ArcFace: Additive Angular Margin Loss for Deep Face Recognition
By Jiankang Deng, Jia Guo, Stefanos P. Zafeiriou. 2018
8,069 citations recorded by the source corpus.
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.
Subfields: Computer Vision and Pattern Recognition, Signal Processing
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Computer Vision and Pattern Recognition
- Luc Van Gool
- Dacheng Tao
- Xiaogang Wang
- Ming-Hsuan Yang
- Trevor Darrell
- Yi Yang
- Andrew Zisserman
- Chen Change Loy
In Signal Processing
- Weihong Deng
- Xiaoming Liu
- Xiaoou Tang
- Mei Wang
- Xiaogang Wang
- Lior Wolf
- Anil K. Jain
- Stefanos P. Zafeiriou
Citations in the corpus
- Diffusion Autoencoders: Toward a Meaningful and Decodable Representation (2021, methodology): “And we test how much the input’s identity is preserved via ArcFace [10] and quantify the manipulation quality in Appendix G.”
- StyleCLIP: Text-Driven Manipulation of StyleGAN Imagery (2021, background): “whereR is a pretrained ArcFace [7] network for face recognition, and 〈·, ·〉 computes the cosine similarity between it’s arguments.”
- Diversity in Faces (2019, methodology): “The gender annotations used two class labels (male and female) and the age group labeling used seven classes ([0-3],[4-12],[13-19],[20-30],[31-45],[46-60],[61-]), as well as a continuous age value to be consistent with the automatic prediction labels.”
- Continual Learning by Modeling Intra-Class Variation (2022, background): “The intuition of why MOCA can well regularize the representation space also comes from the series of works in large-margin softmax (Liu et al., 2016; 2017a;b; 2022; Wang et al., 2018a;b; Deng et al., 2019).”
- Margin-Based Few-Shot Class-Incremental Learning with Class-Level Overfitting Mitigation (2022, background): “Margin-based classification [29, 34, 11, 21] has been widely utilized in metric learning.”
- Few-Shot Class-Incremental Learning from an Open-Set Perspective (2022, positive): “Following SphereFace, CosFace [21] and ArcFace [6] were proposed to reduce the complex loss calculation and make the training procedure more stable.”
- Large-Scale Long-Tailed Recognition in an Open World (2019, methodology): “MS1M-LT: To create a long-tailed version of the MS1MArcFace dataset [14, 8], we sample images for each identity with a probability proportional to the image numbers of each identity.”
- Designing an encoder for StyleGAN image manipulation (2021, methodology): “Note that in the facial domain, we adopt the original identity loss used in pSp, and employ a pretrained ArcFace [9] facial recognition network for extracting the feature embeddings.”
- Encoding in Style: a StyleGAN Encoder for Image-to-Image Translation (2020, methodology): “To tackle this, we incorporate a dedicated recognition loss measuring the cosine similarity between the output image and its source, where R is the pretrained ArcFace [9] network.”
- Bi-Objective Continual Learning: Learning 'New' While Consolidating 'Known' (2020, background): “…(Krizhevsky, Sutskever, and Hinton 2012; He et al. 2015; Wang et al. 2010; Ren et al. 2015; Redmon et al. 2015; Cheng et al. 2016; Shun et al. 2016; Long, Shelhamer, and Darrell 2015; Chen et al. 2017; Liu et al. 2017; Deng et al. 2018; Tusng-Yu, Aruni, and Subhransu 2015; Wei et al. 2018a; 2018b).”
- Continual Representation Learning for Biometric Identification (2020, background): “Biometric identification [23,51], including face recognition [11, 37, 67] and person re-identification (re-id) [34, 66, 71], has achieved significant progress in the recent years due to the advances in modern learnable representations [8, 9, 11, 20, 34, 52, 60, 67] and emerging large datasets [17, 2”
- Identity-Guided Face Generation with Multi-Modal Contour Conditions (2021, methodology): “To preserve the original personal identity, we optimize the identity loss by calculating the cosine similarity between the identity feature of the output and identity images: Lid = 1− zid · zgen ‖zid‖ ‖zgen‖ , (4) 对比其他模型 图片号记录:对比其他模型 where zid and zgen respectively denote the basis feature of the id”
- Learning from the Past: Meta-Continual Learning with Knowledge Embedding for Jointly Sketch, Cartoon, and Caricature Face Recognition (2020, methodology): “Baselines for Face Recognition We compare against various state-of-the-art baselines for face recognition, including CenterLoss Face [49], SphereFace [26], CosFace [45] and ArcFace [9].”
- Quality-Agnostic Image Recognition via Invertible Decoder (2021, methodology): “We train LResNet50A-IR [6] for CASIA-Webface training dataset [12].”
- FastReID: A Pytorch Toolbox for General Instance Re-identification (2020, methodology): “Therefore, we try to obtain the similar scores for all spatial features of X with respect to Y , and the final matching score can be defined as:”
- SimSwap: An Efficient Framework For High Fidelity Face Swapping (2020, methodology): “As for the face recognition model in the ID Injection Module, we use a pretrained Arcface [8] model on [9].”