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.
A baseline for detect- ing misclassified and out-of-distribution examples in neural networks
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
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.