Improving uncertainty estimation in deep neural networks by modeling class and instance uncertainty
Dimitrios Spanos, Nikolaos Passalis, Anastasios Tefas · Pattern Recognition · 2025
• A deep learning method that models data uncertainty for uncertainty estimation is proposed. • A method that generates soft labels in an adaptive manner is used for the optimization. • The uncertainty-aware learning process improves state-of-the-art methodologies in out-of-distribution detection. In the pursuit of enhancing the trustworthiness of deep learning models, there has been a growing interest in improving their uncertainty estimation for more reliable decision-making. Recent methodologies have concentrated on refining uncertainty estimation particularly in the context of identifying out-of-distribution input samples. This work introduces and explores two distinct categories of uncertainty: class uncertainty and instance uncertainty . The former highlights uncertainty stemming from inter-class resemblances, while the latter addresses analogous uncertainty within individual instances. We propose a novel framework, Adaptive Similarity Labeling (ASL), that captures both class-level and instance-level uncertainty by adaptively assigning soft labels based on semantic similarity and instance difficulty. ASL mitigates feature collapse and improves uncertainty estimation without adding inference-time overhead, and can be used regardless of the uncertainty metric used. The proposed approach is architecture-agnostic and can be combined with recent state-of-the-art architectures for uncertainty estimation. Experiments conducted on several datasets demonstrate the effectiveness of ASL in improving uncertainty estimation and out-of-distribution detection across diverse tasks.