Dream-Box generates object-level pixel-space outliers with a diffusion model to train an object detector for out-of-distribution detection, enabling visualization but with lower accuracy than feature-space alternatives.
Barker, Neelanjan Bhowmik, and Toby P
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
-
Dream-Box: Object-wise Outlier Generation for Out-of-Distribution Detection
Dream-Box generates object-level pixel-space outliers with a diffusion model to train an object detector for out-of-distribution detection, enabling visualization but with lower accuracy than feature-space alternatives.