We present a novel online self-supervised method for face identity learning from video streams. The method exploits deep face feature descriptors together with a memory based learning mechanism that takes advantage of the temporal coherence of visual data. Specifically, we introduce a discriminative descriptor matching solution based on Reverse Nearest Neighbor and a memory based cumulative learning strategy that discards redundant descriptors while time progresses. This allows building a comprehensive and cumulative representation of all the past visual information observed so far. It is shown that the proposed learning procedure is asymptotically stable and can be effectively used in relevant applications like multiple face identification and tracking from unconstrained video streams. Experimental results show that the proposed method achieves comparable results in the task of multiple face tracking and better performance in face identification with offline approaches exploiting future information.

我们提出了一种新颖的在线自我监督方法，用于从视频流中学习人脸身份。该方法利用深脸特征描述符以及利用视觉数据的时间一致性的基于记忆的学习机制。具体来说，我们介绍了一种基于反向最近邻的判别描述符匹配解决方案和一种基于内存的累积学习策略，该策略在时间经过时会丢弃冗余描述符。这样就可以对到目前为止观察到的所有过去的视觉信息进行全面和累积的表示。结果表明，所提出的学习过程是渐近稳定的，可以有效地用于相关应用中，例如多人脸识别和不受约束的视频流跟踪。