HyperAI

Multiple Instance Learning On Camelyon16

Metrics

ACC
AUC

Results

Performance results of various models on this benchmark

Model Name
ACC
AUC
Paper TitleRepository
DSMIL0.86820.8944Dual-stream Multiple Instance Learning Network for Whole Slide Image Classification with Self-supervised Contrastive Learning
Snuffy (DINO Exhaustive)0.9480.987Snuffy: Efficient Whole Slide Image Classifier
CAMIL0.9170.959CAMIL: Context-Aware Multiple Instance Learning for Cancer Detection and Subtyping in Whole Slide Images
DGMIL0.80180.8368DGMIL: Distribution Guided Multiple Instance Learning for Whole Slide Image Classification
TransMIL0.88370.9309TransMIL: Transformer based Correlated Multiple Instance Learning for Whole Slide Image Classification
DSMIL-LC0.89920.9165Dual-stream Multiple Instance Learning Network for Whole Slide Image Classification with Self-supervised Contrastive Learning
DTFD-MIL (AFS)0.9080.946DTFD-MIL: Double-Tier Feature Distillation Multiple Instance Learning for Histopathology Whole Slide Image Classification
DTFD-MIL (MaxS)0.8640.907DTFD-MIL: Double-Tier Feature Distillation Multiple Instance Learning for Histopathology Whole Slide Image Classification
Snuffy (MAE Adapter)0.9000.910Snuffy: Efficient Whole Slide Image Classifier
CAMIL (CAMIL-G)0.8910.95CAMIL: Context-Aware Multiple Instance Learning for Cancer Detection and Subtyping in Whole Slide Images
Snuffy (SimCLR Exhaustive)0.9520.970Snuffy: Efficient Whole Slide Image Classifier
CAMIL (CAMIL-L)0.910.953CAMIL: Context-Aware Multiple Instance Learning for Cancer Detection and Subtyping in Whole Slide Images
DTFD-MIL (MAS)0.8970.945DTFD-MIL: Double-Tier Feature Distillation Multiple Instance Learning for Histopathology Whole Slide Image Classification
DTFD-MIL (MaxMinS)0.8990.941DTFD-MIL: Double-Tier Feature Distillation Multiple Instance Learning for Histopathology Whole Slide Image Classification
0 of 14 row(s) selected.