Attending Generalizability in Course of Deep Fake Detection by Exploring Multi-task Learning - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2023

Attending Generalizability in Course of Deep Fake Detection by Exploring Multi-task Learning

Abstract

This work explores various ways of exploring multi-task learning (MTL) techniques aimed at classifying videos as original or manipulated in cross-manipulation scenario to attend generalizability in deep fake scenario. The dataset used in our evaluation is FaceForensics++, which features 1000 original videos manipulated by four different techniques, with a total of 5000 videos. We conduct extensive experiments on multi-task learning and contrastive techniques, which are well studied in literature for their generalization benefits. It can be concluded that the proposed detection model is quite generalized, i.e., accurately detects manipulation methods not encountered during training as compared to the state-of-the-art.
Fichier principal
Vignette du fichier
ICCVW_Moco_final_pdf.pdf (9.37 Mo) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-04397222 , version 1 (16-01-2024)

Identifiers

Cite

Pranav Balaji, Abhijit Das, Srijan Das, Antitza Dantcheva. Attending Generalizability in Course of Deep Fake Detection by Exploring Multi-task Learning. 2023 IEEE/CVF 6 International Conference on Computer Vision Workshops (ICCVW), Oct 2023, Paris, France. ⟨10.1109/ICCVW60793.2023.00054⟩. ⟨hal-04397222⟩
11 View
18 Download

Altmetric

Share

Gmail Mastodon Facebook X LinkedIn More