This month of its monthly seminar SagivTech hosted Elad Hoffer from the Technion.

Elad holds a BSc and MSc both from the Electrical Engineering department at the Technion. Elad is a PhD candidate at the Technion under the supervision of Prof. Nir Ailon. His research is focused on Deep Learning of representations, and related topics of machine learning and computer vision.

Elad gave a talk on his work on Deep metric learning using Triplet networks, Deep unsupervised learning through spatial contrasting and Semi-supervised deep learning by metric embedding.

Triplet networks let us learn a distance metric between images, and have been shown to give better results than other methods like Siamese networks. This kind of metric learning has been since used in many applications like face recognition and image search.
When adding spatial contrasting, it is possible to train deep networks for metric learning on unlabelled data or partially labelled data and obtain representations useful for other tasks, giving state of the art results.

Legal Disclaimer:

You understand that when using the Site you may be exposed to content from a variety of sources, and that SagivTech is not responsible for the accuracy, usefulness, safety or intellectual property rights of, or relating to, such content and that such content does not express SagivTech’s opinion or endorsement of any subject matter and should not be relied upon as such. SagivTech and its affiliates accept no responsibility for any consequences whatsoever arising from use of such content. You acknowledge that any use of the content is at your own risk.