[en] We propose a novel semi-supervised learning method for leveraging unlabeled data by generating pseudo labels with a teacher-student approach. We also introduce three loss parametrizations to introduce doubt in the pseudo labels based on their confidence scores. Finally, we show that our method allows to improve detection performance for satellite images.
Author, co-author :
Vandeghen, Renaud ✱; Université de Liège - ULiège > Département d'électricité, électronique et informatique (Institut Montefiore) > Télécommunications
Cioppa, Anthony ✱; Université de Liège - ULiège > Montefiore Institute of Electrical Engineering and Computer Science
Van Droogenbroeck, Marc ; Université de Liège - ULiège > Montefiore Institute of Electrical Engineering and Computer Science
✱ These authors have contributed equally to this work.
Semi-Supervised Training to Improve Detection for Satellite Images
Publication date :
03 May 2022
Number of pages :
Event name :
AI4Copernicus: Earth Observation and Artificial Intelligence for a Safer World
Event organizer :
The Copernicus Relays of Belgium (Skywin, ISSeP, Spacebel and VITO) and the Belgian Royal Military Academy