Unsupervised Disentangling of Viewpoint and Residues Variations by Substituting Representations for Robust Face Recognition

Cited 1 time in webofscience Cited 0 time in scopus
  • Hit : 259
  • Download : 0
It is well-known that identity-unrelated variations (e.g., viewpoint or illumination) degrade the performances of face recognition methods. In order to handle this challenge, a robust method for disentangling the identity and view representations has drawn an attention in the machine learning area. However, existing methods learn discriminative features which require a manual supervision of such factors of variations. In this paper, we propose a novel disentangling framework through modeling three representations of identity, viewpoint, and residues (i.e., identity and pose unrelated) which do not require supervision of the variations. By jointly modeling the three representations, we enhance the disentanglement of each representation and achieve robust face recognition performance. Further, the learned viewpoint representation can be utilized for pose estimation or editing of a posed facial image. Extensive quantitative and qualitative evaluations verify the effectiveness of our proposed method which disentangles identity, viewpoint, and residues of facial images.
Publisher
International Association of Pattern Recognition
Issue Date
2021-01-10
Language
English
Citation

25th International Conference on Pattern Recognition (ICPR) , pp.8952 - 8959

ISSN
1051-4651
DOI
10.1109/ICPR48806.2021.9413039
URI
http://hdl.handle.net/10203/280796
Appears in Collection
EE-Conference Papers(학술회의논문)
Files in This Item
There are no files associated with this item.
This item is cited by other documents in WoS
⊙ Detail Information in WoSⓡ Click to see webofscience_button
⊙ Cited 1 items in WoS Click to see citing articles in records_button

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0