CurricularFace: Adaptive Curriculum Learning Loss for Deep Face Recognition

Huang, Yuge; Wang, Yuhan; Tai, Ying; Liu, Xiaoming; Shen, Pengcheng; Li, Shaoxin; Li, Jilin; Huang, Feiyue

doi:10.1109/cvpr42600.2020.00594

Cited by 467 publications

(266 citation statements)

References 26 publications

Supporting

Mentioning

258

Contrasting

Unclassified

Order By: Relevance

“…;where x i R d CurricularFace [148] L = − log e s cos(θy i +m) e s cos(θy i +m) + n j=1,j =y i e sN (t (k) ,cos θ j ) , where, N (t, cos θ j ) = { cos θj ,T (cos θy i )−cos θj <0 cos θj (t+cos θj ),T (cos θy i )−cos θj ≥0 and T (cos θ yi ) = cos(θ yi + m) of L-Softmax.…”

Section: Figure 11: Softmax Diagrammentioning

confidence: 99%

See 1 more Smart Citation

Recent Advances in Deep Learning Techniques for Face Recognition

et al. 2021

View full text Add to dashboard Cite

In recent years, researchers have proposed many deep learning (DL) methods for various tasks, and particularly face recognition (FR) made an enormous leap using these techniques. Deep FR systems benefit from the hierarchical architecture of the DL methods to learn discriminative face representation. Therefore, DL techniques significantly improve state-of-the-art performance on FR systems and encourage diverse and efficient real-world applications. In this paper, we present a comprehensive analysis of various FR systems that leverage the different types of DL techniques, and for the study, we summarize 171 recent contributions from this area. We discuss the papers related to different algorithms, architectures, loss functions, activation functions, datasets, challenges, improvement ideas, current and future trends of DL-based FR systems. We provide a detailed discussion of various DL methods to understand the current state-of-the-art, and then we discuss various activation and loss functions for the methods. Additionally, we summarize different datasets used widely for FR tasks and discuss challenges related to illumination, expression, pose variations, and occlusion. Finally, we discuss improvement ideas, current and future trends of FR tasks. INDEX TERMSDeep learning, face recognition, artificial neural network, convolutional neural network, auto encoder, generative adversarial network, deep belief network, reinforcement learning.

show abstract

Section: Figure 11: Softmax Diagrammentioning

confidence: 99%

“…Yuge et al [148] proposed a credible method named Curric-ularFace using Adaptive Curricular Learning. CurricularFace solves convergence issues of features.…”

Section: ) Curricularface: Adaptive Curriculum Learning Lossmentioning

confidence: 99%

Recent Advances in Deep Learning Techniques for Face Recognition

et al. 2021

View full text Add to dashboard Cite

show abstract

“…However, it only modifies the sine and cosine similarity of each sample to enhance feature discrimination, it could not adapt to various situations. Hence, the ACLL is proposed [16]. The ACLL was defined as Equation (12).…”

Section: Structure Of Acllmentioning

confidence: 99%

“…EER is denoted by the false rejection (FR) rate equal to the false acceptance (FA) rate, where FR is a correct signal which is recognized as a wrong signal; FA is a wrong signal which is recognized as a correct signal. Definitions of FR rate and FA rate are shown in Equation (16) and Equation (17). Where N F R is the number of false rejections and N T arget is the total number of real evaluations.…”

Section: Evaluation Indicatorsmentioning

confidence: 99%

Text-Independent Speaker Recognition Based on Adaptive Course Learning Loss and Deep Residual Network

Zhong¹,

Dai

Zhang

et al. 2021

Preprint

View full text Add to dashboard Cite

Text-independent speaker recognition is widely used in identity recognition. In order to improve the features recognition ability, a method of text-independent speaker recognition based on a deep residual network model was proposed in this paper. Firstly, the original audio was extracted with a 64-dimensional log filter bank signal features. Secondly, a deep residual network was used to extract log filter bank signal features. The deep residual network was composed of a residual network and a Convolutional Attention Statistics Pooling (CASP) layer. The CASP layer could aggregate the frame-level features from the residual network into utterance-level features. Lastly, Adaptive Curriculum Learning Loss (ACLL) classifiers was used to optimize the output of abstract features by the deep residual network, and the text-independent speaker recognition was completed by ACLL classifiers. The proposed method was applied to a large VoxCeleb2 dataset for extensive text-independent speaker recognition experiments, and average equal error rate (EER) could achieve 1.76% on VoxCeleb1 test dataset, 1.91% on VoxCeleb1-E test dataset, and 3.24% on VoxCeleb1-H test dataset. Compared with related speaker recognition methods, EER was improved by 1.11% on VoxCeleb1 test dataset, 1.04% on VoxCeleb1-E test dataset, and 1.69% on VoxCeleb1-H test dataset.

show abstract

“…The features are often extracted through multiple hidden layers of deep (convolutional) neural networks and contain representative information that is used to distinguish an individual [9]. Recent work in this domain proposed an adaptive curriculum learning loss (called CurricularFace) that embeds the idea of curriculum learning into the loss function to achieve a novel training strategy for deep face recognition, which mainly addresses easy samples in the early training stage and hard ones in the later stage [20].…”

Section: Related Workmentioning

confidence: 99%

Evaluating facial recognition services as interaction technique for recommender systems

Pessemier

Coppens

Martens

2020

Multimed Tools Appl

View full text Add to dashboard Cite

Recommender systems are tools and techniques to assist users in the content selection process thereby coping with the problem of information overload. For recommender systems, user authentication and feedback gathering are of crucial importance. However, the typical user authentication with username / password and feedback method with a star rating system are not user friendly and often bypassed. This article proposes an alternative method for user authentication based on facial recognition and an automatic feedback gathering method by detecting various face characteristics such as emotions. We studied the use case of video watching. Photos made with the front-facing camera of a tablet, smartphone, or smart TV are used as input of a facial recognition service. The persons in front of the screen can be identified. During video watching, implicit feedback for the video content is automatically gathered through emotion recognition, attention measurements, and behavior analysis. An evaluation with a test panel showed that the recognized emotions are correlated with the user's star ratings and that happiness can be most accurately detected. So as the main contribution, this article indicates that emotion recognition might be used as an alternative feedback mechanism for recommender systems.

show abstract

CurricularFace: Adaptive Curriculum Learning Loss for Deep Face Recognition

Cited by 467 publications

References 26 publications

Recent Advances in Deep Learning Techniques for Face Recognition

Recent Advances in Deep Learning Techniques for Face Recognition

Text-Independent Speaker Recognition Based on Adaptive Course Learning Loss and Deep Residual Network

Evaluating facial recognition services as interaction technique for recommender systems

Contact Info

Product

Resources

About