Catalyst improves OOD detection by multiplicatively scaling baseline scores using channel-wise statistics from pre-pooling feature maps, reducing average FPR by 22-33% on standard benchmarks.
Title resolution pending
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
dataset 1
citation-polarity summary
fields
cs.CV 3years
2026 3roles
dataset 1polarities
use dataset 1representative citing papers
ROSS combines median smoothing with local instability measurement to create a robust OOD detector that outperforms prior methods by up to 40 AUROC points on CIFAR and ImageNet benchmarks while defending symmetrically against score attacks.
DynProto dynamically builds OOD prototypes from ID-only data via coarse caching and fine clustering of confused samples to improve OOD detection in VLMs, cutting FPR95 by 11.6% on ImageNet benchmarks.
citing papers explorer
-
Catalyst: Out-of-Distribution Detection via Elastic Scaling
Catalyst improves OOD detection by multiplicatively scaling baseline scores using channel-wise statistics from pre-pooling feature maps, reducing average FPR by 22-33% on standard benchmarks.
-
A Robust Out-of-Distribution Detection Framework via Synergistic Smoothing
ROSS combines median smoothing with local instability measurement to create a robust OOD detector that outperforms prior methods by up to 40 AUROC points on CIFAR and ImageNet benchmarks while defending symmetrically against score attacks.
-
DynProto: Dynamic Prototype Evolution for Out-of-Distribution Detection
DynProto dynamically builds OOD prototypes from ID-only data via coarse caching and fine clustering of confused samples to improve OOD detection in VLMs, cutting FPR95 by 11.6% on ImageNet benchmarks.