ArcFace: Additive Angular Margin Loss for Deep Face Recognition
Jiankang Deng,Jia Guo,Niannan Xue,Stefanos Zafeiriou +3 more
- pp 4690-4699
TLDR
This paper presents arguably the most extensive experimental evaluation against all recent state-of-the-art face recognition methods on ten face recognition benchmarks, and shows that ArcFace consistently outperforms the state of the art and can be easily implemented with negligible computational overhead.Abstract:
One of the main challenges in feature learning using Deep Convolutional Neural Networks (DCNNs) for large-scale face recognition is the design of appropriate loss functions that can enhance the discriminative power. Centre loss penalises the distance between deep features and their corresponding class centres in the Euclidean space to achieve intra-class compactness. SphereFace assumes that the linear transformation matrix in the last fully connected layer can be used as a representation of the class centres in the angular space and therefore penalises the angles between deep features and their corresponding weights in a multiplicative way. Recently, a popular line of research is to incorporate margins in well-established loss functions in order to maximise face class separability. In this paper, we propose an Additive Angular Margin Loss (ArcFace) to obtain highly discriminative features for face recognition. The proposed ArcFace has a clear geometric interpretation due to its exact correspondence to geodesic distance on a hypersphere. We present arguably the most extensive experimental evaluation against all recent state-of-the-art face recognition methods on ten face recognition benchmarks which includes a new large-scale image database with trillions of pairs and a large-scale video dataset. We show that ArcFace consistently outperforms the state of the art and can be easily implemented with negligible computational overhead. To facilitate future research, the code has been made available.read more
Citations
More filters
Proceedings ArticleDOI
Importance of different facial parts for face detection networks
TL;DR: In this paper, the accuracy of three off-the-shelf face detection algorithms (MTCNN, Retinaface, and DLIB) on occluded faces is evaluated.
Proceedings ArticleDOI
High PE Utilization CNN Accelerator with Channel Fusion Supporting Pattern-Compressed Sparse Neural Networks
Jingyu Wang,Songming Yu,Jinshan Yue,Zhe Yuan,Zhuqing Yuan,Huazhong Yang,Xueqing Li,Yongpan Liu +7 more
TL;DR: The software includes an ADMM-based method which compresses the patterns of convolution kernels with acceptable accuracy loss, and a Huffman encoding method which reduces index storage overhead, and the hardware is a fusion-enabled systolic architecture which can reduce PEs’ no-load rate and improve performance by supporting the channel fusion.
Journal ArticleDOI
Robot System Assistant (RoSA): Towards Intuitive Multi-Modal and Multi-Device Human-Robot Interaction
Dominykas Strazdas,Jan Hintz,Aly Khalifa,Ahmed A. Abdelrahman,Thorsten Hempel,Ayoub Al-Hamadi +5 more
TL;DR: This paper designs and implements a new multi-modal system for contactless human-machine interaction based on speech, facial, and gesture recognition and reports that the method achieves similar usability scores compared to the entirely human remote-controlled robot interaction in the authors' Wizard of Oz study.
Proceedings ArticleDOI
Human Activity Classification Using mm-Wave FMCW Radar by Improved Representation Learning
TL;DR: The paper proposes a novel Euclidean distance softmax layer for radar-based human activity classification that increases the robustness against random and unknown movements compared to state-of-art representation learning techniques.
Posted Content
Identity-Driven DeepFake Detection
Xiaoyi Dong,Jianmin Bao,Dongdong Chen,Weiming Zhang,Nenghai Yu,Dong Chen,Fang Wen,Baining Guo +7 more
TL;DR: This work presents an alternative approach to DeepFake detection that focuses on whether the identity in the suspect image/video is true, and presents a simple identity-based detection algorithm called the OuterFace, which achieves superior detection accuracy and generalizes well to different DeepFake methods, and is robust with respect to video degradation techniques.
References
More filters
Proceedings ArticleDOI
Deep Residual Learning for Image Recognition
TL;DR: In this article, the authors proposed a residual learning framework to ease the training of networks that are substantially deeper than those used previously, which won the 1st place on the ILSVRC 2015 classification task.
Journal Article
Dropout: a simple way to prevent neural networks from overfitting
TL;DR: It is shown that dropout improves the performance of neural networks on supervised learning tasks in vision, speech recognition, document classification and computational biology, obtaining state-of-the-art results on many benchmark data sets.
Proceedings Article
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
Sergey Ioffe,Christian Szegedy +1 more
TL;DR: Applied to a state-of-the-art image classification model, Batch Normalization achieves the same accuracy with 14 times fewer training steps, and beats the original model by a significant margin.
Automatic differentiation in PyTorch
Adam Paszke,Sam Gross,Soumith Chintala,Gregory Chanan,Edward Z. Yang,Zachary DeVito,Zeming Lin,Alban Desmaison,Luca Antiga,Adam Lerer +9 more
TL;DR: An automatic differentiation module of PyTorch is described — a library designed to enable rapid research on machine learning models that focuses on differentiation of purely imperative programs, with a focus on extensibility and low overhead.
Posted Content
TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
Martín Abadi,Ashish Agarwal,Paul Barham,Eugene Brevdo,Zhifeng Chen,Craig Citro,Greg S. Corrado,Andy Davis,Jeffrey Dean,Matthieu Devin,Sanjay Ghemawat,Ian Goodfellow,Andrew Harp,Geoffrey Irving,Michael Isard,Yangqing Jia,Rafal Jozefowicz,Lukasz Kaiser,Manjunath Kudlur,Josh Levenberg,Dan Mané,Rajat Monga,Sherry Moore,Derek G. Murray,Chris Olah,Mike Schuster,Jonathon Shlens,Benoit Steiner,Ilya Sutskever,Kunal Talwar,Paul A. Tucker,Vincent Vanhoucke,Vijay K. Vasudevan,Fernanda B. Viégas,Oriol Vinyals,Pete Warden,Martin Wattenberg,Martin Wicke,Yuan Yu,Xiaoqiang Zheng +39 more
TL;DR: The TensorFlow interface and an implementation of that interface that is built at Google are described, which has been used for conducting research and for deploying machine learning systems into production across more than a dozen areas of computer science and other fields.