SphereFace: Deep Hypersphere Embedding for Face Recognition

@article{Liu2017SphereFaceDH,
  title={SphereFace: Deep Hypersphere Embedding for Face Recognition},
  author={Weiyang Liu and Yandong Wen and Zhiding Yu and Ming Li and Bhiksha Raj and Le Song},
  journal={2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2017},
  pages={6738-6746}
}
  • Weiyang Liu, Yandong Wen, Le Song
  • Published 26 April 2017
  • Computer Science
  • 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
This paper addresses deep face recognition (FR) problem under open-set protocol, where ideal face features are expected to have smaller maximal intra-class distance than minimal inter-class distance under a suitably chosen metric space. [] Key Method Geometrically, A-Softmax loss can be viewed as imposing discriminative constraints on a hypersphere manifold, which intrinsically matches the prior that faces also lie on a manifold.

Figures and Tables from this paper

ArcFace: Additive Angular Margin Loss for Deep Face Recognition
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.
UniformFace: Learning Deep Equidistributed Representation for Face Recognition
TLDR
A new supervision objective named uniform loss to learn deep equidistributed representations for face recognition is proposed, considering the class centers as like charges on the surface of hypersphere with inter-class repulsion, and minimize the total electric potential energy as the uniform loss.
Angular Discriminative Deep Feature Learning for Face Verification
  • Bowen Wu, Huaming Wu
  • Computer Science
    ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
  • 2020
TLDR
The intra-class constraint is extended to force the intra- class cosine similarity larger than the mean of nearest neighboring inter-class ones with a margin in the normalized exponential feature projection space to enhance the discriminative power of the deeply learned features.
Scalable Angular Discriminative Deep Metric Learning for Face Recognition
TLDR
Extensive experiments on Labeled Face in the Wild, Youtube Faces and IARPA Janus Benchmark A datasets demonstrate that the proposed methods outperform the mainstream DML methods and approach the state-of-the-art performance.
TypicFace: Dynamic Margin Cosine Loss for Deep Face Recognition
TLDR
This paper presents a novel loss function, namely TypicFace, which separates the face features of an individual into two portions: the typical feature and the atypical feature, which consistently performs better than the current state-of-the-art methods using the same network architecture and training dataset.
Gaussian Soft Margin Angular Loss for Face Recognition
TLDR
This work proposes a loss function that while maximizing the inter-class distance and intra-class compactness, allows for the samples which naturally reside further from class center to have a smaller margin.
CosFace: Large Margin Cosine Loss for Deep Face Recognition
TLDR
This paper reformulates the softmax loss as a cosine loss by L2 normalizing both features and weight vectors to remove radial variations, based on which acosine margin term is introduced to further maximize the decision margin in the angular space, and achieves minimum intra-class variance and maximum inter- class variance by virtue of normalization and cosine decision margin maximization.
Scalable Similarity-Consistent Deep Metric Learning for Face Recognition
TLDR
This work imposes the intra-class cosine similarity between the features and weight vectors in softmax loss larger than a margin in the training step and extends it from four aspects to alleviate the human labor of adjusting the margin hyper-parameter.
ElasticFace: Elastic Margin Loss for Deep Face Recognition
TLDR
This paper relaxes the fixed margin constrain by proposing elastic margin loss (ElasticFace) that allows flexibility in the push for class separability, and demonstrates the superiority of the elasticmargin loss over ArcFace and CosFace losses, using the same geometric transformation, on a large set of mainstream benchmarks.
Sphere Margins Softmax for Face Recognition
TLDR
The softmax loss with sphere margins is reformulated by normalizing both weights and extracted features of the last fully connected layer and have quantitatively adjustable angular margin by hyperparameter m1 and m2 and gives better results than the present state-of-the-art methods while adopting the same experimental configuration.
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 43 REFERENCES
FaceNet: A unified embedding for face recognition and clustering
TLDR
A system that directly learns a mapping from face images to a compact Euclidean space where distances directly correspond to a measure offace similarity, and achieves state-of-the-art face recognition performance using only 128-bytes perface.
A Discriminative Feature Learning Approach for Deep Face Recognition
TLDR
This paper proposes a new supervision signal, called center loss, for face recognition task, which simultaneously learns a center for deep features of each class and penalizes the distances between the deep features and their corresponding class centers.
Latent Factor Guided Convolutional Neural Networks for Age-Invariant Face Recognition
TLDR
This work proposes a novel deep face recognition framework to learn the ageinvariant deep face features through a carefully designed CNN model, and is the first attempt to show the effectiveness of deep CNNs in advancing the state-of-the-art of AIFR.
Targeting Ultimate Accuracy: Face Recognition via Deep Embedding
TLDR
A two-stage approach that combines a multi-patch deep CNN and deep metric learning, which extracts low dimensional but very discriminative features for face verification and recognition is proposed, showing a clear path to practical high-performance face recognition systems in real world.
DeepFace: Closing the Gap to Human-Level Performance in Face Verification
TLDR
This work revisits both the alignment step and the representation step by employing explicit 3D face modeling in order to apply a piecewise affine transformation, and derive a face representation from a nine-layer deep neural network.
Robust Face Recognition via Multimodal Deep Face Representation
TLDR
A comprehensive deep learning framework to jointly learn face representation using multimodal information is proposed and a small ensemble system achieves higher than 99.0% recognition rate on LFW using publicly available training set.
Deep Learning Face Representation by Joint Identification-Verification
TLDR
This paper shows that the face identification-verification task can be well solved with deep learning and using both face identification and verification signals as supervision, and the error rate has been significantly reduced.
Learning Face Representation from Scratch
TLDR
A semi-automatical way to collect face images from Internet is proposed and a large scale dataset containing about 10,000 subjects and 500,000 images, called CASIAWebFace is built, based on which a 11-layer CNN is used to learn discriminative representation and obtain state-of-theart accuracy on LFW and YTF.
Deeply learned face representations are sparse, selective, and robust
TLDR
This paper designs a high-performance deep convolutional network (DeepID2+) for face recognition that is learned with the identification-verification supervisory signal, and finds it is much more robust to occlusions, although occlusion patterns are not included in the training set.
Deep Learning Face Representation from Predicting 10,000 Classes
TLDR
It is argued that DeepID can be effectively learned through challenging multi-class face identification tasks, whilst they can be generalized to other tasks (such as verification) and new identities unseen in the training set.
...
1
2
3
4
5
...