A framework decomposes segmentation evaluation metrics into five modular stages to expose assumptions and compare design choices across metrics.
Bilateral reference for high-resolution dichotomous image segmentation.CAAI Artificial Intelligence Research, 3:9150038, 2024
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
-
Beyond Pixel Overlap: A Framework for Decomposing Segmentation Evaluation Metrics
A framework decomposes segmentation evaluation metrics into five modular stages to expose assumptions and compare design choices across metrics.