Hybrid Open-set Segmentation with Synthetic Negative Data

arXiv:2301.08555v3 Announce Type: replace
Abstract: Open-set segmentation can be conceived by complementing closed-set classification with anomaly detection. Many of the existing dense anomaly detectors operate through generative modelling of regular data or by discriminating with respect to negative data. These two approaches optimize different objectives and therefore exhibit different failure modes. Consequently, we propose a novel anomaly score that fuses generative and discriminative cues. Our score can be implemented by upgrading any closed-set segmentation model with dense estimates of dataset …

abstract anomaly anomaly detection arxiv classification cs.cv data detection detectors failure generative hybrid modelling negative segmentation set synthetic through type