PyData Yerevan 2022

Erik Harutyunyan

Erik Harutyunyan is a Machine Learning Engineer, mostly specialized and interested in the Computer Vision domain. He is currently working at SuperAnnotate AI as a Machine Learning Researcher and concurrently pursuing a Master's degree in Mathematics in Data Science at the Technical University of Munich.

The speaker's profile picture


Active Learning for 3D mesh semantic segmentation
Erik Harutyunyan

The talk is about applications of active learning methods, mainly Monte-Carlo Dropout on 3D mesh/pointcloud semantic segmentation task. The topic is particularly interesting for practical applications of Deep Learning models on this type of data, as it gives a working approach for reducing the amount of data needed for training.

114W PAB