Recent successes of deep learning-based recognition rely on maintaining the content related to the main-task label. However, how to explicitly dispel the noisy signals for better generalization in a controllable manner remains an open issue. For instance, various factors such as identity-specific attributes, pose, illumination and expression affect the appearance of face images. Disentangling the identity-specific factors is potentially beneficial for facial expression recognition (FER). This chapter systematically summarize the detrimental factors as task-relevant/irrelevant semantic variations and unspecified latent variation. In this chapter, these problems are casted as either a deep metric learning problem or an adversarial minimax game in the latent space. For the former choice, a generalized adaptive (N+M)-tuplet clusters loss function together with the identity-aware hard-negative mining and online positive mining scheme can be used for identity-invariant FER. The better FER performance can be achieved by combining the deep metric loss and softmax loss in a unified two fully connected layer branches framework via joint optimization. For the latter solution, it is possible to equipping an end-to-end conditional adversarial network with the ability to decompose an input sample into three complementary parts. The discriminative representation inherits the desired invariance property guided by prior knowledge of the task, which is marginal independent to the task-relevant/irrelevant semantic and latent variations. The framework achieves top performance on a serial of tasks, including lighting, makeup, disguise-tolerant face recognition and facial attributes recognition. This chapter systematically summarize the popular and practical solution for disentanglement to achieve more discriminative visual recognition.
Heterogeneous Face Recognition via Face Synthesis with Identity-Attribute Disentanglement
Institute of Information Engineering, Chinese Academy of Sciences(中国科学院信息工程研究所);School of Cyber Security, University of Chinese Academy of Sciences(中国科学院大学网络空间安全学院);Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所);CAS Center for Excellence in Brain Science and Intelligence Technology(中国科学院脑科学与智能技术卓越创新中心);School of Artificial Intelligence, University of Chinese Academy of Sciences(中国科学院大学人工智能学院)
Masked Face Recognition with Generative-to-Discriminative Representations
Institute of Information Engineering, Chinese Academy of Sciences(中国科学院信息工程研究所);School of Cyber Security at University of Chinese Academy of Sciences(中国科学院大学网络空间安全学院);Cloud Music Inc.(网易云音乐);Department of Communication Engineering, Shanghai University(上海大学通信工程系)
Distilling Generative-Discriminative Representations for Very Low-Resolution Face Recognition
Institute of Information Engineering, Chinese Academy of Sciences(中国科学院信息工程研究所);School of Cyber Security, University of Chinese Academy of Sciences(中国科学院大学网络空间安全学院)
Cross-Dataset Person Re-Identification via Unsupervised Pose Disentanglement and Adaptation
National Taiwan University(台湾大学);MOST Joint Research Center for AI Technology and All Vista Healthcare(科技部AI技术与全视医疗照护联合研究中心);ASUS Intelligent Cloud Services(华硕智能云服务)
Adversarial Discriminative Heterogeneous Face Recognition
National Laboratory of Pattern Recognition, CASIA(模式识别国家重点实验室,中国科学院自动化研究所);Center for Research on Intelligent Perception and Computing, CASIA(智能感知与计算研究中心,中国科学院自动化研究所);Center for Excellence in Brain Science and Intelligence Technology, CAS(脑科学与智能技术卓越创新中心,中国科学院);University of Chinese Academy of Sciences(中国科学院大学)
MODAL: Multi-Modal Object Re-ID via Model-Driven Sparse Decoupling and Text-Image Differential Filtering
College of Computer Science and Technology, National University of Defense Technology(国防科技大学计算机科学与技术学院);School of Computer Science and Information Engineering, Hefei University of Technology(合肥工业大学计算机与信息工程学院)
Dual-Stream Reciprocal Disentanglement Learning for Domain Adaptation Person Re-Identification
Kunming University of Science and Technology(昆明理工大学);Harbin Institute of Technology, Shenzhen(哈尔滨工业大学(深圳));Chinese University of Hong Kong (Shenzhen)(香港中文大学(深圳));Shenzhen Research Institute of Big Data(深圳大数据研究院)
Focus on Local: Finding Reliable Discriminative Regions for Visual Place Recognition
Shandong Computer Science Center, Qilu University of Technology (Shandong Academy of Sciences)(齐鲁工业大学(山东省科学院)山东省计算中心);School of Artificial Intelligence, Beijing University of Posts and Telecommunications(北京邮电大学人工智能学院);Shandong Provincial Key Laboratory of Computing Power Internet and Service Computing, Shandong Fundamental Research Center for Computer Science(山东省计算机科学基础研究中心山东省算力互联网与服务计算重点实验室);Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所);Tongji University(同济大学);College of Computer and Data Science, Fuzhou University(福州大学计算机与数据科学学院);Shandong University(山东大学)
Scalable Angular Discriminative Deep Metric Learning for Face Recognition
Nankai University(南开大学);Tianjin University(天津大学)
随着深度学习的发展,深度度量学习(Deep Metric Learning,DML)在人脸识别方面取得了很大的进步。具体来说,在训练过程中广泛使用的softmax损失往往会带来很大的类内变化,而特征归一化只在测试过程中使用,以计算对相似度。为了弥补这一差距,我们在训练步骤中将softmax损失中的特征和权重向量之间的类内余弦相似性设置为大于一个裕度,并从四个方面对其进行了扩展。首先,我们探讨了硬样本挖掘策略的效果。为了减轻调整超参数的人工劳动,提出了一种自适应的边缘更新策略。然后,一个规范化的版本,以充分利用余弦相似性约束。此外,我们加强了前一个约束,迫使类内余弦相似度大于平均类间余弦相似度,在指数特征投影空间中有一个保证金。在Labeled Face in the Wild(LFW)、Youtube Faces(YTF)和IARPA Janus Benchmark A(IJB-A)数据集上进行的大量实验表明,本文提出的方法优于主流的DML方法,接近最先进的性能。
OrthoMAD: Morphing Attack Detection Through Orthogonal Identity Disentanglement
INESC TEC(葡萄牙工程与计算机系统研究所);Faculdade de Engenharia da Universidade do Porto(波尔图大学工程学院);Fraunhofer Institute for Computer Graphics Research (IGD)(弗劳恩霍夫计算机图形学研究所);Technische Universität Darmstadt(达姆施塔特工业大学)
Knowledge-guided Disentanglement with Atomic Actions for Action Recognition
Xidian University(西安电子科技大学);National University of Defense Technology(国防科技大学);Human Institute of Advanced Technologyy(人类高级技术研究院);Shanghai Road Transport Development Center(上海市道路运输发展中心)
Text-guided Feature Disentanglement for Cross-modal Gait Recognition
Fujian Key Laboratory of Urban Intelligent Sensing and Computing, Xiamen University(福建城市智能感知与计算重点实验室,厦门大学);Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University(多媒体可信感知与高效计算重点实验室,中华人民共和国教育部,厦门大学)