Table 2 Patch-level ACA (P. ACA, %) of RN on Validation Sets during Different Iterations of DRAL
From: Reverse active learning based atrous DenseNet for pathological image classification
DRAL (Iteration number K) | BACH | CCG | UCSB | |||
|---|---|---|---|---|---|---|
Training set | P. ACA | Training set | P. ACA | Training set | P. ACA | |
trained with original training set (K=0) | 89,600 | 89.16 | 362,832 | 77.87 | 68,640 | 76.40 |
K=1 | 89,026 | 89.58 | 361,007 | 83.88 | 64,944 | 94.24 |
K=2 | 88,170 | 89.71 | 360,563 | 82.88 | 64,200 | 93.23 |
K=3 | 87,363 | 92.81 | - | - | - | - |
K=4 | 86,858 | 92.14 | - | - | - | - |