Deep Learning Identity-Preserving Face Space

By Zhenyao Zhu, Ping Luo, Xiaogang Wang, Xiaoou Tang. IEEE International Conference on Computer Vision, 2013

302 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Signal Processing

View Paper: https://www.semanticscholar.org/paper/53b919c994b3658cca8178e455681ca244a7afad

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

In Signal Processing

Citations in the corpus

Towards Large-Pose Face Frontalization in the Wild (2017, background): “Pose-invariant feature disentanglement [20] or identity preservation [45, 39] methods aim to factorize out the non-identity part with care-fully designed networks.”
FaceID-GAN: Learning a Symmetry Three-Player GAN for Identity-Preserving Face Synthesis (2018, background): “We would also like to acknowledge their contributions [12, 39, 40, 32].”
Face Model Compression by Distilling Knowledge from Neurons (2016, background): “As the emergence of big training data, Deep Neural Networks (DNNs) recently attained great breakthroughs in face recognition [23, 20, 21, 22, 19, 15, 29, 30, 28] and become applicable in many commercial platforms such as social networks, e-commerce, and search engines.”
Deeply Learning Deformable Facial Action Parts Model for Dynamic Expression Analysis (2014, methodology): “When obtain all the gradient, we can update the parameters using the stochastic gradient descent as in [15].”
Learning Deep Representation with Large-Scale Attributes (2015, background): “Deep learning is effective for many vision tasks [17, 34, 43, 14, 19, 11, 26, 28, 23, 25, 44, 47, 21, 49, 5].”
Factors in Finetuning Deep Model for Object Detection with Long-Tail Distribution (2016, background): “Deep learning is found to be effective in many vision tasks [38, 4, 40, 39, 21, 24, 23, 49, 19, 34, 33, 7, 48, 31].”
Auto-encoder based dimensionality reduction (2016, background): “[28] extracted face identity-preserving features from an image under any pose and illumination which could be used to reconstruct the face image in canonical view by designing a deep network.”
DeepReID: Deep Filter Pairing Neural Network for Person Re-identification (2014, background): “Deep learning has achieved great success in solving many computer vision problems, including hand-written digit recognition [22], object recognition [17, 36], object detection [38, 31, 46, 28], image classification [23, 21], scene understanding [8], and face recognition [5, 39, 52, 40].”
Multi-View Perceptron: a Deep Model for Learning Face Identity and View Representations (2014, methodology): “FIP and RL utilized least-square loss to recover the frontal view image.”
A Light CNN for Deep Face Representation With Noisy Labels (2015, unknown): “ght CNN-29 98.55% Human, Average 85.70% Human, Voting 94.20% Table 10. Comparison of Rank-1 accuracy (%) with other state-ofthe-art methods on the Multi-PIE dataset. Method 15 30 45 60 Zhu et al. [63] 90.7 80.7 64.1 45.9 Zhu et al. [64] 92.8 83.7 72.9 60.1 Kan et al. [18] 100 100 90.6 85.9 Yin et al”
Learning Social Relation Traits from Face Images (2015, background): “Deep learning has achieved remarkable success in many tasks of face analysis, e.g . face parsing [25], face landmark detection [42], face attribute prediction [24, 26], and face recognition [33, 43].”
Pedestrian Parsing via Deep Decompositional Network (2013, background): “At the bottom of DDN, the input x is down-sampled to xd. x is also mapped to a binary occlusion mask xo ∈ [0, 1]n through two weight matrices W o1 , W o2 , and biases bo1 , bo2 .”
Person Recognition in Personal Photo Collections (2015, background): “Face normalization (“frontalisation”) [44, 37, 12] improves robustness to pose, view-point and illumination.”
Learning Deep Representation for Face Alignment with Auxiliary Attributes (2014, background): “Facial landmark detection is a fundamental component in many face analysis tasks, such as facial attribute inference [20], face verification [18,30,31,44], and face recognition [42,43].”
High-fidelity Pose and Expression Normalization for face recognition in the wild (2015, methodology): “In Setting-1, we demonstrate the robustness of our method to pose variations.”
Person Recognition in Personal Photo Collections (2017, background): “Face recognition performance have improved significantly in recent years with better architectures and larger open source datasets [3], [4], [5], [7], [8], [9], [10], [54], [55].”
Multi-Directional Multi-Level Dual-Cross Patterns for Robust Face Recognition (2014, background): “n and face veriﬁcation tasks are evaluated. 9 0.9~ É tU 0:: 0.8 5 ~ 0.7 u:= c ~ 0.6~ æ 0.5~ tU E æ 0.4' 2 É O. 1 02r F "0 TVfð q g RU B e-8 , VÛ]Ý / Ng / ktfz / Ç // U r dut |+ DCP,Radii=[23]| -DCP, Radii = [2 4] I ø DCP, Radii = [2 5] I -e-LBP,Radius =2 3 4 5 6 7 N 8 9 10 11 12 Fig. 9. Th”
Deeply learned face representations are sparse, selective, and robust (2014, background): “Face recognition achieved great progress thanks to extensive research effort devoted to this area [31, 33, 6, 24, 37, 27, 25, 23, 38].”
Rotating your face using multi-task deep neural network (2015, methodology): “The DNN have been used to find pose-robust features without hand-crafted features [26, 7, 27].”
Eye In-painting with Exemplar Generative Adversarial Networks (2017, unknown): “An identity-preserving loss is proposed in [17], which uses a perceptual distance of two faces on the manifold of the DNN outlined in [43] as an objective to be minimized.”