CDAL adds a counterfactual attention branch to open-world model attribution, improving novel-attack attribution by several points on OW-DFA and OSMA.
On the detection of digital face manipulation
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Learning Counterfactually Decoupled Attention for Open-World Model Attribution
CDAL adds a counterfactual attention branch to open-world model attribution, improving novel-attack attribution by several points on OW-DFA and OSMA.