A novel loss function enables effective segmentation training from summary statistics combined with minimal weak pixel supervision, outperforming statistics alone on medical imaging tasks.
Proceedings of the 2022 International Conference on Multimedia Retrieval , pages =
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Learning to Segment using Summary Statistics and Weak Supervision
A novel loss function enables effective segmentation training from summary statistics combined with minimal weak pixel supervision, outperforming statistics alone on medical imaging tasks.