Deepfakes are images and videos which combine mixed source material to produce a synthetic result. Their use ranges from trivial to malicious, so methods to detect them are sought after, with the latest techniques often based on networks trained using pairs of original and synthesized images. A new method defies this convention by training algorithms using novel synthesized images created in a unique way. Known as self-blended images, these novel training data can demonstrably improve algorithms designed to spot deepfake images and video.
from News on Artificial Intelligence and Machine Learning https://ift.tt/OFnydur
Home
machine-learning-ai-news
News on Artificial Intelligence and Machine Learning
A new way to train deepfake detection algorithms improves their success
- Blogger Comment
- Facebook Comment
Subscribe to:
Post Comments
(
Atom
)
0 comments:
Post a Comment