PC-MIL shows that anchoring supervision at a 2 mm scale and progressively mixing slide- and region-level labels improves cross-context accuracy in WSI cancer detection without reducing global performance.
In: International conference on machine learning
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
AC-MIL adds an adversarial residual branch and spatial diversity constraint to multiple instance learning so that volume-level quality labels produce localized, interpretable concept maps while preserving competitive grading accuracy.
citing papers explorer
-
PC-MIL: Decoupling Feature Resolution from Supervision Scale in Whole-Slide Learning
PC-MIL shows that anchoring supervision at a 2 mm scale and progressively mixing slide- and region-level labels improves cross-context accuracy in WSI cancer detection without reducing global performance.
-
AC-MIL: Weakly Supervised Atrial LGE-MRI Quality Assessment via Adversarial Concept Disentanglement
AC-MIL adds an adversarial residual branch and spatial diversity constraint to multiple instance learning so that volume-level quality labels produce localized, interpretable concept maps while preserving competitive grading accuracy.