Visualizing Uncertainty: Spatial Maps of Missing and Conflicting Evidence in Deep Learning
Researchers have introduced a new framework called Uncertainty Activation Map (UAM) to visualize uncertainty in deep learning models. This method combines Evidential Deep Learning with Full-Gradient Class Activation Mapping to create spatial maps that highlight areas of missing or conflicting evidence within input data. The UAM framework distinguishes between vacuity (lack of evidence) and dissonance (conflicting evidence), offering a more interpretable understanding of model reliability for safety-critical applications. AI
IMPACT Enhances interpretability of deep learning models by visualizing uncertainty, crucial for reliable deployment in safety-critical domains.