A LoRA-enhanced vision transformer for generalized and robust continual face forgery detection
In this dissertation, we present an efficient training method for face forgery detection models by combining Low-rank adaptation (LoRA) with Vision Transformers (ViT). The approach facilitates continual learning across multiple face forgery datasets organized by their release dates, followed b...
Saved in:
Main Author: | Wu, Yulong |
---|---|
Other Authors: | Alex Chichung Kot |
Format: | Thesis-Master by Coursework |
Language: | English |
Published: |
Nanyang Technological University
2025
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/182478 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
Similar Items
-
Application of the V-HUB Standard using LoRa Beacons, Mobile Cloud, UAVs, and DTN for Disaster-Resilient Communications
by: Solpico, D, et al.
Published: (2019) -
Few-shot forgery detection via guided adversarial interpolation
by: Qiu, Haonan, et al.
Published: (2023) -
Seeing your Face is not Enough: An Inertial Sensor-based Liveness Detection for Face Authentication
by: Li, Yan, et al.
Published: (2015) -
Copy-move image forgery detection based on evolving circular domains coverage
by: Lu, Shilin, et al.
Published: (2022) -
Practical Forgeries and Distinguishers against PAES
by: Jean, Jérémy, et al.
Published: (2016)