A curriculum-based test-time adaptation method, using balanced confident pseudo-labels and multi-scale refinement, improves AIGC detector accuracy on unseen generators by 11 to 29 points over its starting detector.
2019 IEEE international conference on image processing (ICIP) , pages=
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Test-Time Curriculum for Open-Set AIGC Detection
A curriculum-based test-time adaptation method, using balanced confident pseudo-labels and multi-scale refinement, improves AIGC detector accuracy on unseen generators by 11 to 29 points over its starting detector.