BMC Research Notes

Table 3 Performance of the Proposed Vs Existing Models on MS-COCO Dataset

From: MSRP-TODNet: a multi-scale reinforced region wise analyser for tiny object detection

Models	Performance Metrics
Models	Accuracy	Precision	Recall	F1-Score	AUC-ROC
YoLov4-5D [15]	91.86%	92.00%	91.34%	91.79%	0.606
FADNet [16]	92.89%	92.07%	92.40%	92.98%	0.697
OB-SOD [17]	94.86%	94.99%	94.84%	94.97%	0.799
SEPNet [18]	96.15%	96.65%	96.34%	96.26%	0.948
Proposed (MSRP-TODNet)	98.16%	98.89%	99.99%	99.97%	0.995

Back to article page

ISSN: 1756-0500

Contact us

General enquiries: journalsubmissions@springernature.com