AI RESEARCH
RADMI: Latent Information Aggregation as a Proxy for Model Uncertainty
arXiv CS.CV
•
ArXi:2605.01502v1 Announce Type: new Epistemic uncertainty estimation is essential for identifying regions where deep learning system outputs may be unreliable. However, existing approaches require computationally expensive ensemble methods or multiple stochastic forward passes, limiting their scalability to dense prediction tasks like segmentation. We propose Resolution-Aggregated Decoder Mutual Information (RADMI), a single-pass method that estimates prediction uncertainty by measuring mutual information (MI) between consecutive decoder layers in segmentation networks.