人脸看起来相似不等于人脸识别相近 Finding your Lookalike: Measuring Face Similarity Rather than Face Identity

Finding your Lookalike: Measuring Face Similarity Rather than Face Identity

Face images are one of the main areas of focus for computer vision, receiving on a wide variety of tasks. Although face recognition is probably the most widely researched, many other tasks such as kinship detection, facial expression classification and facial aging have been examined. In this work we propose the new, subjective task of quantifying perceived face similarity between a pair of faces. That is, we predict the perceived similarity between facial images, given that they are not of the same person. Although this task is clearly correlated with face recognition, it is different and therefore justifies a separate investigation. Humans often remark that two persons look alike, even in cases where the persons are not actually confused with one another. In addition, because face similarity is different than traditional image similarity, there are challenges in data collection and labeling, and dealing with diverging subjective opinions between human labelers. We present evidence that finding facial look-alikes and recognizing faces are two distinct tasks. We propose a new dataset for facial similarity and introduce the Lookalike network, directed towards similar face classification, which outperforms the ad hoc usage of a face recognition network directed at the same task.

这篇文章很有意思,人眼看起来像的人脸(感知脸部相似性)和人脸识别系统认为相似的人脸是不一样的,这是一个新的好玩的问题。这在某种程度上也说明,目前深度学习系统和我们人类大脑的识别原理不同。

人脸图像是计算机视觉的主要关注领域之一,可以涉及到各种各样的任务。虽然人脸识别可能是最广泛研究的,但还有许多其他任务,例如亲属关系检测,面部表情分类和面部老化等。在这项工作中,我们提出量化一对脸部之间的感知脸部相似性的新的主观任务。也就是说,我们预测面部图像之间的感知相似性,因为它们本就不是同一个人。虽然这项任务明显与脸部识别相关,但它是不同的,因此有理由进行单独的研究。人们经常说,即使在人们并没有真正混淆的情况下,两个人看起来也是一样的。另外,由于人脸相似度与传统图像相似度不同,数据收集和标签方面存在挑战,并且处理人类贴标签者之间的主观意见分歧。我们提出的证据表明找到面部相像和识别面孔是两个截然不同的任务。我们提出了一个面部相似性的新数据集,并引入了类似人脸分类的Lookalike网络,该方法优于临时拿来使用的面向相同任务的人脸识别网络。

https://arxiv.org/abs/1806.05252v1

转载请注明:《人脸看起来相似不等于人脸识别相近 Finding your Lookalike: Measuring Face Similarity Rather than Face Identity

发表评论