当人脸识别遇到人脸年龄合成：一个多任务学习框架
When Age-Invariant Face Recognition Meets Face Age Synthesis: A Multi-Task Learning Framework
摘要：
为了最大限度地减少年龄变化对人脸识别的影响，以往的工作要么通过最小化身份和年龄相关特征之间的相关性来提取身份相关的鉴别特征，称为年龄不变人脸识别（AIFR），要么通过将不同年龄组的人脸转换为相同年龄组来消除年龄变化，称为人脸年龄合成（FAS）;然而，前者缺乏用于模型解释的视觉结果，而后者遭受影响下游识别的伪像。因此，本文提出了一个统一的，多任务的框架来共同处理这两个任务，称为MTLFace，它可以学习年龄不变的身份相关表示，同时实现令人愉快的人脸合成。具体来说，我们首先通过注意力机制将混合人脸特征分解为两个不相关的成分-身份和年龄相关特征，然后使用多任务训练和连续域自适应将这两个成分去相关。与传统的实现组级FAS的独热编码相比，我们提出了一种新的身份条件模块来实现身份级FAS，并采用权重共享策略来提高合成人脸的年龄平滑度。此外，我们还收集并发布了一个带有年龄和性别注释的大型跨年龄人脸数据集，以推进AIFR和FAS的开发。在五个基准跨年龄数据集上进行的广泛实验表明，我们提出的MTLFace比现有的AIFR和FAS最先进的方法具有更好的性能。我们进一步验证MTLFace在两个流行的一般人脸识别数据集，显示在野外人脸识别的竞争力的表现。源代码和数据集可在~ \url{https://github.com/Hzzone/MTLFace}获得。
英文摘要：
To minimize the effects of age variation in face recognition, previous work either extracts identity-related discriminative features by minimizing the correlation between identity- and age-related features, called age-invariant face recognition (AIFR), or removes age variation by transforming the faces of different age groups into the same age group, called face age synthesis (FAS); however, the former lacks visual results for model interpretation while the latter suffers from artifacts compromising downstream recognition. Therefore, this paper proposes a unified, multi-task framework to jointly handle these two tasks, termed MTLFace, which can learn age-invariant identity-related representation while achieving pleasing face synthesis. Specifically, we first decompose the mixed face feature into two uncorrelated components -- identity- and age-related feature -- through an attention mechanism, and then decorrelate these two components using multi-task training and continuous domain adaption. In contrast to the conventional one-hot encoding that achieves group-level FAS, we propose a novel identity conditional module to achieve identity-level FAS, with a weight-sharing strategy to improve the age smoothness of synthesized faces. In addition, we collect and release a large cross-age face dataset with age and gender annotations to advance the development of the AIFR and FAS. Extensive experiments on five benchmark cross-age datasets demonstrate the superior performance of our proposed MTLFace over existing state-of-the-art methods for AIFR and FAS. We further validate MTLFace on two popular general face recognition datasets, showing competitive performance for face recognition in the wild. The source code and dataset are available at~\url{https://github.com/Hzzone/MTLFace}.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
