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
Journal ArticleDOI
Additive Margin Softmax for Face Verification
TL;DR: In this paper, the authors proposed a conceptually simple and intuitive learning objective function, i.e., additive margin softmax, for face verification, which is more intuitive and interpretable.
Proceedings ArticleDOI
Large-Scale Long-Tailed Recognition in an Open World
TL;DR: An integrated OLTR algorithm is developed that maps an image to a feature space such that visual concepts can easily relate to each other based on a learned metric that respects the closed-world classification while acknowledging the novelty of the open world.
Proceedings ArticleDOI
MaskGAN: Towards Diverse and Interactive Facial Image Manipulation
TL;DR: MaskGAN as mentioned in this paper proposes MaskGAN to enable diverse and interactive face manipulation by learning style mapping between a free-form user modified mask and a target image, enabling diverse generation results.
Proceedings ArticleDOI
RetinaFace: Single-Shot Multi-Level Face Localisation in the Wild
TL;DR: A novel single-shot, multi-level face localisation method, named RetinaFace, which unifies face box prediction, 2D facial landmark localisation and 3D vertices regression under one common target: point regression on the image plane.
Proceedings ArticleDOI
ECAPA-TDNN : Emphasized Channel Attention, Propagation and Aggregation in TDNN based speaker verification
TL;DR: The proposed ECAPA-TDNN architecture significantly outperforms state-of-the-art TDNN based systems on the Voxceleb test sets and the 2019 VoxCeleb Speaker Recognition Challenge.
References
More filters
Proceedings Article
Learning towards Minimum Hyperspherical Energy
TL;DR: The redundancy regularization problem is reduced to generic energy minimization, and a minimum hyperspherical energy (MHE) objective is proposed as generic regularization for neural networks.
Posted Content
Face Recognition via Centralized Coordinate Learning.
Xianbiao Qi,Lei Zhang +1 more
TL;DR: This work formulate jointly the learning of face features and classification vectors, and propose a simple yet effective centralized coordinate learning (CCL) method, which enforces the features to be dispersedly spanned in the coordinate space while ensuring the classification vectors to lie on a hypersphere.
Proceedings Article
Multicolumn Networks for Face Recognition
Weidi Xie,Andrew Zisserman +1 more
TL;DR: In this paper, a multicolumn network (MN) is proposed for set-based face recognition, which takes a set of images (the number in the set can vary) as input, and learns to compute a fix-sized feature descriptor for the entire set.
Posted Content
Rethinking Feature Distribution for Loss Functions in Image Classification
TL;DR: In this article, a large margin Gaussian Mixture (L-GM) loss is proposed for deep neural networks in classification tasks, which is based on the assumption that the deep features of the training set follow a Gaussian mixture distribution.
Journal ArticleDOI
Maximally Compact and Separated Features with Regular Polytope Networks
TL;DR: In this article , the authors proposed to extract from CNNs features with the properties of maximum inter-class separability and maximum intra-class compactness by setting the parameters of the classifier transformation as not trainable.