8 papers
Disentangling Hallucinations: Orthogonal Semantic Projection for Robust Interpretability
Emirhan Bilgiç, Baptiste Caramiaux, Zhi Yan +1
As Vision-Language Models are increasingly deployed in safety-critical applications, the trustworthiness of their explanations becomes crucial. Explainable AI (XAI) methods for Vis…
A Geometric Unification of Concept Learning with Concept Cones
Alexandre Rocchi, Thomas Fel, Gianni Franchi
Two traditions of interpretability have evolved side by side but seldom spoken to each other: Concept Bottleneck Models (CBMs), which prescribe what a concept should be, and Sparse…
From Local Geometry to Global Pseudo Labeling for Robust Positive Unlabeled Learning under Covariate Shift
Firas Gabetni, Alexandre Rocchi Henry, Alexandre Rocchi +3
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…
SS3D: End2End Self-Supervised 3D from Web Videos
Marwane Hariat, Gianni Franchi, David Filliat +1
We present SS3D, a web-scale SfM-based self-supervision pretraining pipeline for feed-forward 3D estimation from monocular video. Our model jointly predicts depth, ego-motion, and…
FakeParts: a New Family of AI-Generated DeepFakes
Ziyi Liu, Firas Gabetni, Awais Hussain Sani +5
We introduce FakeParts, a new class of deepfakes characterized by subtle, localized manipulations to specific spatial regions or temporal segments of otherwise authentic videos. Un…
Double Descent Meets Out-of-Distribution Detection: Theoretical Insights and Empirical Analysis on the role of model complexity
Mouïn Ben Ammar, David Brellmann, Arturo Mendoza +2
Out-of-distribution (OOD) detection is essential for ensuring the reliability and safety of machine learning systems. In recent years, it has received increasing attention, particu…