HyperRPS: An Efficient Multi-Fidelity Hyper-Parameter Tuning Framework for Rock Particle Segmentation
Tsinghua Science and Technology (TST), 2026.
* Equal contribution.
Overview
HyperRPS expands the hyperparameter search space for rock particle segmentation and accelerates tuning through multi-fidelity surrogate fitting and time-constraint modeling. It also manages intermediate model storage during asynchronous scheduling.