An Agile and Efficient Neural Network Based on Knowledge Distillation for Scene Text Detection

Table 1

The results of different pruning ratios. “”, “”, and “” represent “Precision,” “Recall,” and “-score,” respectively.

Method	Pruning ratio	(%)	(%)	(%)
DBNet	—	88.3	82.5	82.8	50
The proposed	0.1	86.5	80.4	83.3	52
The proposed	0.2	86.6	80	83.2	54
The proposed	0.5	89.9	79.1	82.8	57