TransMIL

Reported on 4 benchmarks across 1 task · 1 paper · 1 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Methodology4 results

Multiple Instance LearningonCAMELYON16
AUC· 2021-06-02
0.9309
best: 0.987 (Snuffy (DINO Exhaustive))
SOTA
TransMIL: Transformer based Correlated Multiple Instance Learning for Whole Slide Image Classification arXiv:2106.00908
Multiple Instance LearningonTCGA
ACC· 2021-06-02
0.8835
best: 0.951 (DTFD-MIL (AFS))
TransMIL: Transformer based Correlated Multiple Instance Learning for Whole Slide Image Classification arXiv:2106.00908
Multiple Instance LearningonTCGA
AUC· 2021-06-02
0.9603
best: 0.972 (Snuffy (SimCLR Exhaustive))
TransMIL: Transformer based Correlated Multiple Instance Learning for Whole Slide Image Classification arXiv:2106.00908
Multiple Instance LearningonCAMELYON16
ACC· 2021-06-02
0.8837
best: 0.952 (Snuffy (SimCLR Exhaustive))
TransMIL: Transformer based Correlated Multiple Instance Learning for Whole Slide Image Classification arXiv:2106.00908