A two-branch MIL training method with self-confidence losses and attention calibration improves bag- and instance-level whole-slide image classification on CAMELYON16 and TCGA-NSCLC over WENO and MHIM-MIL baselines.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Denoising Mutual Knowledge Distillation in Bi-Directional Multiple Instance Learning
A two-branch MIL training method with self-confidence losses and attention calibration improves bag- and instance-level whole-slide image classification on CAMELYON16 and TCGA-NSCLC over WENO and MHIM-MIL baselines.