SymFace: Additional Facial Symmetry Loss for Deep Face Recognition

Pritesh Prakash, Koteswar Rao Jerripothula, Ashish Jacob Sam, Prinsh Kumar Singh, S Umamaheswaran
{"title":"SymFace: Additional Facial Symmetry Loss for Deep Face Recognition","authors":"Pritesh Prakash, Koteswar Rao Jerripothula, Ashish Jacob Sam, Prinsh Kumar Singh, S Umamaheswaran","doi":"arxiv-2409.11816","DOIUrl":null,"url":null,"abstract":"Over the past decade, there has been a steady advancement in enhancing face\nrecognition algorithms leveraging advanced machine learning methods. The role\nof the loss function is pivotal in addressing face verification problems and\nplaying a game-changing role. These loss functions have mainly explored\nvariations among intra-class or inter-class separation. This research examines\nthe natural phenomenon of facial symmetry in the face verification problem. The\nsymmetry between the left and right hemi faces has been widely used in many\nresearch areas in recent decades. This paper adopts this simple approach\njudiciously by splitting the face image vertically into two halves. With the\nassumption that the natural phenomena of facial symmetry can enhance face\nverification methodology, we hypothesize that the two output embedding vectors\nof split faces must project close to each other in the output embedding space.\nInspired by this concept, we penalize the network based on the disparity of\nembedding of the symmetrical pair of split faces. Symmetrical loss has the\npotential to minimize minor asymmetric features due to facial expression and\nlightning conditions, hence significantly increasing the inter-class variance\namong the classes and leading to more reliable face embedding. This loss\nfunction propels any network to outperform its baseline performance across all\nexisting network architectures and configurations, enabling us to achieve SoTA\nresults.","PeriodicalId":501130,"journal":{"name":"arXiv - CS - Computer Vision and Pattern Recognition","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2024-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - CS - Computer Vision and Pattern Recognition","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2409.11816","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

Abstract

Over the past decade, there has been a steady advancement in enhancing face recognition algorithms leveraging advanced machine learning methods. The role of the loss function is pivotal in addressing face verification problems and playing a game-changing role. These loss functions have mainly explored variations among intra-class or inter-class separation. This research examines the natural phenomenon of facial symmetry in the face verification problem. The symmetry between the left and right hemi faces has been widely used in many research areas in recent decades. This paper adopts this simple approach judiciously by splitting the face image vertically into two halves. With the assumption that the natural phenomena of facial symmetry can enhance face verification methodology, we hypothesize that the two output embedding vectors of split faces must project close to each other in the output embedding space. Inspired by this concept, we penalize the network based on the disparity of embedding of the symmetrical pair of split faces. Symmetrical loss has the potential to minimize minor asymmetric features due to facial expression and lightning conditions, hence significantly increasing the inter-class variance among the classes and leading to more reliable face embedding. This loss function propels any network to outperform its baseline performance across all existing network architectures and configurations, enabling us to achieve SoTA results.
SymFace:深度人脸识别的额外面部对称性损失
过去十年来,利用先进的机器学习方法改进人脸识别算法的工作取得了稳步进展。损失函数在解决人脸识别问题中起着举足轻重的作用,并扮演着改变游戏规则的角色。这些损失函数主要探讨了类内或类间分离的变化。本研究探讨了人脸验证问题中的人脸对称这一自然现象。近几十年来,左右半边脸对称已被广泛应用于许多研究领域。本文采用这种简单的方法,将人脸图像垂直分成两半。受这一概念的启发,我们根据对称的一对分割人脸的嵌入差异对网络进行惩罚。对称损失有可能最大限度地减少由于面部表情和光照条件而导致的轻微不对称特征,从而显著增加类间差异,实现更可靠的人脸嵌入。这种损耗功能可以推动任何网络在所有现有网络架构和配置中超越其基准性能,从而使我们获得 SoTA 结果。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信