Table 3.
Configurations of CA-Conv-LSTM architectures.
Model | CNN model | Class Attention Map | Bi. |
---|---|---|---|
CA-VGG-LSTM | VGG-16 | ![]() |
|
CA-VGG-BiLSTM | VGG-16 | ✓ | |
CA-GoogLeNet-LSTM | Inception-v3 | ![]() |
|
CA-GoogLeNet-BiLSTM | Inception-v3 | ✓ | |
CA-ResNet-LSTM | ResNet-50 | ![]() |
|
CA-ResNet-BiLSTM | ResNet-50 | ✓ |
N indicates the number of classes in the dataset.
Bi. indicates whether the model is bidirectional or not.