LoRA-based pairwise training with distortion and size simulations boosts robust AIGI detection under severe distortions, placing third in the NTIRE challenge.
Oddn: Addressing unpaired data challenges in open-world deepfake detection on online social networks
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Boosting Robust AIGI Detection with LoRA-based Pairwise Training
LoRA-based pairwise training with distortion and size simulations boosts robust AIGI detection under severe distortions, placing third in the NTIRE challenge.