Unbalancedness in Neural Monge Maps Improves Unpaired Domain Translation

arXiv:2311.15100v2 Announce Type: replace-cross
Abstract: In optimal transport (OT), a Monge map is known as a mapping that transports a source distribution to a target distribution in the most cost-efficient way. Recently, multiple neural estimators for Monge maps have been developed and applied in diverse unpaired domain translation tasks, e.g. in single-cell biology and computer vision. However, the classic OT framework enforces mass conservation, which makes it prone to outliers and limits its applicability in real-world scenarios. The latter can …

abstract arxiv cost cs.ai cs.cv cs.lg distribution diverse domain map mapping maps multiple tasks translation transport type