In this paper we present an efficient implementation using triplet loss for face recognition. We conduct the practical experiment to analyze the factors that influence the training of triplet loss. All models are trained on CASIA-Webface dataset and tested on LFW. We analyze the experiment results and give some insights to help others balance the factors when they apply triplet loss to their own problem especially for face recognition task. Code has been released in https://github.com/yule-li/MassFace.
翻译:在本文中,我们用三重损失来进行面部识别,以高效地实施三重损失;我们进行实际实验,分析影响三重损失培训的因素;所有模型都接受CASIA-Webface数据集的培训,并在LFW上进行测试;我们分析实验结果,提供一些见解,帮助他人平衡在对自身问题适用三重损失时,特别是为了面部识别任务,三重损失的因素。代码已在https://github.com/yule-li/MassFace上公布。