CLOFAI is a new domain-incremental benchmark where a classifier must detect fake images from five generative model types in sequence; replay methods beat the naive baseline, while EWC does not.
Using Noise to Compute Error Sur- faces in Connectionist Networks: A Novel Means of Reducing Catastrophic Forgetting
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
CLOFAI: A Dataset of Real And Fake Image Classification Tasks for Continual Learning
CLOFAI is a new domain-incremental benchmark where a classifier must detect fake images from five generative model types in sequence; replay methods beat the naive baseline, while EWC does not.