Table 3 Ablation results of the graph convolutional feature extraction block and the residual gated recurrent unit in R-GNN
From: R-GNN: recurrent graph neural networks for font classification of oracle bone inscriptions
GC block | GRU | Attention | LSTM | R-GRU | Top-1 |
|---|---|---|---|---|---|
✓ | ✗ | ✗ | ✗ | ✗ | 0.855 |
✓ | ✗ | ✓ | ✗ | ✗ | 0.871 |
✓ | ✗ | ✗ | ✓ | ✗ | 0.869 |
✓ | ✓ | ✗ | ✗ | ✗ | 0.874 |
✓ | ✗ | ✗ | ✗ | ✓ | 0.877 |