EPL: Empirical Prototype Learning for Deep Face Recognition
National Engineering Laboratory for Big Data System Computing Technology(大数据系统计算技术国家工程实验室);Computer Vision Institute, Shenzhen University(深圳大学计算机视觉研究所);School of Computer Science, University of Birmingham(伯明翰大学计算机科学学院);Aqara, Lumi United Technology Coopration(绿米联创科技有限公司(Aqara))
Weijia Fan, Jiajun Wen, Xi Jia, Linlin Shen, Jiancan Zhou, Qiufu Li
Prototype learning is widely used in face recognition, which takes the row vectors of coefficient matrix in the last linear layer of the feature extraction model as the prototypes for each class. When the prototypes are updated using the facial sample feature gradients in the model training, they are prone to being pulled away from the class center by the hard samples, resulting in decreased overall model performance. In this paper, we explicitly define prototypes as the expectations of sample features in each class and design the empirical prototypes using the existing samples in the dataset. We then devise a strategy to adaptively update these empirical prototypes during the model training based on the similarity between the sample features and the empirical prototypes. Furthermore, we propose an empirical prototype learning (EPL) method, which utilizes an adaptive margin parameter with respect to sample features. EPL assigns larger margins to the normal samples and smaller margins to the hard samples, allowing the learned empirical prototypes to better reflect the class center dominated by the normal samples and finally pull the hard samples towards the empirical prototypes through the learning. The extensive experiments on MFR, IJB-C, LFW, CFP-FP, AgeDB, and MegaFace demonstrate the effectiveness of EPL. Our code is available at $\href{https://github.com/WakingHours-GitHub/EPL}{https://github.com/WakingHours-GitHub/EPL}$.
Multi-Prototype Networks for Unconstrained Set-based Face Recognition
National University of Singapore(新加坡国立大学);National University of Defense Technology(国防科技大学);Tencent FiT DeepSea AI Lab(腾讯FiT深海人工智能实验室);University of Electronic Science and Technology of China(电子科技大学);Inception Institute of Artificial Intelligence(人工智能初创研究所);Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所);Qihoo 360 AI Institute(奇虎360人工智能研究院)
EPL: Evidential Prototype Learning for Semi-supervised Medical Image Segmentation
Key Laboratory of High Confidence Software Technologies (Peking University)(高可信软件技术重点实验室(北京大学));School of Computer Science, Peking University(北京大学计算机学院)
Physics-inspired Pseudo Anomaly Generation and Prototype Feature Guidance for 3D Anomaly Detection
School of Computer Science, Wuhan University(武汉大学计算机科学学院);Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ)(广东省人工智能与数字经济实验室(深圳));School of Information and Software Engineering, East China Jiaotong University(华东交通大学信息工程学院);School of Computer Science and Technology, Dalian University of Technology(大连理工大学计算机科学与技术学院)
Large-scale Bisample Learning on ID Versus Spot Face Recognition
College of Software, Beihang University(北京航空航天大学软件学院);DAMO Academy, Alibaba Group(阿里巴巴集团达摩院);HUAWEI Cloud, USA(美国华为云);Center for Biometrics and Security Research & National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所生物识别与安全技术研究中心&模式识别国家重点实验室)
3D Facial Imperfection Regeneration: Deep learning approach and 3D printing prototypes
CIRTECH Institute(CIRTECH研究所);HUTECH University(胡志明市工业大学);Quy Nhon University(归仁大学);China Medical University Hospital(中国医药大学附设医院);China Medical University(中国医药大学)
Diffusion Model Meets Non-Exemplar Class-Incremental Learning and Beyond
