DiffPathV2 detects out-of-distribution images by measuring weighted errors in a pretrained diffusion model's predicted noise, without retraining on the target dataset.
Title resolution pending
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
-
Zero-Shot Image Anomaly Detection Using Generative Foundation Models
DiffPathV2 detects out-of-distribution images by measuring weighted errors in a pretrained diffusion model's predicted noise, without retraining on the target dataset.