17 papers
When AUC Misleads: Polarization-Aware Evaluation of Deepfake Detectors under Domain Shift
Dat Nguyen, Cosmin Radoi, Romain Hermary +4
Recent advances in generative AI, such as diffusion models and face-swapping tools, have enabled the creation of highly realistic deepfakes, leading to real-world harms including f…
LAA-X: Unified Localized Artifact Attention for Quality-Agnostic and Generalizable Face Forgery Detection
Dat Nguyen, Enjie Ghorbel, Anis Kacem +2
In this paper, we propose Localized Artifact Attention X (LAA-X), a novel deepfake detection framework that is both robust to high-quality forgeries and capable of generalizing to…
Cov2Pose: Leveraging Spatial Covariance for Direct Manifold-aware 6-DoF Object Pose Estimation
Nassim Ali Ousalah, Peyman Rostami, Vincent Gaudillière +4
In this paper, we address the problem of 6-DoF object pose estimation from a single RGB image. Indirect methods that typically predict intermediate 2D keypoints, followed by a Pers…
When Unsupervised Domain Adaptation meets One-class Anomaly Detection: Addressing the Two-fold Unsupervised Curse by Leveraging Anomaly Scarcity
Nesryne Mejri, Enjie Ghorbel, Anis Kacem +3
This paper introduces the first fully unsupervised domain adaptation (UDA) framework for unsupervised anomaly detection (UAD). The performance of UAD techniques degrades significan…
FPG-NAS: FLOPs-Aware Gated Differentiable Neural Architecture Search for Efficient 6DoF Pose Estimation
Nassim Ali Ousalah, Peyman Rostami, Anis Kacem +3
We introduce FPG-NAS, a FLOPs-aware Gated Differentiable Neural Architecture Search framework for efficient 6DoF object pose estimation. Estimating 3D rotation and translation from…
Uncertainty-Aware Knowledge Distillation for Compact and Efficient 6DoF Pose Estimation
Nassim Ali Ousalah, Anis Kacem, Enjie Ghorbel +2
Compact and efficient 6DoF object pose estimation is crucial in applications such as robotics, augmented reality, and space autonomous navigation systems, where lightweight models…