PyData Yerevan 2023 Meetup

About the Event:

We are happy to announce the last #PyDataYVN meetup of 2023!

Vahan Huroyan, a machine learning researcher at the YerevaNN research lab, will feature a talk on “Recent Developments in Self-Supervised Learning for Computer Vision.”

Huroyan will provide an overview of the latest developments in Self-Supervised Learning (SSL) for computer vision, delve into its challenges, and discuss future directions in this field.

SSL is a powerful tool for training computer vision models without the need for extensive labeled data. SSL methods are designed around pretext tasks that force models to learn valuable representations from the training data. These learned representations can then be transferred to downstream tasks, such as:

• Image classification
• Object detection
• Segmentation with minimal fine-tuning

The two main approaches of SSL include contrastive learning and masked image modeling:

• Contrastive learning is a general SSL framework that trains models to distinguish between positive and negative pairs of images.
• Masked image modeling is a specific type of SSL that involves masking random patches of an image and training the model to predict the masked pixels.

Register now and save the date to join us on December 14 at 7:00pm in 314w, PAB, to discover more: https://forms.gle/9y2Latee1zmTtGaAA

About the Speaker:

Vahan Huroyan earned his bachelor’s in mathematics from Yerevan State University in 2012. Subsequently, from 2012 to 2018, he completed his Ph.D. in mathematics at the University of Minnesota. His doctoral thesis, titled “Mathematical Formulations, Algorithms, and Theory for Big Data Problems,” focused on the foundational aspects of data science and machine learning. From 2018 to 2022, Vahan worked as a postdoctoral researcher at the University of Arizona. Currently, he is a machine learning researcher at the YerevaNN research lab, where he focuses on computer vision-related problems.

Language: English