Opendata, web and dolomites


Understanding Deep Face Recognition

Total Cost €


EC-Contrib. €






Project "DeepFace" data sheet

The following table provides information about the project.


Organization address
address: RAMAT AVIV
city: TEL AVIV
postcode: 69978

contact info
title: n.a.
name: n.a.
surname: n.a.
function: n.a.
email: n.a.
telephone: n.a.
fax: n.a.

 Coordinator Country Israel [IL]
 Total cost 1˙696˙888 €
 EC max contribution 1˙696˙888 € (100%)
 Programme 1. H2020-EU.1.1. (EXCELLENT SCIENCE - European Research Council (ERC))
 Code Call ERC-2016-COG
 Funding Scheme ERC-COG
 Starting year 2017
 Duration (year-month-day) from 2017-05-01   to  2022-04-30


Take a look of project's partnership.

# participants  country  role  EC contrib. [€] 
1    TEL AVIV UNIVERSITY IL (TEL AVIV) coordinator 1˙696˙888.00


 Project objective

Face recognition is a fascinating domain: no other domain seems to present as much value when analysing casual photos; it is one of the few domains in machine learning in which millions of classes are routinely learned; and the trade-off between subtle inter-identity variations and pronounced intra-identity variations forms a unique challenge.

The advent of deep learning has brought machines to what is considered a human level of performance. However, there are many research questions that are left open. At the top most level, we ask two questions: what is unique about faces in comparison to other recognition tasks that also employ deep networks and how can we make the next leap in performance of automatic face recognition?

We consider three domains of research. The first is the study of methods that promote effective transfer learning. This is crucial since all state of the art face recognition methods rely on transfer learning. The second domain is the study of the tradeoffs that govern the optimal utilization of the training data and how the properties of the training data affect the optimal network design. The third domain is the post transfer utilization of the learned deep networks, where given the representations of a pair of face images, we seek to compare them in the most accurate way.

Throughout this proposal, we put an emphasis on theoretical reasoning. I aim to support the developed methods by a theoretical framework that would both justify their usage as well as provide concrete guidelines for using them. My goal of achieving a leap forward in performance through a level of theoretical analysis that is unparalleled in object recognition, makes our research agenda truly high-risk/ high-gains. I have been in the forefront of face recognition for the last 8 years and my lab's recent achievements in deep learning suggest that we will be able to carry out this research. To further support its feasibility, we present very promising initial results.


year authors and title journal last update
List of publications.
2019 Benjamin Klein Lior Wolf
End-to-End Supervised Product Quantization for Image Search and Retrieval
published pages: , ISSN: , DOI:
2020 W-J. Nam, Shir Gur, J. Choi, Lior Wolf, S-W. Lee.
Relative Attributing Propagation: Interpreting the Comparative Contributions of Individual Units in Deep Neural Networks
published pages: , ISSN: , DOI:
AAAI 2019-12-16
2017 Benaim, Sagie; Wolf, Lior
One-Sided Unsupervised Domain Mapping
published pages: , ISSN: , DOI:
NIPS 2019-12-16
2019 Gur, Shir; Wolf, Lior; Golgher, Lior; Blinder, Pablo
Unsupervised Microvascular Image Segmentation Using an Active Contours Mimicking Neural Network
published pages: , ISSN: , DOI:
ICCV 2019-12-16
2019 Shir Gur Lior Wolf
Single Image Depth Estimation Trained via Depth from Defocus Cues
published pages: , ISSN: , DOI:
2018 Galanti, Tomer; Benaim, Sagie; Wolf, Lior
Generalization Bounds for Unsupervised Cross-Domain Mapping with WGANs
published pages: , ISSN: , DOI:
arXiv preprint 1 2019-12-16
2019 Tomer Cohen Lior Wolf
Bidirectional One-Shot Unsupervised Domain Mapping
published pages: , ISSN: , DOI:
ICCV 2019-12-16
2020 Eyal Shulman Lior Wolf
Meta Decision Trees for Explainable Recommendation Systems
published pages: , ISSN: , DOI:
Artificial Intelligence, Ethics, and Society (AIES) 2019-12-16
2019 Littwin, Gidi; Wolf, Lior
Deep Meta Functionals for Shape Representation
published pages: , ISSN: , DOI:
ICCV 2019-12-16
2019 Sagie Benaim Michael Khaitov Tomer Galanti Lior Wolf
Domain Intersection and Domain Difference.
published pages: , ISSN: , DOI:
2019 Oron Ashual Lior Wolf
Specifying Object Attributes and Relations in Interactive Scene Generation.
published pages: , ISSN: , DOI:
ICCV 2019-12-16
2019 Etai Littwin, Lior Wolf
On the Convex Behavior of Deep Neural Networks in Relation to the Layers\' Width
published pages: , ISSN: , DOI:
ICML 2019 Workshop Deep Phenomena homepage 2019-12-16
2017 Klein, Benjamin; Wolf, Lior
In Defense of Product Quantization
published pages: , ISSN: , DOI:
arXiv preprint 2 2019-05-23
2018 Benaim, Sagie; Wolf, Lior
One-Shot Unsupervised Cross Domain Translation
published pages: , ISSN: , DOI:
NIPS 1 2019-05-23
2019 L. Wolf, S. Benaim, T. Galanti.
Unsupervised Learning of the Set of Local Maxima. International Conference on Learning Representations (ICLR), 2019.
published pages: , ISSN: , DOI:
ICLR 2019-02-26
2018 Tomer Galanti, Lior Wolf
Generalization Bounds for Unsupervised Cross-Domain Mapping with WGANs.
published pages: , ISSN: , DOI:
Integration of Deep Learning Theories NIPS workshop 2019-02-26
2018 Lior Wolf; Etai Littwin
Regularizing by the Variance of the Activations\' Sample-Variances
published pages: , ISSN: , DOI:
NIPS 2019-02-26
2018 Doron Sobol, Lior Wolf, Yaniv Taigman
Visual analogies between Atari games for studying transfer learning
published pages: , ISSN: , DOI:
arXiv preprint 2019-02-26
2018 Galanti, Tomer; Wolf, Lior; Benaim, Sagie
The Role of Minimal Complexity Functions in Unsupervised Learning of Semantic Mappings
published pages: , ISSN: , DOI:
ICLR 2 2019-02-26
2019 L. Wolf, T. Galanti, T. Hazan
A Formal Approach to Explainability.
published pages: , ISSN: , DOI:
Artificial Intelligence, Ethics, and Society (AIES) 2019-02-26
2019 O. Press, T. Galanti, S. Benaim, L. Wolf
Emerging Disentanglement in Auto-Encoder Based Unsupervised Image Content Transfer.
published pages: , ISSN: , DOI:
ICLR 2019-02-26

Are you the coordinator (or a participant) of this project? Plaese send me more information about the "DEEPFACE" project.

For instance: the website url (it has not provided by EU-opendata yet), the logo, a more detailed description of the project (in plain text as a rtf file or a word file), some pictures (as picture files, not embedded into any word file), twitter account, linkedin page, etc.

Send me an  email ( and I put them in your project's page as son as possible.

Thanks. And then put a link of this page into your project's website.

The information about "DEEPFACE" are provided by the European Opendata Portal: CORDIS opendata.

More projects from the same programme (H2020-EU.1.1.)

VictPart (2019)

Righting Victim Participation in Transitional Justice

Read More  


The Enemy of the Good: Towards a Theory of Moral Progress

Read More  

Photopharm (2020)

Photopharmacology: From Academia toward the Clinic.

Read More