Table 2.
Comparison of the performance of the competing algorithms in the form of AUC and AP scores.
Method | AUC | AP |
---|---|---|
CNN () | 0.748 ± 0.035 | 0.498 ± 0.037 |
NoisyAND () | 0.761 ± 0.027 | 0.538 ± 0.037 |
AttentionMIL () | 0.743 ± 0.055 | 0.486 ± 0.095 |
NoisyAND () | 0.845 ± 0.016 | 0.708 ± 0.041 |
AttentionMIL () | 0.823 ± 0.021 | 0.643 ± 0.048 |
AveragePooling () | 0.850 ± 0.025 | 0.693 ± 0.037 |
Proposed () | 0.858 ± 0.017 | 0.719 ± 0.029 |
Proposed () | 0.852 ± 0.024 | 0.713 ± 0.040 |
Proposed () | 0.835 ± 0.024 | 0.693 ± 0.049 |
Proposed () | 0.858 ± 0.014 | 0.721 ± 0.035 |
Proposed () | 0.857 ± 0.018 | 0.733 ± 0.048 |
Proposed2Heads () | 0.860 ± 0.019 | 0.711 ± 0.046 |
Proposed () | 0.870 ± 0.017 | 0.743 ± 0.037 |
Proposed () | 0.860 ± 0.024 | 0.730 ± 0.047 |