15 citations · 21 across the 7 of their papers we have counts for
10 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…
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…
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…
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…
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…
COOkeD: Ensemble-based OOD detection in the era of zero-shot CLIP
Galadrielle Humblot-Renaux, Gianni Franchi, Sergio Escalera +1
Out-of-distribution (OOD) detection is an important building block in trustworthy image recognition systems as unknown classes may arise at test-time. OOD detection methods typical…
Foundation Models and Transformers for Anomaly Detection: A Survey
Mouïn Ben Ammar, Arturo Mendoza, Nacim Belkhir +2
In line with the development of deep learning, this survey examines the transformative role of Transformers and foundation models in advancing visual anomaly detection (VAD). We ex…
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…
NECO: NEural Collapse Based Out-of-distribution detection
Mouïn Ben Ammar, Nacim Belkhir, Sebastian Popescu +2
Detecting out-of-distribution (OOD) data is a critical challenge in machine learning due to model overconfidence, often without awareness of their epistemological limits. We hypoth…
Scaling for Training Time and Post-hoc Out-of-distribution Detection Enhancement
Kai Xu, Rongyu Chen, Gianni Franchi +1
The capacity of a modern deep learning system to determine if a sample falls within its realm of knowledge is fundamental and important. In this paper, we offer insights and analys…