I am Ksenia, a Ph.D. student in the CVLab at EPFL. In my research I apply methods from machine learning (and in particular active learning) to challenging problems in computer vision.

In my free time I enjoy the pleasures of Switzerland: beautiful sceneries for photography, high mountains for snowboarding and hiking, and picturesque lakes for sailing.

Biography

I joined CVlab in 2014 and since then I have been working with Prof. Pascal Fua and Prof. Raphael Sznitman. In automne 2017 during my internship at Google Research in Zurich I had a chance to work with Vittorio Ferrari and Jasper Uijlings. I am planning to graduate at the end of 2018!

I obtained my M.Sc. degree in Algorithms and Machine Learning from University of Helsinki. During that time, I also worked as a research assistant in the CoSCo group at HIIT. Before, I studied in Russia at the Higher School of Economics in the faculty of Business Informatics and Applied Mathematics.

Current research

Currently I am working on active learning for different classification tasks. Given a pool of unlabelled data, the goal of AL is to select which data should be annotated in order to learn the model as quickly as possible. In practice, this means that instead of asking experts to annotate everything, we decide iteratively and adaptively which datapoints should be labelled in priority.

Over the years, many AL strategies have been developed for various classification tasks, without any one of them clearly outperforming others in all cases. Thus, we work on data-driven approach to active learning: Learning Active Learning.

News

June, 2018: My work was featured in the CVPR Daily in the Computer Vision News magazine. There I talk about our paper on Intelligent Annotation Dialogs. Check it out on page 8!

June, 2018: Our article "Learning Intelligent Dialogs for Bounding Box Annotation" written during my internship at Google was at CVPR18! The poster and code are available.

March, 2018: My interview for TWiML&AI podcast is released. There I talk about active learning and other techniques for reducing annotation load. Check it out!

December, 2017: Our article "Learning Active Learning" was accepted to NIPS! The poster and code are available.

Ksenia Konyushkova