Towards Calibrated Deep Clustering Network

arXiv:2403.02998v1 Announce Type: new
Abstract: Deep clustering has exhibited remarkable performance; however, the overconfidence problem, i.e., the estimated confidence for a sample belonging to a particular cluster greatly exceeds its actual prediction accuracy, has been overlooked in prior research. To tackle this critical issue, we pioneer the development of a calibrated deep clustering framework. Specifically, we propose a novel dual-head deep clustering pipeline that can effectively calibrate the estimated confidence and the actual accuracy. The calibration head adjusts the overconfident …

abstract accuracy arxiv cluster clustering confidence cs.cv development framework issue network performance prediction prior research sample type