Imperial College London

STEFANOS ZAFEIRIOU, PhD

Faculty of EngineeringDepartment of Computing

Reader in Machine Learning and Computer Vision
 
 
 
//

Contact

 

+44 (0)20 7594 8461s.zafeiriou Website CV

 
 
//

Location

 

375Huxley BuildingSouth Kensington Campus

//

Summary

 

Publications

Citation

BibTex format

@article{Wang:2018:10.1109/TPAMI.2017.2783940,
author = {Wang, M and Panagakis, Y and Snape, P and Zafeiriou, SP},
doi = {10.1109/TPAMI.2017.2783940},
journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
pages = {2682--2695},
title = {Disentangling the modes of variation in unlabelled data},
url = {http://dx.doi.org/10.1109/TPAMI.2017.2783940},
volume = {40},
year = {2018}
}

RIS format (EndNote, RefMan)

TY  - JOUR
AB - Statistical methods are of paramount importance in discovering the modes of variation in visual data. The Principal Component Analysis (PCA) is probably the most prominent method for extracting a single mode of variation in the data. However, in practice, several factors contribute to the appearance of visual objects including pose, illumination, and deformation, to mention a few. To extract these modes of variations from visual data, several supervised methods, such as the TensorFaces relying on multilinear (tensor) decomposition have been developed. The main drawbacks of such methods is that they require both labels regarding the modes of variations and the same number of samples under all modes of variations (e.g., the same face under different expressions, poses etc.). Therefore, their applicability is limited to well-organised data, usually captured in well-controlled conditions. In this paper, we propose a novel general multilinear matrix decomposition method that discovers the multilinear structure of possibly incomplete sets of visual data in unsupervised setting (i.e., without the presence of labels). We also propose extensions of the method with sparsity and low-rank constraints in order to handle noisy data, captured in unconstrained conditions. Besides that, a graph-regularised variant of the method is also developed in order to exploit available geometric or label information for some modes of variations. We demonstrate the applicability of the proposed method in several computer vision tasks, including Shape from Shading (SfS) (in the wild and with occlusion removal), expression transfer, and estimation of surface normals from images captured in the wild.
AU - Wang,M
AU - Panagakis,Y
AU - Snape,P
AU - Zafeiriou,SP
DO - 10.1109/TPAMI.2017.2783940
EP - 2695
PY - 2018///
SN - 0162-8828
SP - 2682
TI - Disentangling the modes of variation in unlabelled data
T2 - IEEE Transactions on Pattern Analysis and Machine Intelligence
UR - http://dx.doi.org/10.1109/TPAMI.2017.2783940
UR - https://www.ncbi.nlm.nih.gov/pubmed/29990016
UR - http://hdl.handle.net/10044/1/68681
VL - 40
ER -