Nicolas Larue

Nicolas Larue

Final-year PhD Candidate in Machine Learning — Generative AI Robustness, Model Evaluation, Self-Supervised Learning, Computer Vision

SeeABLE: Soft Discrepancies and Bounded Contrastive Learning for Exposing Deepfakes

Published in ICCV 2023, 2023

Recommended citation: Nicolas Larue, Ngoc-Son Vu, Vitomir Štruc, Peter Peer, Vassilis Christophides. SeeABLE: Soft Discrepancies and Bounded Contrastive Learning for Exposing Deepfakes. ICCV 2023. https://openaccess.thecvf.com/content/ICCV2023/html/Larue_SeeABLE_Soft_Discrepancies_and_Bounded_Contrastive_Learning_for_Exposing_Deepfakes_ICCV_2023_paper.html

Contrastive learning framework for robust deepfake detection and generalization to unseen synthetic media.

Paper