# An Adversarial Neuro-Tensorial Approach For Learning Disentangled Representations

arXiv: https://arxiv.org/abs/1711.10402 · HTML: https://mlsanity.com/paper/1711.10402/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Nov 2017.

## Built on by (most cited first, 8 of 8)

- [Tensor Methods in Computer Vision and Deep Learning](https://mlsanity.com/paper/2107.03436/) (2021)
- [Unsupervised Human Pose Estimation through Transforming Shape Templates](https://mlsanity.com/paper/2105.04154/) (2021)
- [Tensor Component Analysis for Interpreting the Latent Space of GANs](https://mlsanity.com/paper/2111.11736/) (2021)
- [AR-NeRF: Unsupervised Learning of Depth and Defocus Effects from Natural Images with Aperture Rendering Neural Radiance Fields](https://mlsanity.com/paper/2206.06100/) (2022)
- [Structural Causal 3D Reconstruction](https://mlsanity.com/paper/2207.10156/) (2022)
- [PoseFace: Pose-Invariant Features and Pose-Adaptive Loss for Face Recognition](https://mlsanity.com/paper/2107.11721/) (2021)
- [Unsupervised Learning of Depth and Depth-of-Field Effect from Natural Images with Aperture Rendering Generative Adversarial Networks](https://mlsanity.com/paper/2106.13041/) (2021)
- [MI-NeRF: Learning a Single Face NeRF from Multiple Identities](https://mlsanity.com/paper/2403.19920/) (2024)

## Abstract (arXiv)

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.