top of page


Share on:
Asset 14icon.png
Asset 39icon.png
Asset 12icon.png

Shira is an experienced Algorithm Developer in the fields of Computer Vision and Deep Learning, co-founder of Women in Computer Vision Israel, co-organizer and community leader at Women in Data Science Israel, and a career mentor at Baot.

With a Chemistry B.Sc. from BGU, Shira applies her theoretical knowledge and practical experience in Computer Vision and Deep Learning in various domains.
Shira has a great passion for her profession, enjoying the end-to-end ride from concept to production, and passing it forward with her various initiatives.
Shira is also a Snowboarding Instructor and has a daughter named Aria (not stark).

Shira Navot

Computer Vision & Deep Learning Algorithm Developer
Asset 12icon.png
Asset 1TWITTER.png
Asset 39icon.png
Asset 17icon.png
English, Hebrew
Asset 7TWITTER.png
Herzliya, Israel
Asset 7TWITTER.png
Can also give an online talk/webinar
Paid only. Contact speaker for pricing!


Stop Labelling Everything! How Self-Supervision Can Reduce Labelling Costs

Data / AI / ML

Asset 12SLIDES.png
Asset 21talk.png
Asset 11SLIDES.png

Imagine you have a dataset that contains 1M images, and a deep learning supervised task that requires a great amount of data to be annotated in order to train it.
The big question then becomes, do you send all 1M images for labelling? This would be time-consuming and not to mention very costly. What if your budget can cover only 10% of the data? How do you choose which items to send for annotating?

In this talk, I will describe my practical solution to this problem, as an Algorithm Developer at Dataloop, where I was handling dozens of datasets in various domains. Starting by using unsupervised methods in order to find “what matters” in a dataset, I will cover the differences between self-supervision and unsupervised learning, and demonstrate how the former succeeded where the latter failed. I will also show why you shouldn't be afraid of high-dimensional data and how you could train a neural network without a specific task.

Asset 1icon.png

Stop Labelling Everything! How Self-Supervision Can Reduce Labelling Costs







Go to lecture page

bottom of page