Tag: out-of-distribution detection

A new open-set recognition network flags tomato leaf images from disease classes it was never trained on, outperforming standard baselines ...

A new Applied Intelligence study proposes UOMC, a multi-view classification model that quantifies view-specific uncertainty and reports accuracy gains on ...

Researchers have combined neutrosophic set theory with deep feature geometry to give pretrained neural networks an interpretable, three-part measure of ...

A new survey of 161 studies maps how out-of-distribution data undermines AI-based mechanical fault diagnosis and argues that generalization, calibrated ...

Hybrid classical-quantum neural networks have rapidly become one of the most actively pursued directions in quantum machine learning, promising classification ...

Machine learning models are famously confident, sometimes catastrophically so. Ask a survival model to estimate a cancer patient's five-year prognosis ...