Skip to main content
To KTH's start page To KTH's start page

On Label Noise in Image Classification

An Aleatoric Uncertainty Perspective

Time: Mon 2024-06-03 09.00

Location: F3 (Flodis), Lindstedsvägen 26 & 28

Video link:

Language: English

Subject area: Computer Science

Doctoral student: Erik Englesson , Robotik, perception och lärande, RPL

Opponent: Professor Gustavo Carneiro, University of Surrey

Supervisor: Associate Professor Hossein Azizpour, Robotik, perception och lärande, RPL; Associate Professor Morteza Haghir Chehreghani, Chalmers University of Technology, Gothenburg, Sweden

Export to calendar

QC 20240516


Deep neural networks and large-scale datasets have revolutionized the field of machine learning. However, these large networks are susceptible to overfitting to label noise, resulting in generalization degradation. In response, the thesis closely examines the problem both from an empirical and theoretical perspective. We empirically analyse the input smoothness of networks as they overfit to label noise, and we theoretically explore the connection to aleatoric uncertainty. These analyses improve our understanding of the problem and have led to our novel methods aimed at enhancing robustness against label noise in classification.