“…Thanks to uncertainty measurements, these models have shown superior performance and improved robustness in realistic deployment settings. Moving beyond image models, Xia et al [10], [45], [52] have benchmarked uncertainty estimation methods on various data modalities, i.e., respiratory sounds, heart activity, brain waves, etc. Although uncertainty-aware modeling has been explored in various applications, the existing focus has mainly been on simple Softmax-based approaches that can be overly confident, or MCDP and Ensembles that require substantial com-putational power and are challenging to deploy in realworld scenarios.…”