FodFoM generates fake OOD images from ID semantics via shifted CLIP text embeddings and blurred backgrounds, and uses them to train classifiers that set new SOTA OOD detection scores on CIFAR10/100 and ImageNet100.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
FodFoM: Fake Outlier Data by Foundation Models Creates Stronger Visual Out-of-Distribution Detector
FodFoM generates fake OOD images from ID semantics via shifted CLIP text embeddings and blurred backgrounds, and uses them to train classifiers that set new SOTA OOD detection scores on CIFAR10/100 and ImageNet100.