Gala (Galadrielle Humblot-Renaux)

DDSA PhD Fellow

neo.jpg

important cat

I’m a PhD student in the Visual Analysis & Perception lab @ Aalborg University, Denmark, under the supervision of Sergio Escalera & Thomas Moeslund. I have a background in engineering & robotic perception, and after receiving a scholarship from the Danish Data Science Academy, I am now working at the intersection of computer vision & uncertainty. I like questioning the trustworthiness of deep learning models & how we evaluate them. Lately I’ve been especially interested in the problems of out-of-distribution detection and data/label uncertainty.

Education:

selected publications

  1. ECCVW’24
    Underwater Uncertainty: A Multi-Annotator Image Dataset for Benthic Habitat Classification
    Galadrielle Humblot-Renaux, Anders Skaarup Johansen, Jonathan Eichild Schmidt, Amanda Frederikke Irlind, Niels Madsen, Thomas B. Moeslund, and Malte Pedersen
    In Computer Vision – ECCV 2024 Workshops , 2024
  2. CVPR’24
    A noisy elephant in the room: Is your out-of-distribution detector robust to label noise?
    Galadrielle Humblot-Renaux, Sergio Escalera, and Thomas B. Moeslund
    In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) , 2024
  3. CVPRW’23
    Beyond AUROC & Co. for Evaluating Out-of-Distribution Detection Performance
    Galadrielle Humblot-Renaux, Sergio Escalera, and Thomas B. Moeslund
    In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops , Jun 2023
  4. ICRA’22
    Navigation-Oriented Scene Understanding for Robotic Autonomy: Learning to Segment Driveability in Egocentric Images
    Galadrielle Humblot-Renaux, Letizia Marchegiani, Thomas B. Moeslund, and Rikke Gade
    IEEE Robotics and Automation Letters, Jun 2022