Multi-Objective Optimization for Deep Neural Network Calibration

Dexter Neo, Tsuhan Chen; Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops, 2025, pp. 6280-6291

The rapid adoption of deep neural networks underscores an urgent need for models to be safe, trustworthy and well-calibrated. Despite recent advancements in network calibration, the optimal unification of techniques remains relatively unexplored. By framing the task as a multi-objective optimization problem, we demonstrate that unifying state-of-the-art methods can further boost calibration performance. We feature a total of seven state-of-the-art calibration algorithms and provide both theoretical and empirical motivation for their equal and weighted importance unification. We conduct experiments on both in-distribution and out-of-distribution computer vision benchmarks, investigating the speeds and contributions of different components.