This work proposes to solve the problem of few-shot biometric authentication by computing the Mahalanobis distance between testing embeddings and a multivariate Gaussian distribution of training embeddings obtained using pre-trained CNNs. Experimental results show that models pre-trained on the ImageNet dataset significantly outperform models pre-trained on human faces. With a VGG16 model, we obtain a FRR of 1.18% for a FAR of 1.25% on a dataset of 20 cattle identities.

翻译：本研究提出通过计算测试嵌入与预训练CNN获取的训练嵌入多元高斯分布之间的马氏距离，来解决少样本生物特征认证问题。实验结果表明，在ImageNet数据集上预训练的模型显著优于在人脸数据集上预训练的模型。采用VGG16模型时，在包含20个牛只身份的数据集上，当错误接受率为1.25%时，错误拒绝率达1.18%。