Saved in:
Bibliographic Details
Main Authors: Reddy, Shukesh, Das, Srijan, Das, Abhijit
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2601.00789
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918269616652288
author Reddy, Shukesh
Das, Srijan
Das, Abhijit
author_facet Reddy, Shukesh
Das, Srijan
Das, Abhijit
contents In this work, we attempted to unleash the potential of self-supervised learning as an auxiliary task that can optimise the primary task of generalised deepfake detection. To explore this, we examined different combinations of the training schemes for these tasks that can be most effective. Our findings reveal that fusing the feature representation from self-supervised auxiliary tasks is a powerful feature representation for the problem at hand. Such a representation can leverage the ultimate potential and bring in a unique representation of both the self-supervised and primary tasks, achieving better performance for the primary task. We experimented on a large set of datasets, which includes DF40, FaceForensics++, Celeb-DF, DFD, FaceShifter, UADFV, and our results showed better generalizability on cross-dataset evaluation when compared with current state-of-the-art detectors.
format Preprint
id arxiv_https___arxiv_org_abs_2601_00789
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Fusion-SSAT: Unleashing the Potential of Self-supervised Auxiliary Task by Feature Fusion for Generalized Deepfake Detection
Reddy, Shukesh
Das, Srijan
Das, Abhijit
Computer Vision and Pattern Recognition
In this work, we attempted to unleash the potential of self-supervised learning as an auxiliary task that can optimise the primary task of generalised deepfake detection. To explore this, we examined different combinations of the training schemes for these tasks that can be most effective. Our findings reveal that fusing the feature representation from self-supervised auxiliary tasks is a powerful feature representation for the problem at hand. Such a representation can leverage the ultimate potential and bring in a unique representation of both the self-supervised and primary tasks, achieving better performance for the primary task. We experimented on a large set of datasets, which includes DF40, FaceForensics++, Celeb-DF, DFD, FaceShifter, UADFV, and our results showed better generalizability on cross-dataset evaluation when compared with current state-of-the-art detectors.
title Fusion-SSAT: Unleashing the Potential of Self-supervised Auxiliary Task by Feature Fusion for Generalized Deepfake Detection
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2601.00789