arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2305.00848cs.CVcs.LG
收藏

基于GPU的抗噪声ResNet-50年龄估计方法

Noise-Tolerance GPU-based Age Estimation Using ResNet-50

Vali-e-Asr University of Rafsanjan(拉夫桑詹瓦利埃阿斯尔大学);Tallinn University of Technology(塔林理工大学)

Mahtab Taheri, Mahdi Taheri, Amirhossein Hadjahmadi

AI总结:

本研究在UTKFace数据集上实现基于ResNet-50的GPU年龄估计方法,MAE相较近期工作降低28.3%、相较AlexNet降低71.39%,且在5倍正常环境噪声下性能下降不足1.5%,具备强抗噪性。

摘要:

人脸包含身份、性别、年龄、种族等重要且可解读的信息。近年来,年龄作为人脸的重要特征之一得到了广泛研究。年龄估计系统通常由两个模块组合构成:人脸图像的表征处理与年龄特征提取,随后基于这些特征判定确切年龄或年龄组。目前已有多种年龄估计算法被提出,各有优劣。本研究在UTKFace数据集上实现了一种深度残差神经网络。我们通过将其与不同年龄估计算法的当前最优实现进行对比,验证了该实现的性能:结果显示,作为关键误差验证指标之一的平均绝对误差(MAE),相较近期相关工作降低了28.3%,相较实现的AlexNet模型MAE降低了71.39%。最后我们证实,当向输入数据注入15dB噪声(为正常环境噪声的5倍)时,我们实现的网络性能下降低于1.5%,证明了所提方法的噪声耐受能力。

英文摘要:

The human face contains important and understandable information such as personal identity, gender, age, and ethnicity. In recent years, a person's age has been studied as one of the important features of the face. The age estimation system consists of a combination of two modules, the presentation of the face image and the extraction of age characteristics, and then the detection of the exact age or age group based on these characteristics. So far, various algorithms have been presented for age estimation, each of which has advantages and disadvantages. In this work, we implemented a deep residual neural network on the UTKFace data set. We validated our implementation by comparing it with the state-of-the-art implementations of different age estimation algorithms and the results show 28.3% improvement in MAE as one of the critical error validation metrics compared to the recent works and also 71.39% MAE improvements compared to the implemented AlexNet. In the end, we show that the performance degradation of our implemented network is lower than 1.5% when injecting 15 dB noise to the input data (5 times more than the normal environmental noise) which justifies the noise tolerance of our proposed method.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