ID 原文 译文
40086 在实现差分隐私保护的同时，有效地减少了训练过程中隐私预算的消耗。 While achieving differential privacy protection, IDP-GAN effectively reduces the consumption of privacy budget during training.
40087 标准数据集MNIST和CelebA上的实验验证了IDP-GAN可以生成更高质量的图像数据，此外用成员推理攻击实验证明了IDP-GAN具有较好的抗攻击能力。 Experiments on the standard data sets MNIST and CelebA verify that IDP-GAN can generate higher quality image data.In addition, membership inference attacks experiments prove that IDP-GAN has better ability to resist attacks.
40088 针对现实场景中遮挡人脸检测精度低的问题，提出了一种基于汇聚CNN和注意力增强网络的遮挡人脸检测方法。 Aiming at the problem of low detection accuracy of occluded faces in real scenes, an occluded face detection method based on convergent convolutional neural network(CNN) and attention enhancement network was proposed.
40089 首先，在主网络的多层原始特征图上，通过有监督学习的方法增强原始特征图中人脸可见部分的响应值。 First, on the multi-layer original feature map of the main network, the response value of the visible part of the face in the original feature map is enhanced by supervised learning.
40090 然后，将多个增强特征图组合成附加增强网络与主网络汇聚设置，以加快对多尺度遮挡人脸的检测速度。 Then, multiple enhanced feature maps are combined into an additional enhanced network and set in converge with the main network to accelerate the detection of multi-scale occlusion faces.
40091 最后，将有监督信息分散到各个尺寸的特征图上进行监督学习，为不同尺寸的特征图设置了基于锚框尺寸的损失函数。 Finally, supervised information is distributed to feature maps of various sizes for supervised learning, and loss functions based on anchor frame sizes are set for feature maps of different sizes.
40092 在WIDER FACE和MAFA数据集上的实验结果表明，该方法的检测精度高于当前主流人脸检测方法。 Experimental results on WIDER FACE and MAFA datasets show that the detection accuracy of the proposed method is higher than the current mainstream face detection methods.
40093 行人再识别技术目前逐步被应用于视频监控、智能安防等领域。 As security issues have received widespread attention, the research on person re-identification has become more realistic, which is gradually being applied to video surveillance, intelligent security and other fields.
40094 监控设备与日俱增，给研究工作提供了海量数据支持，但人工标注或检测器识别难以避免地引入带有噪声的数据标签。 The increasing of the number of monitoring equipments provides massive data support for research, but manual labeling or detector recognition inevitably introduces noisy labels.
40095 在进行大规模深度神经网络训练时，伴随数据量增加，标签的噪声给模型训练带来不可忽视的损害。 When training large-scale deep neural networks, as the amount of data increases, the noise of the label brings nonnegligible damage to model training.