基于Transformer的跨年龄人脸识别方法

Transformer for Age-Invariant Face Recognition

人脸特征随着年龄变化而变化,会严重影响人脸识别的性能。提出一种基于Transformer的跨年龄人脸识别方法,首先通过改善的T2T-ViT模型提取人脸年龄和身份混合特征,然后通过残差因子分解获取人脸年龄特征和身份特征,再使用线性特征分解的去相关对抗式学习算法对人脸的年龄特征和身份特征去除相关性,从而实现年龄抗干扰性的人脸识别。相比基于卷积神经网络的DAL和MTLFace方法,所提方法在参数量、multiply-add operations(MACs)和计算耗时上均有明显降低,同时在基准数据集AgeDB-30、CACD_VS、CALFW、LFW上取得了相媲美的准确率,证明了所提方法的有效性。

The change in the facial features with age is a crucial factor affecting the performance of face recognition systems.Therefore,this paper proposes a crossage face recognition method based on a Transformer.First,the improved T2TViT model was used to extract mixed features considering the age and identity.The extracted age and identity features were obtained through residual factor decomposition.Subsequently,the correlation between the age and identity features was removed using a decorrelated adversarial learning algorithm with linear feature decomposition to achieve ageinvariant face recognition.Compared with the convolutional neural networkbased DAL and MTLFace methods,the improved model significantly reduces the number of model parameters,multiplyadd operations(MACs),and calculation time.Finally,the effectiveness of the proposed method is verified using the recognition results on benchmark datasets,AgeDB30,CACD_VS,CALFW,and LFW,and the accuracy of the proposed method is comparable to that of the DAL and MTLFace methods for ageinvariant face recognition.