Toward End-to-End Face Recognition Through Alignment Learning

A common practice in modern face recognition methods is to specifically align the face area based on the prior knowledge of human face structure before recognition feature extraction. The face alignment is usually implemented independently, causing difficulties in the designing of end-to-end face recognition models. We study the possibility of end-to-end face recognition through alignment learning in which neither prior knowledge on facial landmarks nor artificially defined geometric transformations are required. Only human identity clues are used for driving the automatic learning of appropriate geometric transformations for the face recognition task. Trained purely on publicly available datasets, our model achieves a verification accuracy of 99.33% on the LFW dataset, which is on par with state-of-the-art single model methods.