Back to Search
Start Over
An Adversarial Neuro-Tensorial Approach For Learning Disentangled Representations
- Publication Year :
- 2017
- Publisher :
- arXiv, 2017.
-
Abstract
- Several factors contribute to the appearance of an object in a visual scene, including pose, illumination, and deformation, among others. Each factor accounts for a source of variability in the data, while the multiplicative interactions of these factors emulate the entangled variability, giving rise to the rich structure of visual object appearance. Disentangling such unobserved factors from visual data is a challenging task, especially when the data have been captured in uncontrolled recording conditions (also referred to as "in-the-wild") and label information is not available. In this paper, we propose the first unsupervised deep learning method (with pseudo-supervision) for disentangling multiple latent factors of variation in face images captured in-the-wild. To this end, we propose a deep latent variable model, where the multiplicative interactions of multiple latent factors of variation are explicitly modelled by means of multilinear (tensor) structure. We demonstrate that the proposed approach indeed learns disentangled representations of facial expressions and pose, which can be used in various applications, including face editing, as well as 3D face reconstruction and classification of facial expression, identity and pose.
- Subjects :
- FOS: Computer and information sciences
Technology
Multilinear map
DATABASE
Computer science
Computer Vision and Pattern Recognition (cs.CV)
Computer Science - Computer Vision and Pattern Recognition
02 engineering and technology
Computer Science, Artificial Intelligence
Adversarial autoencoder
Artificial Intelligence
Tensor (intrinsic definition)
0801 Artificial Intelligence and Image Processing
0202 electrical engineering, electronic engineering, information engineering
Artificial Intelligence & Image Processing
Latent variable model
Disentangled representation
Facial expression
Science & Technology
business.industry
Deep learning
Pattern recognition
Object (computer science)
Tensor decomposition
Face (geometry)
Computer Science
Pattern recognition (psychology)
020201 artificial intelligence & image processing
Computer Vision and Pattern Recognition
Artificial intelligence
business
Software
Subjects
Details
- Database :
- OpenAIRE
- Accession number :
- edsair.doi.dedup.....02d69668f0cfba2b96df51c790864434
- Full Text :
- https://doi.org/10.48550/arxiv.1711.10402