行检查通过激活最大化进行检查通过树可视化进行检查解决透明盒的设计问题通过规则提

2020-10-21 17:11:55 1496 1

原创 [论文解读]Towards Improved Testing For Deep Learning

Towards Improved Testing For Deep Learning文章目录Towards Improved Testing For Deep Learning简介摘要初步背景先验文学改善的机会为什么我们需要更好的覆盖标准？为什么我们需要更好的测试输入生成？为什么我们需要一个更好的oracle呢？初步探讨和结果结论简介论文标题Towards Improved Testing For Deep Learning走向深度学习的改进测试2019提出了一种组合测试的覆盖方法,以三元

2020-10-12 14:27:03 830 6

原创 [论文解读]Adaptive Random Testing: The ART of test case diversity

Adaptive Random Testing: The ART of test case diversity文章目录Adaptive Random Testing: The ART of test case diversity简介摘要介绍关于“随机性”的一点注记故障模式自适应随机测试理论极限数字程序以外的ART进一步的影响自适应随机序列基于故障的测试一种软件测试理论测试用例多样性的作用结论简介论文标题Adaptive Random Testing: The ART of test case di

2020-09-17 21:28:32 2037

原创 ValueError: You are trying to load a weight file containing 4 layers into a model with 0 layers.

ValueError: You are trying to load a weight file containing 4 layers into a model with 0 layers.问题: 在使用keras时报如上错误,通常是由load_model函数引起的原因: load_model(model)中的参数model, model的层名称与model的权重中的层名称无法对应,从而导致权重无法加载到模型的层中解决方案通常有如下具体原因:擅自修改模型的层的名称,如以下代码 def mo

2020-08-18 14:14:10 4182

原创 [论文解读] Relating Code Coverage, Mutation Score and Test Suite Reducibility to Defect Density

Relating Code Coverage, Mutation Score and Test Suite Reducibility to Defect Density文章目录Relating Code Coverage, Mutation Score and Test Suite Reducibility to Defect Density简介摘要介绍目标和方法实验结果Properties of Subjects变异体生成突变体分类突变分数测试缩减缺陷密度结果分析相关工作结论简介论文标题Rela

2020-07-12 19:55:37 633

原创 [论文解读] Beyond Code Coverage – an Approach for Test Suite Assessment and Improvement

Beyond Code Coverage – an Approach for Test Suite Assessment and Improvement文章目录Beyond Code Coverage – an Approach for Test Suite Assessment and Improvement简介摘要介绍动机和目标TAIME 方法方法度量用例对SODA的改进相关工作前景展望简介论文标题Beyond Code Coverage – an Approach for Test Suit

2020-07-10 19:21:06 415

原创 [论文解读]Coverage Is Not Strongly Correlated with Test Suite Effectiveness

Coverage Is Not Strongly Correlated with Test Suite Effectiveness文章目录Coverage Is Not Strongly Correlated with Test Suite Effectiveness简介摘要介绍相关工作方法论术语目标程序生成错误程序生成测试套件测量覆盖范围衡量有效性结果规模是否与有效性相关当忽略规模时，覆盖率是否与有效性相关？当规模固定时，覆盖率是否与有效性相关？讨论对有效性的威胁结构有效性内部有效性外部有效性简介论

2020-07-09 14:42:44 522

原创 DeepMutation 变异操作实现代码

cnn_operator.py前馈神经网络的变异操作# 神经元随机阻塞def random_select(total_num, select_num, layer_list, layer_dict): """ :param total_num: :param select_num: :param layer_list: :param layer_dict: :return: """ indices = np.random.choice(

2020-06-28 18:06:37 613 1

原创 [论文解读] Adversarial Attacks on Deep Learning Models in Natural Language Processing: A Survey

Adversarial Attacks on Deep Learning Models in Natural Language Processing: A Survey文章目录Adversarial Attacks on Deep Learning Models in Natural Language Processing: A Survey简介摘要介绍自然语言处理中的对抗性攻击与深度学习技术综述深度学习模型的对抗性攻击：一般分类法定义威胁模型。测量。深度学习在自然语言处理中的应用从图像到文本精心制作对抗

2020-06-18 10:50:46 2947

原创 [论文解读] DeepRoad: GAN-Based Metamorphic Testing and Input Validation Framework for Autonomous Driving

DeepRoad: GAN-Based Metamorphic Testing and Input Validation Framework for Autonomous Driving Systems文章目录DeepRoad: GAN-Based Metamorphic Testing and Input Validation Framework for Autonomous Driving Systems简介摘要介绍背景DNN体系结构方法基于DNN的自动驾驶系统蜕变测试基于DNN的自动驾驶系统的输入验

2020-05-31 23:09:41 2005

原创 [论文解读] Concolic Testing for Deep Neural Networks

Concolic Testing for Deep Neural Networks文章目录Concolic Testing for Deep Neural Networks简介摘要介绍相关工作DNNs的鲁棒性Concolic测试与相关工作对比深度神经网络DNNS的覆盖测试激活模式形式化测试覆盖标准测试覆盖率指标具体覆盖要求Lipschitz连续性神经元覆盖率修改条件/决策(MC/DC)覆盖范围神经元边界覆盖我们的方法概述排名覆盖要求启发法新的具体投入的符号化生成利用线性规划进行符号分析基于全局优化的符号分

2020-05-29 17:21:40 1726

原创 [论文解读] DeepStellar: Model-Based Quantitative Analysis of Stateful Deep Learning Systems

DeepStellar: Model-Based Quantitative Analysis of Stateful Deep Learning Systems文章目录DeepStellar: Model-Based Quantitative Analysis of Stateful Deep Learning Systems简介摘要介绍综述RNN的状态转移建模RNN内部状态和状态转换抽象状态转换模型轨迹相似性度量将训练好的RNN表示为离散时间马尔可夫链RNN的覆盖标准State-Level Covera

2020-05-15 15:19:14 1310

第4章 多维信号张量表示与分析（NEW9）.pdf

sklearn与tensrflow指南中文pdf.zip

空空如也

第4章多维信号张量表示与分析（NEW9）.pdf