arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1807.09192cs.CV
收藏

用于人脸识别的多列网络

Multicolumn Networks for Face Recognition

University of Oxford(牛津大学)

Weidi Xie, Andrew Zisserman

摘要:

这项工作的目标是基于集合的人脸识别,即决定是否两组图像的人脸是同一个人或没有。传统上,集合式特征描述符被计算为来自集合内的各个面部图像的描述符的平均值。在本文中,我们设计了一个神经网络架构,学习聚合的基础上“视觉”质量(分辨率,照明),和“内容”质量(相对重要性的区别性分类)。为此,我们提出了一个多列网络(MN),它将一组图像(集合中的数量可以变化)作为输入,并学习为整个集合计算固定大小的特征描述符。为了鼓励高质量的表示,每个单独的输入图像首先通过其“视觉”质量进行加权,由自我质量评估模块确定,然后基于相对于集合中其他图像的“内容”质量进行动态重新校准。这两种品质都是在集合分类的训练过程中隐式学习的。与之前使用相同数据集(VGGFace 2)训练的最先进架构相比,我们的多列网络在IARPA IJB人脸识别基准测试中显示出2-6%的改进,并且超过了这些基准测试中所有方法的最先进水平。

英文摘要:

The objective of this work is set-based face recognition, i.e. to decide if two sets of images of a face are of the same person or not. Conventionally, the set-wise feature descriptor is computed as an average of the descriptors from individual face images within the set. In this paper, we design a neural network architecture that learns to aggregate based on both "visual" quality (resolution, illumination), and "content" quality (relative importance for discriminative classification). To this end, we propose a Multicolumn Network (MN) that takes a set of images (the number in the set can vary) as input, and learns to compute a fix-sized feature descriptor for the entire set. To encourage high-quality representations, each individual input image is first weighted by its "visual" quality, determined by a self-quality assessment module, and followed by a dynamic recalibration based on "content" qualities relative to the other images within the set. Both of these qualities are learnt implicitly during training for set-wise classification. Comparing with the previous state-of-the-art architectures trained with the same dataset (VGGFace2), our Multicolumn Networks show an improvement of between 2-6% on the IARPA IJB face recognition benchmarks, and exceed the state of the art for all methods on these benchmarks.

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。

↑