Lundi 27 juin 2016 Alexander Gepperth, enseignant-chercheur au laboratoire d'informatique et d'ingénierie des systèmes (U2IS) a soutenu son HDR.
Résumé de son travail présenté à cette occasion :
In this presentation, I first analyze some of the reasons why real-world environment perception is still strongly inferior to human perception in overall accuracy and reliability. In particular, I focus on the task of object detection in traffic scenes and present an argument why this task is in fact a good model task for other, related perception problems (e.g. in robotics or surveillance).
Discussing the difficulties encountered in this model task, I come to the conclusion that problems in object detection can in fact be, to a significant extent, traced back to problems of the underlying learning algorithms. Namely, the lack of a probabilistic interpretation, the lack of incremental learning capacity, the lack of training samples and the inherent ambiguity of local pattern analysis are identified and used to justify a road map for research efforts aimed at overcoming these problems. I present several of my works concerning real-world applications of machine learning in perception, where the stated problems become very apparent. Subsequently, I describe in detail my recent research contributions and their significance in the context of the proposed road map: context-based object detection, generative and multi-modal learning as well as an original method for incremental learning.
