EURASIP Journal on Image and Video Processing

Table 2 Comparison of the output results of the middle part features

From: Anchor-free object detection with mask attention

Feature map	Stacks_1	Stacks_2	Stacks_1 + Stacks_2
Accuracy	92.95	91.72	91.63
Recall	82.34	89.76	89.83

Back to article page