Beijing National Research Center for Information Science and Technology (BNRist)(北京信息科学与技术国家研究中心(BNRist));Department of Electronic Engineering, Tsinghua University(清华大学电子工程系)
SCKAN: Structural Consensus-based KAN Prototype Learning for Semi-Supervised Pancreas Segmentation
School of Computer Science and Technology, Tongji University, Shanghai, China(同济大学计算机科学与技术学院);Artificial Intelligence Institute, Shanghai University, Shanghai, China(上海大学人工智能研究院);Department of Computer and Data Science and Department of Biomedical Engineering, Case Western Reserve University, Cleveland, USA(凯斯西储大学计算机与数据科学系及生物医学工程系)
Mixture of Gaussian-distributed Prototypes with Generative Modelling for Interpretable and Trustworthy Image Recognition
Australian Institute for Machine Learning (AIML), University of Adelaide(阿德莱德大学澳大利亚机器学习研究所);Stanford University(斯坦福大学);Cornell University(康奈尔大学);Cornell Tech(康奈尔理工学院);University of Oxford(牛津大学);St. Vincent’s Institute of Medical Research(圣文森特医学研究所);Melbourne Integrative Genomics, The University of Melbourne(墨尔本大学墨尔本整合基因组学中心);St Vincent’s Hospital Melbourne(墨尔本圣文森特医院);Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey(萨里大学视觉、语音与信号处理中心);The University of Adelaide(阿德莱德大学)
Unified Unsupervised and Sparsely-Supervised 3D Object Detection by Semantic Pseudo-Labeling and Prototype Learning
Institute of Medical Robotics, Shanghai Jiao Tong University(上海交通大学医疗机器人研究院);Key Laboratory of System Control and Information Processing, Ministry of Education of China(系统控制与信息处理教育部重点实验室)
Decouple, Purify and Unite: Semantic-Structural Prototype Learning for Federated Medical Segmentation
Peking Union Medical College Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College(北京协和医院,中国医学科学院北京协和医学院);Beijing University of Posts and Telecommunications(北京邮电大学);Nanyang Technological University(南洋理工大学);Ant Group(蚂蚁集团);Shanghai Innovation Institute(上海创新研究院);Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所);DAMO Academy, Alibaba Group(阿里巴巴达摩院);Fourth Military Medical University(中国人民解放军空军军医大学);Macao Polytechnic University(澳门理工大学);Wuhan University(武汉大学);The Hong Kong Polytechnic University(香港理工大学)
由于面部发育的不同阶段存在较大的非线性变化,因此对面部衰老过程进行建模是一项具有挑战性的任务。本文提出了一种人脸年龄增长的深度模型方法,可以有效地捕捉非线性的老化过程,并自动合成一系列年龄增长的人脸在不同的年龄范围。在这种方法中,我们首先将长期年龄进程分解为一系列短期变化,并将其建模为人脸序列。然后,构造基于时间深度限制玻尔兹曼机的年龄进展模型以及原型人脸,以学习序列中人脸之间的老化转换。此外,为了增强在以后的年龄范围内的面部皱纹,皱纹模型进一步构建使用限制玻尔兹曼机捕捉它们在不同的面部区域的变化。在最后一步中还考虑了几何约束,以获得更一致的年龄进展结果。使用各种人脸老化数据库,即FG-NET,跨年龄名人数据集(CACD)和MORPH,以及我们收集的大型老化数据库名为AginG Faces in the Wild(AGFW),对所提出的方法进行了评估。此外,当输入图像的真实年龄不可用时,我们提出的系统能够在老化过程之前自动估计输入面部的年龄。
Can Vision Transformers with ResNet's Global Features Fairly Authenticate Demographic Faces?
National Research Council of Italy - Institute of Applied Sciences and Intelligent Systems (CNR-ISASI)(意大利国家研究 council - 应用科学和智能系统研究所(CNR-ISASI));University of Gour Banga(Gour Banga 大学);Visva-Bharati(Visva-Bharati 研究院)
Tied Prototype Model for Few-Shot Medical Image Segmentation
Department of Physics and Technology, UiT - The Arctic University of Norway(物理与技术系,UiT - 北极大学);Norwegian Centre for Clinical Artificial Intelligence (SPKI)(挪威临床人工智能中心);University Hospital of North-Norway(北挪威大学医院);Norwegian Computing Center(挪威计算中心)
Deep learning vessel segmentation and quantification of the foveal avascular zone using commercial and prototype OCT-A platforms
Simon Fraser University(西蒙菲莎大学);University of British Columbia(不列颠哥伦比亚大学);University of Western Australia(西澳大学);Lions Eye Institute(狮子眼科研究所);Vitreous Retina Macula Consultants of New York(纽约玻璃体视网膜黄斑 Consultants);Manhattan Eye, Ear and Throat Hospital(曼哈顿眼耳鼻喉医院);University of Zagreb(萨格勒布大学)