About us
Espace utilisateur
Education
INSTN offers more than 40 diplomas from operator level to post-graduate degree level. 30% of our students are international students.
Professionnal development
Professionnal development
Find a training course
INSTN delivers off-the-self or tailor-made training courses to support the operational excellence of your talents.
Human capital solutions
At INSTN, we are committed to providing our partners with the best human capital solutions to develop and deliver safe & sustainable projects.
Thesis
Home   /   Thesis   /   Out-of-Distribution Detection with Vision Foundation Models and Post-hoc Methods

Out-of-Distribution Detection with Vision Foundation Models and Post-hoc Methods

Artificial intelligence & Data intelligence Automatics, Remote handling Engineering sciences Technological challenges

Abstract

The thesis focuses on improving the reliability of deep learning models, particularly in detecting out-of-distribution (OoD) samples, which are data points that differ from the training data and can lead to incorrect predictions. This is especially important in critical fields like healthcare and autonomous vehicles, where errors can have serious consequences. The research leverages vision foundation models (VFMs) like CLIP and DINO, which have revolutionized computer vision by enabling learning from limited data. The proposed work aims to develop methods that maintain the robustness of these models during fine-tuning, ensuring they can still effectively detect OoD samples. Additionally, the thesis will explore solutions for handling changing data distributions over time, a common challenge in real-world applications. The expected results include new techniques for OoD detection and adaptive methods for dynamic environments, ultimately enhancing the safety and reliability of AI systems in practical scenarios.

Laboratory

Département Ingénierie Logiciels et Systèmes (LIST)
LSEA (DILS)
Labo.conception des systèmes embarqués et autonomes
Paris-Saclay
Top envelopegraduation-hatlicensebookuserusersmap-markercalendar-fullbubblecrossmenuarrow-down