基于图网络的半监督人脸识别
张琪
2020-05-27
Pages72
Subtype硕士
Abstract

    尽管近些年来,人脸识别取得了相当可观的成绩,但它在很大程度上依赖于大规模的标记数据来训练高容量的深度卷积神经网络。收集更大的标记数据集以进一步提高性能是不切实际的,这需要繁重且昂贵的标注工作。同时,现实中存在许多未标记的人脸图像。联合使用有限的标记数据和大量的未标记数据来获得更高的性能增益,这一任务是具有挑战性但有前景的,它同时也是半监督学习的目标。
    本文提出了一种自底向上的方法,即自适应邻域感知注意力网络,用于半监督开集场景下的人脸识别。它包含基于邻域感知注意力网络的协同关系预测和基于异常邻居检测的自适应邻域建图。基于邻域感知注意力网络的协同关系预测,是判断两个节点的连接关系,并依据这些关系来将未标记的人脸图像聚类, 其中邻域被定义为以给定样本为中心的n阶自我中心网络。考虑到邻居节点在计算中的不同重要性,本文采用图注意力机制来学习中心节点的特征表示。在人脸数据集 MegaFace 和 IJB-A 上的实验结果表明,提出的方法都有效提高了基准模型的性能。
    除此之外,本文在上述框架中还引入了异常邻居检测分支,以适应性地为每个节点构建不同尺寸的自我中心网络,旨在解决在人脸识别场景下常见的样本类别数量不平衡问题。这个设计在保证邻域信息丰富的前提下,减少了中心节点特征受到噪声的干扰程度。在人脸识别数据集 MegaFace 和 IJB-A 上的实验结果表明,模型对噪声更加鲁棒,能够获得更好的性能。

Other Abstract

    Although face recognition has achieved fairly remarkable results in recent years, it heavily relies on large-scale labeled data to train the high-capacity deep convolutional neural networks. It is unrealistic to collect larger labeled datasets to further boost the performance, which requires burdensome and expensive annotation efforts. Meanwhile, there exist numerous unlabeled face images. It is challenging but promising to jointly utilize limited labeled and abundant unlabeled data to obtain higher performance gain, which is the target of semi-supervised learning.
    In this paper, we propose a bottom-up method, Adaptive Neighborhood-Aware Attention Network, for semi-supervised face recognition. It includes collaborative relationship prediction based on neighborhood information, and adaptive neighborhood construction based on abnormal neighbor detection. The former is to predict the connection relationship between two nodes, and cluster unlabeled face images based on these relationships, where the neighborhood is defined as a n-hop ego network centered in the given sample called “ego”. Considering the different importance of neighbors, we employ the graph attention network to learn the ego’s representation. The experimental results on MegaFace and IJB-A show that the proposed method can effectively improve the performance of the baseline model.
    Moreover, we introduce the abnormal neighbor detection branch to adaptively construct the ego networks of different sizes, which can deal with the imbalanced classes problem. This design reduces the interference of noise in the feature updating process of target samples on the premise that the neighborhood information is rich enough. The experimental results on MegaFace and IJB-A show that the model with the abnormal neighbor detection branch is more robust to noise and yields better performance.

Keyword半监督学习 人脸识别 自我中心网络 异常邻居检测
Language中文
Sub direction classification生物特征识别
Document Type学位论文
Identifierhttp://ir.ia.ac.cn/handle/173211/39248
Collection多模态人工智能系统全国重点实验室_生物识别与安全技术
Recommended Citation
GB/T 7714
张琪. 基于图网络的半监督人脸识别[D]. 中科院自动化所. 中国科学院大学,2020.
Files in This Item:
File Name/Size DocType Version Access License
张琪-基于图网络的半监督人脸识别.pdf(5303KB)学位论文 开放获取CC BY-NC-SA
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[张琪]'s Articles
Baidu academic
Similar articles in Baidu academic
[张琪]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[张琪]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.