Deeply learned face representations are sparse, selective, and robust

@article{Sun2015DeeplyLF,
  title={Deeply learned face representations are sparse, selective, and robust},
  author={Yi Sun and Xiaogang Wang and Xiaoou Tang},
  journal={2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2015},
  pages={2892-2900}
}
This paper designs a high-performance deep convolutional network (DeepID2+) for face recognition. [] Key Result (1) It is observed that neural activations are moderately sparse. Moderate sparsity maximizes the discriminative power of the deep net as well as the distance between images. It is surprising that DeepID2+ still can achieve high recognition accuracy even after the neural responses are binarized. (2) Its neurons in higher layers are highly selective to identities and identity-related attributes. We…
Sparsifying Neural Network Connections for Face Recognition
TLDR
The proposed sparse ConvNet model significantly improves the face recognition performance of the previous state-of-the-art DeepID2+ models given the same training data, while it keeps theperformance of the baseline model with only 12% of the original parameters.
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.
Face Attributes as Cues for Deep Face Recognition Understanding
  • M. A. Diniz, W. R. Schwartz
  • Computer Science
    2020 15th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2020)
  • 2020
TLDR
The experiments show that, inside DCNNs optimized for face identification, there exists latent neurons encoding face attributes almost as accurately as DCNN's optimized for these attributes.
A Light CNN for Deep Face Representation With Noisy Labels
TLDR
Experimental results show that the proposed framework can utilize large-scale noisy data to learn a Light model that is efficient in computational costs and storage spaces and achieves state-of-the-art results on various face benchmarks without fine-tuning.
Sparse Graph Based Deep Learning Networks for Face Recognition
TLDR
A sparse graph representation based on the face correlation in- formation that is embedded via the sparse reconstruction and deep learning within an irregular domain is proposed and is remarkably robust.
SeqFace: Make full use of sequence information for face recognition
TLDR
The designed SeqFace can train CNNs by using an additional dataset which includes a large number of face sequences collected from videos, and the label smoothing regularization and a new proposed discriminative sequence agent (DSA) loss are employed to enhance discrimination power of deep face features via making full use of the sequence data.
Compressed Deep Convolution Neural Network for Face Recognition
TLDR
This paper optimizes a lightened baseline CNN model by adopting an additional contrastive loss to learn more discriminative features and utilizes the pruning method to convert the dense model to a sparse layer to reduce the size of model storage.
DeepVisage: Making Face Recognition Simple Yet With Powerful Generalization Skills
TLDR
This work proposes an easily trainable and single CNN based FR method that exploits the residual learning framework and uses normalized features to compute the loss and obtains very competitive and state-of-the-art results on the LFW, IJB-A, YouTube faces and CACD datasets.
Deep learning and face recognition: the state of the art
TLDR
This talk and accompanying paper attempts to provide a review and summary of the deep learning techniques used in the state-of-the-art, and highlights the need for both larger and more challenging public datasets to benchmark these systems.
...
...

References

SHOWING 1-10 OF 51 REFERENCES
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.
Learning hierarchical representations for face verification with convolutional deep belief networks
TLDR
It is shown that a recognition system using only representations obtained from deep learning can achieve comparable accuracy with a system using a combination of hand-crafted image descriptors, and empirically show that learning weights not only is necessary for obtaining good multilayer representations, but also provides robustness to the choice of the network architecture parameters.
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.
Web-scale training for face identification
TLDR
A link between the representation norm and the ability to discriminate in a target domain is found, which sheds lights on how deep convolutional networks represent faces.
Hybrid Deep Learning for Face Verification
TLDR
This work proposes a hybrid convolutional network-Restricted Boltzmann Machine model for face verification in wild conditions to directly learn relational visual features, which indicate identity similarities, from raw pixels of face pairs with a hybrid deep network.
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.
Deep Attribute Networks
TLDR
The potential of deep learning for attribute-based classification is demonstrated by showing comparable results with existing state-of-the-art results and does away with calculating low-level features which are maybe unreliable and computationally expensive.
Deep Learning Identity-Preserving Face Space
TLDR
This paper proposes a new learning based face representation: the face identity-preserving (FIP) features, a deep network that combines the feature extraction layers and the reconstruction layer that significantly outperforms the state-of-the-art face recognition methods.
A Deep Sum-Product Architecture for Robust Facial Attributes Analysis
TLDR
This work has modeled region interdependencies with a discriminative decision tree, where each node consists of a detector and a classifier trained on a local region, which makes it more robust to occlusions and misdetection of face regions.
Robust Face Recognition via Sparse Representation
TLDR
This work considers the problem of automatically recognizing human faces from frontal views with varying expression and illumination, as well as occlusion and disguise, and proposes a general classification algorithm for (image-based) object recognition based on a sparse representation computed by C1-minimization.
...
...