Multi-View Perceptron: a Deep Model for Learning Face Identity and View Representations

By Zhenyao Zhu, Ping Luo, Xiaogang Wang, Xiaoou Tang. 2014

261 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Representation & Self-Supervised Learning

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 Representation & Self-Supervised Learning

Citations in the corpus

InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets (2016, background): “One class of such methods trains a subset of the representation to match the supplied label using supervised learning: bilinear models [18] separate style and content; multi-view perceptron [19] separate face identity and view point; and Yang et al.”
A Sober Look at the Unsupervised Learning of Disentangled Representations and their Evaluation (2020, background): “Given that unsupervised algorithms did not initially perform well on realistic settings most of the other works have considered some more or less explicit form of supervision (Reed et al., 2014; Zhu et al., 2014; Yang et al., 2015; Kulkarni et al., 2015; Cheung et al., 2014; Mathieu et al., 2016; Na”
Learning to generate chairs with convolutional neural networks (2014, background): “[35] approached this task with a neural network: their network takes a face image as input and generates a random view of this face together with the corresponding viewpoint.”
Deep Learning Face Attributes in the Wild (2014, background): “Deep learning [18, 34, 23, 7, 19, 32, 31, 13, 33, 22, 3, 28] recently achieved great success in attribute prediction, due to their ability to learn compact and discriminative features.”
Interpretable Machine Learning: Fundamental Principles and 10 Grand Challenges (2021, background): “Earlier work in this domain disentangles the latent space for specific applications, such as face recognition, where we might aim to separate identity and pose (Zhu et al., 2014).”
Theory and Evaluation Metrics for Learning Disentangled Representations (2019, methodology): “Supervised methods [22, 43] assume access to the ground truth factors.”
Towards a Definition of Disentangled Representations (2018, background): “However, many other approaches [50, 23, 66, 63, 80, 78, 36, 17, 77, 46] and a recent disentanglement metric by [65] consider it perfectly ﬁne for each data generative factor to be encoded by multiple latent dimensions.”
Understanding disentangling in β-VAE (2018, background): “Most initial attempts to learn disentangled representations required supervised knowledge of the data generative factors [18, 35, 32, 44, 43, 12, 24, 7, 42, 20].”
Weakly-supervised Disentangling with Recurrent Transformations for 3D View Synthesis (2015, background): “The multi-view perceptron [30] employs a stochastic feedforward network to disentangle the identity and pose factors of face images in order to achieve view-invariant recognition.”
Multi-view 3D Models from Single Images with a Convolutional Network (2015, background): “The multi-view perceptron [7] is a network that takes a face image and a random vector as input and generates a random view of this face together with the corresponding viewpoint.”
A Survey of Inductive Biases for Factorial Representation-Learning (2016, background): “In [64], a representation of faces is learned that separates view from identity, and is trained to transform images in a similar way, using direct constraints on pose and equality constraints on identity.”
Beyond Face Rotation: Global and Local Perception GAN for Photorealistic and Identity Preserving Frontal View Synthesis (2017, methodology): “[45, 46] develop novel architectures and learning objectives to disentangle the identity and pose representation while estimating the frontal view.”
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.”
Learning Factorized Multimodal Representations (2018, background): “…particular variations of data and performing supervised training (Cheung et al., 2014; Karaletsos et al., 2015; Yang et al., 2015; Reed et al., 2014; Zhu et al., 2014), assuming an isotropic Gaussian prior over latent variables to learn disentangled generative representations (Kingma & Welling,…”
Generative Adversarial Networks for Face Generation: A Survey (2022, methodology): “Disentanglement representation learning (DRL) was previously applied in multi-task CNNs [148, 157, 169] using joint models to learn feature transformations in the target subdomains.”
Pixels, Voxels, and Views: A Study of Shape Representations for Single View 3D Object Shape Prediction (2018, background): “Our work is related to recent studies [18, 9, 23, 24, 22, 14, 10] that generate multiview projections of 3D objects.”