3 papers
cs.CV2026
From Local Geometry to Global Pseudo Labeling for Robust Positive Unlabeled Learning under Covariate Shift
Firas Gabetni, Alexandre Rocchi, Nacim Belkhir +2
Detecting covariate shift is critical for building reliable vision systems. While most prior work focuses on improving robustness to shift, explicitly detecting covariate shift rem…
cs.LG2025
Torch-Uncertainty: A Deep Learning Framework for Uncertainty Quantification
Adrien Lafage, Olivier Laurent, Firas Gabetni +1
Deep Neural Networks (DNNs) have demonstrated remarkable performance across various domains, including computer vision and natural language processing. However, they often struggle…
cs.LG2025
Ensembling Pruned Attention Heads For Uncertainty-Aware Efficient Transformers
Firas Gabetni, Giuseppe Curci, Andrea Pilzer +3
Uncertainty quantification (UQ) is essential for deploying deep neural networks in safety-critical settings. Although methods like Deep Ensembles achieve strong UQ performance, the…