• Corpus ID: 7588609

Recover Canonical-View Faces in the Wild with Deep Neural Networks

@article{Zhu2014RecoverCF,
  title={Recover Canonical-View Faces in the Wild with Deep Neural Networks},
  author={Zhenyao Zhu and Ping Luo and Xiaogang Wang and Xiaoou Tang},
  journal={ArXiv},
  year={2014},
  volume={abs/1404.3543}
}
Face images in the wild undergo large intra-personal variations, such as poses, illuminations, occlusions, and low resolutions, which cause great challenges to face-related applications. This paper addresses this challenge by proposing a new deep learning framework that can recover the canonical view of face images. It dramatically reduces the intra-person variances, while maintaining the inter-person discriminativeness. Unlike the existing face reconstruction methods that were either evaluated… 

Figures and Tables from this paper

Single Sample Face Recognition via Learning Deep Supervised Autoencoders

Results demonstrate that the stacked supervised autoencoders-based face representation significantly outperforms the commonly used image representations in single sample per person face recognition, and it achieves higher recognition accuracy compared with other deep learning models, including the deep Lambertian network.

Learning Pose-Aware Models for Pose-Invariant Face Recognition in the Wild

This paper presents an extensive analysis of the IARPA Janus Benchmark A, evaluating the effects that landmark detection accuracy, CNN layer selection, and pose model selection all have on the performance of the recognition pipeline.

Discriminant auto encoders for face recognition with expression and pose variations

This study clearly shows the value of using non-linear discriminant error criterion as a tractable objective to guide the learning of useful high level features in various face related problems.

Pose-Aware Face Recognition in the Wild

A method to push the frontiers of unconstrained face recognition in the wild by using multiple pose specific models and rendered face images called Pose-Aware Models (PAMs), which achieve remarkably better performance than commercial products and surprisingly also outperform methods that are specifically fine-tuned on the target dataset.

Using deep autoencoders to learn robust domain-invariant representations for still-to-video face recognition

An efficient Canonical Face Representation CNN (CFR-CNN) is proposed for accurate still-to-video FR from a single sample per person, where still and video ROIs are captured in different conditions, and experimental results indicate that the proposed CFR-CNN can achieve convincing level of accuracy.

Multi-View Face Recognition Via Well-Advised Pose Normalization Network

This work designs an end-to-end facial pose normalization network with adaptive weights on different objectives to exploit potentialities of various profile-front relationships and encourages intra-class compactness and inter-class separability between facial features by introducing quality-aware feature fusion.

Learning and Transferring Multi-task Deep Representation for Face Alignment

A novel tasks-constrained deep model is formulated, with task-wise early stopping to facilitate learning convergence and reduces model complexity drastically compared to the state-of-the-art method based on cascaded deep model.

Hierarchical-PEP model for real-world face recognition

  • Haoxiang LiG. Hua
  • Computer Science
    2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2015
The Hierarchical-PEP model exploits the fine-grained structures of the face parts at different levels of details to address the pose variations and is also guided by supervised information in constructing the face part/face representations.

Face verification based on deep reconstruction network

Experimental results on the CMP-PIE dataset demonstrate that the DRN has good capability to reconstruct the reference face, and the facial features extracted by DRN have good robustness to obtain high face verification accuracy.

High-fidelity Pose and Expression Normalization for face recognition in the wild

A High-fidelity Pose and Expression Normalization (HPEN) method with 3D Morphable Model (3DMM) which can automatically generate a natural face image in frontal pose and neutral expression and an inpainting method based on Possion Editing to fill the invisible region caused by self occlusion is proposed.
...

References

SHOWING 1-10 OF 44 REFERENCES

Learning Deep Face Representation

A very easy-to-implement deep learning framework for face representation based on a new structure of deep network (called Pyramid CNN), which adopts a greedy-filter-and-down-sample operation, which enables the training procedure to be very fast and computationefficient.

Tom-vs-Pete Classifiers and Identity-Preserving Alignment for Face Verification

A method of face verification that takes advantage of a reference set of faces, disjoint by identity from the test faces, labeled with identity and face part locations, to perform an “identity-preserving” alignment.

Surpassing Human-Level Face Verification Performance on LFW with GaussianFace

A principled multi-task learning approach based on Discriminative Gaussian Process Latent VariableModel (DGPLVM), named GaussianFace, for face verification, which achieved an impressive accuracy rate and introduced a more efficient equivalent form of Kernel Fisher Discriminant Analysis to DGPLVM.

Learning hierarchical representations for face verification with convolutional deep belief networks

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.

Hybrid Deep Learning for Face Verification

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.

Deep Learning Face Representation from Predicting 10,000 Classes

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.

Face recognition with learning-based descriptor

  • Zhimin CaoQi YinXiaoou TangJian Sun
  • Computer Science
    2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition
  • 2010
This work proposes a pose-adaptive matching method that uses pose-specific classifiers to deal with different pose combinations of the matching face pair, and finds that a simple normalization mechanism after PCA can further improve the discriminative ability of the descriptor.

An associate-predict model for face recognition

The proposed associate-predict model is built on an extra generic identity data set, in which each identity contains multiple images with large intra-personal variation, and can substantially improve the performance of most existing face recognition methods.

A Practical Transfer Learning Algorithm for Face Verification

This work proposes a principled transfer learning approach for merging plentiful source-domain data with limited samples from some target domain of interest to create a classifier that ideally performs nearly as well as if rich target- domain data were present.

Eigenfaces vs. Fisherfaces: Recognition Using Class Specific Linear Projection

A face recognition algorithm which is insensitive to large variation in lighting direction and facial expression is developed, based on Fisher's linear discriminant and produces well separated classes in a low-dimensional subspace, even under severe variations in lighting and facial expressions.