Hyperbolic Active Learning for Semantic Segmentation under Domain Shift

arXiv:2306.11180v4 Announce Type: replace
Abstract: We introduce a hyperbolic neural network approach to pixel-level active learning for semantic segmentation. Analysis of the data statistics leads to a novel interpretation of the hyperbolic radius as an indicator of data scarcity. In HALO (Hyperbolic Active Learning Optimization), for the first time, we propose the use of epistemic uncertainty as a data acquisition strategy, following the intuition of selecting data points that are the least known. The hyperbolic radius, complemented by the widely-adopted …

abstract active learning analysis arxiv cs.ai cs.cv data domain halo interpretation leads network neural network novel optimization pixel segmentation semantic shift statistics type