Skip to content

Prof. Lior Wolf

Prof. Lior Wolf

Research Scientist, Facebook AI Research (FAIR)
Full professor, School of Computer Science at Tel-Aviv University


Prof. Wolf is a research scientist in Facebook AI Research (FAIR) and a full professor at the School of Computer Science at Tel-Aviv University. Prof. Wolf’s work has received several awards including the best paper awards at ICANN'16 and at the CVPR'13 workshop on action recognition.

Prof. Wolf has extensive experience in forming, advising and heading R&D at multiple computer vision startups and his research focuses on computer vision and deep learning and includes topics such as face identification, document analysis, natural language processing, digital paleography, and video action recognition.


The Ongoing Revolution of Unsupervised Learning


The recent success in mapping between two domains in an unsupervised way and without any existing knowledge, other than network hyperparameters, is nothing less than extraordinary and has far-reaching consequences. As far as we know, nothing in the existing machine learning or cognitive science literature suggests that this would be possible.

We conjecture that functions of minimal complexity play a pivotal role in this success. If our hypothesis is correct, simply by training networks that are not too complex, the "correct" target mapping stands out from all other alternative mappings. Our analysis leads directly to a new unsupervised cross-domain mapping algorithm that is able to avoid the ambiguity of such mapping, yet enjoy the expressiveness of deep neural networks.

Taking this approach a step further, we define a general Occam’s razor property and employ it in order to obtain generalization bounds for unsupervised learning. The bounds hold both in expectation, with application to hyperparameter selection, and per sample, thus supporting dynamic confidence-based runtime behavior. The latter is crucial for real-world computer vision systems and was never shown for functions learned in an unsupervised way.

I will also present new results on the AI task of Identifying analogies across domains without supervision. Recent advances in cross domain image mapping have concentrated on translating images across domains. Although the progress made is impressive, the visual fidelity many times does not suffice for identifying the matching sample from the other domain. Our work tackles this very task of finding exact analogies between datasets e.g. for every image from domain A find an analogous image in domain B.