S3 2023

Požega, July 23rd - August 2nd

Projects Workshops Lectures


Elephant on the road - how do deep models handle the unexpected?

Deep models are computing systems designed to imitate the function of a human brain. They are usually trained on large amounts of data to perform different types of statistical analysis. They have shown tremendous potential for application in many different fields such as image analysis, text analysis, or medicine. Still, the good performance of deep models in controlled environments might not necessarily translate to their success in real-world settings. Take, for example, deep models intended for autonomous driving. They will most likely be trained to recognize the most common elements of driving scenes, such as cars, people, road tracks, etc. So, what happens if an elephant suddenly appears in front of the car? Our models can only classify it into one of the known classes. We could modify our training data to include elephants, but ultimately it is impossible to foresee every possible scenario. The next best thing is to equip deep models with the ability to say they do not know the correct answer. This ability of deep models to recognize potential failure is critical for their safe deployment in real-world applications.

In this project, we will train simple image classification models, test their performance on expected inputs, and see how they respond to unexpected data. We will discuss potential methods for detecting model failure and see how we can compare different models with respect to their ability to detect anomalies. We will look at possible modifications to the model and training procedure that increase robustness to unusual input. Finally, we will combine the acquired insights to produce better classification models.

Petra Bevandic
University of Zagreb, Faculty of Electrical Engineering and Computing

Petra is a last-year PhD student and teaching assistant at the Faculty of Electrical Engineering and Computing at the University of Zagreb. Her research is in the field of image analysis, primarily of road driving images. She focuses on improving model robustness for real-world applications. Currently, she is trying to figure out how to automatically connect visual concepts across multiple datasets to train general-purpose models. Outside of work, she enjoys painting, classic movies, books, yoga, and pub quizzes.

More coming soon...


Coming soon...


Lecture schedule

Coming soon...