Is Vehicle Plate Corner Prediction by Vision Transformer Better than CNNs?

Figure 5

The validation losses of the ViT models according to different combinations of the four structural parameters. (a) Validation loss according to patch size, (b) loss according to depth, (c) loss depending on embedding dimension, and (d) loss in relation with number of heads of the proposed architecture.

(a)

(b)

(c)

(d)