Table 4 Comparison with other state-of-the-art methods on the NEU-DET dataset.

From: Balancing complexity and accuracy for defect detection on filters with an improved RT-DETR

Model

mAP@0.5(%)

YOLOX (Li et al.21)

77.0

YOLOv5n (Tian et al.22)

75.3

RT-DETR-LGA (Ours, average)

80.28

Back to article page